@Article{info:doi/10.2196/69021,
author="Zhou, Liang
and Liu, Haoyang
and Fan, Mengjie
and Liu, Jiahao
and Yu, Xingyao
and Zhao, Xintian
and Zhang, Shaoxing",
title="Personal Protection Equipment Training as a Virtual Reality Game in Immersive Environments: Development Study and Pilot Randomized Controlled Trial",
journal="JMIR Serious Games",
year="2025",
month="Mar",
day="20",
volume="13",
pages="e69021",
keywords="virtual reality training",
keywords="nosocomial infections control",
keywords="visualization",
keywords="human computer interaction",
keywords="personal protection equipment",
keywords="PPE",
abstract="Background: Proper donning and doffing of personal protection equipment (PPE) and hand hygiene in the correct spatial context of a health facility is important for the prevention and control of nosocomial infections. On-site training is difficult due to the potential infectious risks and shortages of PPE, whereas video-based training lacks immersion which is vital for the familiarization of the environment. Virtual reality (VR) training can support the repeated practice of PPE donning and doffing in an immersive environment that simulates a realistic configuration of a health facility. Objective: This study aims to develop and evaluate a VR simulation focusing on the correct event order of PPE donning and doffing, that is, the item and hand hygiene order in the donning and doffing process but not the detailed steps of how to don and doff an item, in an immersive environment that replicates the spatial zoning of a hospital. The VR method should be generic and support customizable sequencing of PPE donning and doffing. Methods: An immersive VR PPE training tool was developed by computer scientists and medical experts. The effectiveness of the immersive VR method versus video-based learning was tested in a pilot study as a randomized controlled trial (N=32: VR group, n=16; video-based training, n=16) using questionnaires on spatial-aware event order memorization questions, usability, and task workload. Trajectories of participants in the immersive environment were also recorded for behavior analysis and potential improvements of the real environment of the health facility. Results: Comparable sequence memorization scores (VR mean 79.38, SD 12.90 vs video mean 74.38, SD 17.88; P=.37) as well as National Aeronautics and Space Administration Task Load Index scores (VR mean 42.9, SD 13.01 vs video mean 51.50, SD 20.44; P=.16) were observed. The VR group had an above-average usability in the System Usability Scale (mean 74.78>70.0) and was significantly better than the video group (VR mean 74.78, SD 13.58 vs video mean 57.73, SD 21.13; P=.009). The analysis and visualization of trajectories revealed a positive correlation between the length of trajectories and the completion time, but neither correlated to the accuracy of the memorization task. Further user feedback indicated a preference for the VR method over the video-based method. Limitations of and suggestions for improvements in the study were also identified. Conclusions: A new immersive VR PPE training method was developed and evaluated against the video-based training. Results of the pilot study indicate that the VR method provides training quality comparable to video-based training and is more usable. In addition, the immersive experience of realistic settings and the flexibility of training configurations make the VR method a promising alternative to video instructions. ",
doi="10.2196/69021",
url="https://games.jmir.org/2025/1/e69021"
}


@Article{info:doi/10.2196/64682,
author="Oami, Takehiko
and Okada, Yohei
and Nakada, Taka-aki",
title="GPT-3.5 Turbo and GPT-4 Turbo in Title and Abstract Screening for Systematic Reviews",
journal="JMIR Med Inform",
year="2025",
month="Mar",
day="12",
volume="13",
pages="e64682",
keywords="large language models",
keywords="citation screening",
keywords="systematic review",
keywords="clinical practice guidelines",
keywords="artificial intelligence",
keywords="sepsis",
keywords="AI",
keywords="review",
keywords="GPT",
keywords="screening",
keywords="citations",
keywords="critical care",
keywords="Japan",
keywords="Japanese",
keywords="accuracy",
keywords="efficiency",
keywords="reliability",
keywords="LLM",
doi="10.2196/64682",
url="https://medinform.jmir.org/2025/1/e64682"
}


@Article{info:doi/10.2196/63291,
author="Chen, Qimin
and Li, Wei
and Wang, Ying
and Chen, Xianjun
and He, Dehua
and Liu, Ming
and Yuan, Jia
and Xiao, Chuan
and Li, Qing
and Chen, Lu
and Shen, Feng",
title="Investigating the Association Between Mean Arterial Pressure on 28-Day Mortality Risk in Patients With Sepsis: Retrospective Cohort Study Based on the MIMIC-IV Database",
journal="Interact J Med Res",
year="2025",
month="Mar",
day="5",
volume="14",
pages="e63291",
keywords="mean arterial pressure",
keywords="28-day mortality",
keywords="sepsis",
keywords="MIMIC-?",
keywords="retrospective study",
keywords="Medical Information Mart for Intensive Care IV",
abstract="Background: Sepsis is a globally recognized health issue that continues to contribute significantly to mortality and morbidity in intensive care units (ICUs). The association between mean arterial pressure (MAP) and prognosis among patients with patients is yet to be demonstrated. Objective: The aim of this study was to explore the association between MAP and 28-day mortality in ICU patients with sepsis using data from a large, multicenter database. Methods: This is a retrospective cohort study. We extracted data of 35,010 patients with sepsis from the MIMIC-IV (Medical Information Mart for Intensive Care) database between 2008 and 2019, according to the Sepsis 3.0 diagnostic criteria. The MAP was calculated as the average of the highest and lowest readings within the first 24 hours of ICU admission, and patients were divided into 4 groups based on the mean MAP, using the quadruple classification approach. Other worst-case indications from the first 24 hours of ICU admission, such as vital signs, severity of illness scores, laboratory indicators, and therapies, were also gathered as baseline data. The independent effects of MAP on 28-day mortality were explored using binary logistic regression and a two-piecewise linear model, with MAP as the exposure and 28-day mortality as the outcome variables, respectively. To address the nonlinearity relationship, curve fitting and a threshold effect analysis were performed. Results: A total of 34,981 patients with sepsis were included in the final analysis, the mean age was 66.67 (SD 16.01) years, and the 28-day mortality rate was 16.27\% (5691/34,981). The generalized additive model and smoothed curve fitting found a U-shaped relationship between MAP and 28-day mortality in these patients. The recursive algorithm determined the low and high inflection points as 70 mm and 82 mm Hg, respectively. Our data demonstrated that MAP was negatively associated with 28-day mortality in the range of 34.05 mm Hg-69.34 mm Hg (odds ratio [OR] 0.93, 95\% CI 0.92-0.94; P<.001); however, once the MAP exceeded 82 mm Hg, a positive association existed between MAP and 28-day mortality of patients with sepsis (OR 1.01; 95\% CI 1.01-1.02, P=.002). Conclusions: There is a U-shaped association between MAP and the probability of 28-day mortality in patients with sepsis. Both the lower and higher MAP were related with a higher risk of mortality in patients with sepsis. These patients have a decreased risk of mortality when their MAP remains between 70 and 82 mm Hg. ",
doi="10.2196/63291",
url="https://www.i-jmr.org/2025/1/e63291"
}


@Article{info:doi/10.2196/55492,
author="Campagner, Andrea
and Agnello, Luisa
and Carobene, Anna
and Padoan, Andrea
and Del Ben, Fabio
and Locatelli, Massimo
and Plebani, Mario
and Ognibene, Agostino
and Lorubbio, Maria
and De Vecchi, Elena
and Cortegiani, Andrea
and Piva, Elisa
and Poz, Donatella
and Curcio, Francesco
and Cabitza, Federico
and Ciaccio, Marcello",
title="Complete Blood Count and Monocyte Distribution Width--Based Machine Learning Algorithms for Sepsis Detection: Multicentric Development and External Validation Study",
journal="J Med Internet Res",
year="2025",
month="Feb",
day="26",
volume="27",
pages="e55492",
keywords="sepsis",
keywords="medical machine learning",
keywords="external validation",
keywords="complete blood count",
keywords="controllable AI",
keywords="machine learning",
keywords="artificial intelligence",
keywords="development study",
keywords="validation study",
keywords="organ",
keywords="organ dysfunction",
keywords="detection",
keywords="clinical signs",
keywords="clinical symptoms",
keywords="biomarker",
keywords="diagnostic",
keywords="machine learning model",
keywords="sepsis detection",
keywords="early detection",
keywords="data distribution",
abstract="Background: Sepsis is an organ dysfunction caused by a dysregulated host response to infection. Early detection is fundamental to improving the patient outcome. Laboratory medicine can play a crucial role by providing biomarkers whose alteration can be detected before the onset of clinical signs and symptoms. In particular, the relevance of monocyte distribution width (MDW) as a sepsis biomarker has emerged in the previous decade. However, despite encouraging results, MDW has poor sensitivity and positive predictive value when compared to other biomarkers. Objective: This study aims to investigate the use of machine learning (ML) to overcome the limitations mentioned earlier by combining different parameters and therefore improving sepsis detection. However, making ML models function in clinical practice may be problematic, as their performance may suffer when deployed in contexts other than the research environment. In fact, even widely used commercially available models have been demonstrated to generalize poorly in out-of-distribution scenarios. Methods: In this multicentric study, we developed ML models whose intended use is the early detection of sepsis on the basis of MDW and complete blood count parameters. In total, data from 6 patient cohorts (encompassing 5344 patients) collected at 5 different Italian hospitals were used to train and externally validate ML models. The models were trained on a patient cohort encompassing patients enrolled at the emergency department, and it was externally validated on 5 different cohorts encompassing patients enrolled at both the emergency department and the intensive care unit. The cohorts were selected to exhibit a variety of data distribution shifts compared to the training set, including label, covariate, and missing data shifts, enabling a conservative validation of the developed models. To improve generalizability and robustness to different types of distribution shifts, the developed ML models combine traditional methodologies with advanced techniques inspired by controllable artificial intelligence (AI), namely cautious classification, which gives the ML models the ability to abstain from making predictions, and explainable AI, which provides health operators with useful information about the models' functioning. Results: The developed models achieved good performance on the internal validation (area under the receiver operating characteristic curve between 0.91 and 0.98), as well as consistent generalization performance across the external validation datasets (area under the receiver operating characteristic curve between 0.75 and 0.95), outperforming baseline biomarkers and state-of-the-art ML models for sepsis detection. Controllable AI techniques were further able to improve performance and were used to derive an interpretable set of diagnostic rules. Conclusions: Our findings demonstrate how controllable AI approaches based on complete blood count and MDW may be used for the early detection of sepsis while also demonstrating how the proposed methodology can be used to develop ML models that are more resistant to different types of data distribution shifts. ",
doi="10.2196/55492",
url="https://www.jmir.org/2025/1/e55492"
}


@Article{info:doi/10.2196/67660,
author="Joubert, Dominique
and Bolor{\'e}, Sylvain
and Baroni, Carelle
and Hans, Anne-Sophie
and Wasser, Aline
and Kivrak, Selin
and Murat-Ringot, Audrey
and Dussart, Claude",
title="Interdisciplinary Strategies to Reduce Surgical Infectious Risk in the Operating Theater: Protocol for Scoping Review",
journal="JMIR Res Protoc",
year="2025",
month="Feb",
day="12",
volume="14",
pages="e67660",
keywords="surgical site infection",
keywords="infection prevention",
keywords="interdisciplinary strategies",
keywords="surgical team",
keywords="operating room",
keywords="standardized operating procedures",
abstract="Background: Surgical site infections (SSIs) represent one of the most prevalent and significant complications associated with surgical procedures, often leading to prolonged hospitalization and delayed patient recovery. While recent international consensus guidelines have proposed evidence-based strategies to mitigate SSIs, they fall short in addressing the efficient and interdisciplinary implementation of these measures within the operating theater. Consequently, further research is required to identify and evaluate optimal interdisciplinary organizational approaches for the prevention of SSIs. Objective: This study aims to map the scope, diversity, and nature of research on interdisciplinary strategies aimed at reducing SSIs and to analyze the impact of interdisciplinary on the effectiveness of preventive interventions. Methods: Using the Joanna Briggs Institute (JBI) methodology for scoping reviews, a comprehensive search will be conducted across databases including Embase (encompassing MEDLINE and PubMed-not-MEDLINE), CINAHL, and the Cochrane Library, supplemented by manual searches of reference lists from included papers. This review targets studies published between 2016 and 2024, aligning with the World Health Organization's 2016 SSI prevention guidelines, which introduced significant advancements in practice and remain the global benchmark. Only studies published in English or French will be considered. Around 5 reviewers independently distributed the included papers for detailed reading and data extraction, while the lead author concurrently and independently reviewed all papers. Inclusion criteria follow the Participants, Concept, and Context (PCC) framework, specifying that the eligible population comprises surgical teams. The primary concept of interest is interdisciplinary strategies aimed at preventing infection risk. The context focuses on adult surgical procedures within the operating room during turnover periods. Studies using experimental, quasi-experimental, preexperimental, observational, case-control, or cross-sectional designs will be included. Results: From the 1679 papers initially identified, 45 were selected for detailed analysis by 5 reviewers, with the selection process completed by November 2024. Conclusions: Emerging interdisciplinary strategies demonstrate significant potential in reducing the incidence of SSIs. This initiative forms part of a broader global project focused on codeveloping standardized protocols for preoperative preparation within the operating room to mitigate SSI risks. The findings of this scoping review will serve as the foundation for a subsequent qualitative survey and a pre-post quasi-experimental quantitative study to evaluate the integration and effectiveness of these strategies in clinical practice. The review protocol will be formally registered in the Open Science Framework (OSF) in 2024. International Registered Report Identifier (IRRID): DERR1-10.2196/67660 ",
doi="10.2196/67660",
url="https://www.researchprotocols.org/2025/1/e67660"
}


@Article{info:doi/10.2196/65093,
author="Virachith, Siriphone
and Phakhounthong, Khanxayaphone
and Khounvisith, Vilaysone
and Mayxay, Mayfong
and Kounnavong, Sengchanh
and Sayasone, Somphou
and H{\"u}bschen, M. Judith
and Black, P. Antony",
title="Hepatitis B Virus Exposure, Seroprotection Status, and Susceptibility in Health Care Workers From Lao People's Democratic Republic: Cross-Sectional Study",
journal="JMIR Public Health Surveill",
year="2024",
month="Dec",
day="17",
volume="10",
pages="e65093",
keywords="hepatitis B",
keywords="hepatitis D",
keywords="health care workers",
keywords="Laos",
keywords="prevalence",
abstract="Background: Despite the high prevalence of chronic hepatitis B virus (HBV) infection in adults in Lao People's Democratic Republic (Lao PDR), Lao health care workers (HCWs) have previously been shown to have low levels of protection against infection. Furthermore, the prevalence of hepatitis D virus (HDV), which increases disease severity in individuals infected with HBV, is not known in Lao PDR. Objective: This study aimed to estimate the exposure and seroprotection against HBV, as well as exposure to HDV, in Lao HCWs from 5 provinces. Methods: In 2020, a total of 666 HCWs aged 20 to 65 years from 5 provinces of Lao PDR were recruited, and their sera were tested by enzyme-linked immunosorbent assay to determine their HBV and HDV coinfection status. Results: HBV exposure, as indicated by the presence of anti--hepatitis B core antibodies, was 40.1\% (267/666) overall and significantly higher for HCWs from Oudomxay province (21/31, 67.7\%; adjusted odds ratio 3.69, 95\% CI 1.68?8.12; P=.001). The prevalence of hepatitis B surface antigen was 5.4\% (36/666) overall and increased with age, from 3.6\% (9/248) in those aged ?30 years to 6.8\% (8/118) in those aged ?50 years. Only 28.7\% (191/666) of participants had serological indication of immunization. We could find no evidence for HDV exposure in this study. Conclusions: The study found intermediate hepatitis B surface antigen prevalence among HCWs in Lao PDR, with no evidence of HDV coinfection. Notably, a significant proportion of HCWs remains susceptible to HBV, indicating a substantial gap in seroprotection against the disease. ",
doi="10.2196/65093",
url="https://publichealth.jmir.org/2024/1/e65093"
}


@Article{info:doi/10.2196/58039,
author="Jian, Ming-Jr
and Lin, Tai-Han
and Chung, Hsing-Yi
and Chang, Chih-Kai
and Perng, Cherng-Lih
and Chang, Feng-Yee
and Shang, Hung-Sheng",
title="Pioneering Klebsiella Pneumoniae Antibiotic Resistance Prediction With Artificial Intelligence-Clinical Decision Support System--Enhanced Matrix-Assisted Laser Desorption/Ionization Time-of-Flight Mass Spectrometry: Retrospective Study",
journal="J Med Internet Res",
year="2024",
month="Nov",
day="7",
volume="26",
pages="e58039",
keywords="Klebsiella pneumoniae",
keywords="multidrug resistance",
keywords="AI-CDSS",
keywords="quinolone",
keywords="ciprofloxacin",
keywords="levofloxacin",
abstract="Background: The rising prevalence and swift spread of multidrug-resistant gram-negative bacteria (MDR-GNB), especially Klebsiella pneumoniae (KP), present a critical global health threat highlighted by the World Health Organization, with mortality rates soaring approximately 50\% with inappropriate antimicrobial treatment. Objective: This study aims to advance a novel strategy to develop an artificial intelligence-clinical decision support system (AI-CDSS) that combines machine learning (ML) with matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), aiming to significantly improve the accuracy and speed of diagnosing antibiotic resistance, directly addressing the grave health risks posed by the widespread dissemination of pan drug-resistant gram-negative bacteria across numerous countries. Methods: A comprehensive dataset comprising 165,299 bacterial specimens and 11,996 KP isolates was meticulously analyzed using MALDI-TOF MS technology. Advanced ML algorithms were harnessed to sculpt predictive models that ascertain resistance to quintessential antibiotics, particularly levofloxacin and ciprofloxacin, by using the amassed spectral data. Results: Our ML models revealed remarkable proficiency in forecasting antibiotic resistance, with the random forest classifier emerging as particularly effective in predicting resistance to both levofloxacin and ciprofloxacin, achieving the highest area under the curve of 0.95. Performance metrics across different models, including accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1-score, were detailed, underlining the potential of these algorithms in aiding the development of precision treatment strategies. Conclusions: This investigation highlights the synergy between MALDI-TOF MS and ML as a beacon of hope against the escalating threat of antibiotic resistance. The advent of AI-CDSS heralds a new era in clinical diagnostics, promising a future in which rapid and accurate resistance prediction becomes a cornerstone in combating infectious diseases. Through this innovative approach, we answered the challenge posed by KP and other multidrug-resistant pathogens, marking a significant milestone in our journey toward global health security. ",
doi="10.2196/58039",
url="https://www.jmir.org/2024/1/e58039"
}


@Article{info:doi/10.2196/53828,
author="Zhu, Jiayue Nina
and Weldegiorgis, Misghina
and Carter, Emma
and Brown, Colin
and Holmes, Alison
and Aylin, Paul",
title="Economic Burden of Community-Acquired Antibiotic-Resistant Urinary Tract Infections: Systematic Review and Meta-Analysis",
journal="JMIR Public Health Surveill",
year="2024",
month="Oct",
day="9",
volume="10",
pages="e53828",
keywords="cost-effectiveness",
keywords="urinary tract infection",
keywords="antibiotic resistance",
keywords="mortality",
keywords="hospital length of stay",
abstract="Background: Antibiotic resistance (ABR) poses a major burden to global health and economic systems. ABR in community-acquired urinary tract infections (CA-UTIs) has become increasingly prevalent. Accurate estimates of ABR's clinical and economic burden are needed to support medical resource prioritization and cost-effectiveness evaluations of urinary tract infection (UTI) interventions. Objective: This study aims to systematically synthesize the evidence on the economic costs associated with ABR in CA-UTIs, using published studies comparing the costs of antibiotic-susceptible and antibiotic-resistant cases. Methods: We searched the PubMed, Ovid MEDLINE and Embase, Cochrane Review Library, and Scopus databases. Studies published in English from January 1, 2008, to January 31, 2023, reporting the economic costs of ABR in CA-UTI of any microbe were included. Independent screening of titles/abstracts and full texts was performed based on prespecified criteria. A quality assessment was performed using the Integrated Quality Criteria for Review of Multiple Study Designs (ICROMS) tool. Data in UTI diagnosis criteria, patient characteristics, perspectives, resource costs, and patient and health economic outcomes, including mortality, hospital length of stay (LOS), and costs, were extracted and analyzed. Monetary costs were converted into 2023 US dollars. Results: This review included 15 studies with a total of 57,251 CA-UTI cases. All studies were from high- or upper-middle-income countries. A total of 14 (93\%) studies took a health system perspective, 13 (87\%) focused on hospitalized patients, and 14 (93\%) reported UTI pathogens. Escherichia coli, Klebsiella pneumoniae, and Pseudomonas aeruginosa are the most prevalent organisms. A total of 12 (80\%) studies reported mortality, of which, 7 reported increased mortality in the ABR group. Random effects meta-analyses estimated an odds ratio of 1.50 (95\% CI 1.29-1.74) in the ABR CA-UTI cases. All 13 hospital-based studies reported LOS, of which, 11 reported significantly higher LOS in the ABR group. The meta-analysis of the reported median LOS estimated a pooled excess LOS ranging from 1.50 days (95\% CI 0.71-4.00) to 2.00 days (95\% CI 0.85-3.15). The meta-analysis of the reported mean LOS estimated a pooled excess LOS of 2.45 days (95\% CI 0.51?4.39). A total of 8 (53\%) studies reported costs in monetary terms---none discounted the costs. All 8 studies reported higher medical costs spent treating patients with ABR CA-UTI in hospitals. The highest excess cost was observed in UTIs caused by carbapenem-resistant Enterobacterales. No meta-analysis was performed for monetary costs due to heterogeneity. Conclusions: ABR was attributed to increased mortality, hospital LOS, and economic costs among patients with CA-UTI. The findings of this review highlighted the scarcity of research in this area, particularly in patient morbidity and chronic sequelae and costs incurred in community health care. Future research calls for a cost-of-illness analysis of infections, standardizing therapy-pathogen combination comparators, medical resources, productivity loss, intangible costs to be captured, and data from community sectors and low-resource settings and countries. ",
doi="10.2196/53828",
url="https://publichealth.jmir.org/2024/1/e53828"
}


@Article{info:doi/10.2196/57820,
author="Rosslenbroich, Steffen
and Laumann, Marion
and Hasebrook, Joachim
and Rodde, Sibyll
and Grosser, John
and Greiner, Wolfgang
and Hirsch, Tobias
and Windrich, Stefan
and Raschke, J. Michael",
title="Improving the Care of Severe, Open Fractures and Postoperative Infections of the Lower Extremities: Protocol for an Interdisciplinary Treatment Approach",
journal="JMIR Res Protoc",
year="2024",
month="Sep",
day="16",
volume="13",
pages="e57820",
keywords="open fracture",
keywords="open soft tissue damage",
keywords="telemedicine",
keywords="plastic surgery",
keywords="infectiology",
keywords="limb function",
keywords="health-related quality of life",
keywords="workload",
keywords="work engagement",
keywords="health economic evaluation",
abstract="Background: Patients with open fractures often experience complications during their injury. The treatments incur high costs. Interdisciplinary cooperation between different medical disciplines may improve treatment outcomes. Such cooperation has not yet been envisaged in the German health care system. Objective: The aim of the study is to improve the treatment of fractures with open soft tissue damage or postoperative complications in terms of duration and sustainability in a region in northwest Germany. Largely standardized diagnostics and therapy are intended to optimize processes in hospitals. In addition, a reduction in the duration of treatment and treatment costs is to be achieved. Methods: Using a digital platform, physicians from 31 hospitals present patient cases to an interdisciplinary group of experts from the fields of plastic surgery, infectiology, hygiene, and others. The group of experts from the environment of the University Hospital M{\"u}nster promptly makes a joint treatment recommendation for the individual case. The plan is to examine 3300 patients with open fractures or surgical complications. As consortium partners, there are also 3 statutory health insurance companies. The extent to which the therapy recommendations are effective and contribute to cost reduction in the health care system will be empirically investigated in a stepped-wedge cluster-randomized design. In addition, medical and nonmedical professional groups involved in the project will be asked about their work in the project (in total, 248 clinic employees). The primary outcome is the complication rate of open fractures or the occurrence of postoperative complications. As secondary outcomes, the number of antibiotics administered, limb function, and quality of life will be assessed. The health economic evaluation refers to the costs of health services and absenteeism. For the work-related evaluation, workload, work engagement, work-related resources, readiness for technology, and ergonomic aspects of the new telemedical technology will be collected. In addition, clinic employees will give their assessments of the success of the project in a structured telephone interview based on scaled and open-ended questions. Results: The project started in June 2022; data collection started in April 2023. As of mid-June 2024, data from 425 patients had been included. In total, 146 members of staff had taken part in the questionnaire survey and 15 had taken part in the interviews. Conclusions: Standardized treatment pathways in the standard care of patients with open fractures and postoperative infections will be established to reduce complications, improve chances of recovery, and reduce costs. Unnecessary and redundant treatment steps will be avoided through standardized diagnostics and therapy. The interdisciplinary treatment perspective allows for a more individualized therapy. In the medium term, outpatient or inpatient treatment centers specialized in the patient group could be set up where the new diagnostic and therapeutic pathways could be competently applied. Trial Registration: German Clinical Trials Register DRKS00031308; https://drks.de/search/de/trial/DRKS00031308 International Registered Report Identifier (IRRID): DERR1-10.2196/57820 ",
doi="10.2196/57820",
url="https://www.researchprotocols.org/2024/1/e57820"
}


@Article{info:doi/10.2196/57195,
author="van der Meijden, Lise Siri
and van Boekel, M. Anna
and van Goor, Harry
and Nelissen, GHH Rob
and Schoones, W. Jan
and Steyerberg, W. Ewout
and Geerts, F. Bart
and de Boer, GJ Mark
and Arbous, Sesmu M.",
title="Automated Identification of Postoperative Infections to Allow Prediction and Surveillance Based on Electronic Health Record Data: Scoping Review",
journal="JMIR Med Inform",
year="2024",
month="Sep",
day="10",
volume="12",
pages="e57195",
keywords="postoperative infections",
keywords="surveillance",
keywords="prediction",
keywords="surgery",
keywords="artificial intelligence",
keywords="chart review",
keywords="electronic health record",
keywords="scoping review",
keywords="postoperative",
keywords="surgical",
keywords="infection",
keywords="infections",
keywords="predictions",
keywords="predict",
keywords="predictive",
keywords="bacterial",
keywords="machine learning",
keywords="record",
keywords="records",
keywords="EHR",
keywords="EHRs",
keywords="synthesis",
keywords="review methods",
keywords="review methodology",
keywords="search",
keywords="searches",
keywords="searching",
keywords="scoping",
abstract="Background: Postoperative infections remain a crucial challenge in health care, resulting in high morbidity, mortality, and costs. Accurate identification and labeling of patients with postoperative bacterial infections is crucial for developing prediction models, validating biomarkers, and implementing surveillance systems in clinical practice. Objective: This scoping review aimed to explore methods for identifying patients with postoperative infections using electronic health record (EHR) data to go beyond the reference standard of manual chart review. Methods: We performed a systematic search strategy across PubMed, Embase, Web of Science (Core Collection), the Cochrane Library, and Emcare (Ovid), targeting studies addressing the prediction and fully automated surveillance (ie, without manual check) of diverse bacterial infections in the postoperative setting. For prediction modeling studies, we assessed the labeling methods used, categorizing them as either manual or automated. We evaluated the different types of EHR data needed for the surveillance and labeling of postoperative infections, as well as the performance of fully automated surveillance systems compared with manual chart review. Results: We identified 75 different methods and definitions used to identify patients with postoperative infections in studies published between 2003 and 2023. Manual labeling was the predominant method in prediction modeling research, 65\% (49/75) of the identified methods use structured data, and 45\% (34/75) use free text and clinical notes as one of their data sources. Fully automated surveillance systems should be used with caution because the reported positive predictive values are between 0.31 and 0.76. Conclusions: There is currently no evidence to support fully automated labeling and identification of patients with infections based solely on structured EHR data. Future research should focus on defining uniform definitions, as well as prioritizing the development of more scalable, automated methods for infection detection using structured EHR data. ",
doi="10.2196/57195",
url="https://medinform.jmir.org/2024/1/e57195",
url="http://www.ncbi.nlm.nih.gov/pubmed/39255011"
}


@Article{info:doi/10.2196/54044,
author="Ito, Genta
and Yada, Shuntaro
and Wakamiya, Shoko
and Aramaki, Eiji",
title="Predictive Model for Extended-Spectrum $\beta$-Lactamase--Producing Bacterial Infections Using Natural Language Processing Technique and Open Data in Intensive Care Unit Environment: Retrospective Observational Study",
journal="JMIR Form Res",
year="2024",
month="Jul",
day="10",
volume="8",
pages="e54044",
keywords="predictive modeling",
keywords="MIMIC-3 dataset",
keywords="natural language processing",
keywords="NLP",
keywords="QuickUMLS",
keywords="named entity recognition",
keywords="ESBL-producing bacterial infections",
abstract="Background: Machine learning has advanced medical event prediction, mostly using private data. The public MIMIC-3 (Medical Information Mart for Intensive Care III) data set, which contains detailed data on over 40,000 intensive care unit patients, stands out as it can help develop better models including structured and textual data. Objective: This study aimed to build and test a machine learning model using the MIMIC-3 data set to determine the effectiveness of information extracted from electronic medical record text using a named entity recognition, specifically QuickUMLS, for predicting important medical events. Using the prediction of extended-spectrum $\beta$-lactamase (ESBL)--producing bacterial infections as an example, this study shows how open data sources and simple technology can be useful for making clinically meaningful predictions. Methods: The MIMIC-3 data set, including demographics, vital signs, laboratory results, and textual data, such as discharge summaries, was used. This study specifically targeted patients diagnosed with Klebsiella pneumoniae or Escherichia coli infection. Predictions were based on ESBL-producing bacterial standards and the minimum inhibitory concentration criteria. Both the structured data and extracted patient histories were used as predictors. In total, 2 models, an L1-regularized logistic regression model and a LightGBM model, were evaluated using the receiver operating characteristic area under the curve (ROC-AUC) and the precision-recall curve area under the curve (PR-AUC). Results: Of 46,520 MIMIC-3 patients, 4046 were identified with bacterial cultures, indicating the presence of K pneumoniae or E coli. After excluding patients who lacked discharge summary text, 3614 patients remained. The L1-penalized model, with variables from only the structured data, displayed a ROC-AUC of 0.646 and a PR-AUC of 0.307. The LightGBM model, combining structured and textual data, achieved a ROC-AUC of 0.707 and a PR-AUC of 0.369. Key contributors to the LightGBM model included patient age, duration since hospital admission, and specific medical history such as diabetes. The structured data-based model showed improved performance compared to the reference models. Performance was further improved when textual medical history was included. Compared to other models predicting drug-resistant bacteria, the results of this study ranked in the middle. Some misidentifications, potentially due to the limitations of QuickUMLS, may have affected the accuracy of the model. Conclusions: This study successfully developed a predictive model for ESBL-producing bacterial infections using the MIMIC-3 data set, yielding results consistent with existing literature. This model stands out for its transparency and reliance on open data and open-named entity recognition technology. The performance of the model was enhanced using textual information. With advancements in natural language processing tools such as BERT and GPT, the extraction of medical data from text holds substantial potential for future model optimization. ",
doi="10.2196/54044",
url="https://formative.jmir.org/2024/1/e54044"
}


@Article{info:doi/10.2196/43743,
author="Isigi, Shivuli Sharon
and Parsa, Davod Ali
and Alasqah, Ibrahim
and Mahmud, Ilias
and Kabir, Russell",
title="Predisposing Factors of Nosocomial Infections in Hospitalized Patients in the United Kingdom: Systematic Review",
journal="JMIR Public Health Surveill",
year="2023",
month="Dec",
day="19",
volume="9",
pages="e43743",
keywords="hospital-acquired infections",
keywords="nosocomial infections",
keywords="infection risk",
keywords="systematic review",
keywords="hospitalized patients",
keywords="public health",
abstract="Background: Nosocomial infections are infections incubating or not present at the time of admission to a hospital and manifest 48 hours after hospital admission. The specific factors contributing to the risk of infection during hospitalization remain unclear, particularly for the hospitalized population of the United Kingdom. Objective: The aim of this systematic literature review was to explore the risk factors of nosocomial infections in hospitalized adult patients in the United Kingdom. Methods: A comprehensive keyword search was conducted through the PubMed, Medline, and EBSCO CINAHL Plus databases. The keywords included ``risk factors'' or ``contributing factors'' or ``predisposing factors'' or ``cause'' or ``vulnerability factors'' and ``nosocomial infections'' or ``hospital-acquired infections'' and ``hospitalized patients'' or ``inpatients'' or ``patients'' or ``hospitalized.'' Additional articles were obtained through reference harvesting of selected articles. The search was limited to the United Kingdom with papers written in English, without limiting for age and gender to minimize bias. The above process retrieved 377 articles, which were further screened using inclusion and exclusion criteria following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. The retained 9 studies were subjected to critical appraisal using the Critical Appraisal Skills Programme (cohort and case-control studies) and Appraisal Tool for Cross-Sectional Studies (cross-sectional studies) checklists. Finally, 6 eligible publications were identified and used to collect the study findings. A thematic analysis technique was used to analyze data extracted on risk factors of nosocomial infections in hospitalized patients in the United Kingdom. Results: The risk factors for nosocomial infections that emerged from the reviewed studies included older age, intrahospital transfers, cross-infection, longer hospital stay, readmissions, prior colonization with opportunistic organisms, comorbidities, and prior intake of antibiotics and urinary catheters. Nosocomial infections were associated with more extended hospital stays, presenting with increased morbidity and mortality. Measures for controlling nosocomial infections included the use of single-patient rooms, well-equipped wards, prior screening of staff and patients, adequate sick leave for staff, improved swallowing techniques and nutritional intake for patients, improved oral hygiene, avoiding unnecessary indwelling plastics, use of suprapubic catheters, aseptic techniques during patient care, and prophylactic use. Conclusions: There is a need for further studies to aid in implementing nosocomial infection prevention and control. ",
doi="10.2196/43743",
url="https://publichealth.jmir.org/2023/1/e43743",
url="http://www.ncbi.nlm.nih.gov/pubmed/38113098"
}


@Article{info:doi/10.2196/29927,
author="Iglesias, Natalia
and Juarez, M. Jose
and Campos, Manuel",
title="Business Process Model and Notation and openEHR Task Planning for Clinical Pathway Standards in Infections: Critical Analysis",
journal="J Med Internet Res",
year="2022",
month="Sep",
day="15",
volume="24",
number="9",
pages="e29927",
keywords="openEHR task planning",
keywords="business process model and notation",
keywords="BPMN",
keywords="clinical pathways",
keywords="catheter-related bloodstream infection",
keywords="CR-BSI",
keywords="clinical guidelines",
abstract="Background: Clinical pathways (CPs) are usually expressed by means of workflow formalisms, providing health care personnel with an easy-to-understand, high-level conceptual model of medical steps in specific patient conditions, thereby improving overall health care process quality in clinical practice. From a standardized perspective, the business process model and notation (BPMN), a widely spread general-purpose process formalism, has been used for conceptual modeling in clinical domains, mainly because of its easy-to-use graphical notation, facilitating the common understanding and communication of the parties involved in health care. However, BPMN is not particularly oriented toward the peculiarities of complex clinical processes such as infection diagnosis and treatment, in which time plays a critical role, which is why much of the BPMN clinical-oriented research has revolved around how to extend the standard to address these special needs. The shift from an agnostic, general-purpose BPMN notation to a natively clinical-oriented notation such as openEHR Task Planning (TP) could constitute a major step toward clinical process improvement, enhancing the representation of CPs for infection treatment and other complex scenarios. Objective: Our work aimed to analyze the suitability of a clinical-oriented formalism (TP) to successfully represent typical process patterns in infection treatment, identifying domain-specific improvements to the standard that could help enhance its modeling capabilities, thereby promoting the widespread adoption of CPs to improve medical practice and overall health care quality. Methods: Our methodology consisted of 4 major steps: identification of key features of infection CPs through literature review, clinical guideline analysis, and BPMN extensions; analysis of the presence of key features in TP; modeling of relevant process patterns of catheter-related bloodstream infection as a case study; and analysis and proposal of extensions in view of the results. Results: We were able to easily represent the same logic applied in the extended BPMN-based process models in our case study using out-of-the-box standard TP primitives. However, we identified possible improvements to the current version of TP to allow for simpler conceptual models of infection CPs and possibly of other complex clinical scenarios. Conclusions: Our study showed that the clinical-oriented TP specification is able to successfully represent the most complex catheter-related bloodstream infection process patterns depicted in our case study and identified possible extensions that can help increase its adequacy for modeling infection CPs and possibly other complex clinical conditions. ",
doi="10.2196/29927",
url="https://www.jmir.org/2022/9/e29927",
url="http://www.ncbi.nlm.nih.gov/pubmed/36107480"
}


@Article{info:doi/10.2196/38386,
author="Fredericks-Younger, Janine
and Fine, H. Daniel
and Subramanian, Gayathri
and Coker, O. Modupe
and Meyerowitz, Cyril
and Ragusa, Patricia
and Allareddy, Veerasathpurush
and McBurnie, Ann Mary
and Funkhouser, Ellen
and Gennaro, Laura Maria
and Feldman, A. Cecile",
title="The Pragmatic Return to Effective Dental Infection Control Through Triage and Testing (PREDICT) Study: Protocol for a Prospective Clinical Study in the National Dental Practice--Based Research Network",
journal="JMIR Res Protoc",
year="2022",
month="Aug",
day="31",
volume="11",
number="8",
pages="e38386",
keywords="COVID-19",
keywords="COVID-19 triage",
keywords="COVID-19 testing",
keywords="SARS-CoV-2",
keywords="feasibility study",
keywords="National Dental Practice--Based Research Network",
keywords="PBRN",
keywords="dental practice",
keywords="dental health",
keywords="dentist",
keywords="dentistry",
keywords="safety",
keywords="healthcare professional safety",
keywords="health care",
keywords="patient safety",
keywords="dental healthcare staff",
abstract="Background: Dental practice has been greatly affected by the COVID-19 pandemic. As SARS-CoV-2 infection is transmitted by respiratory fluids, dental practice techniques, which include aerosol-generating procedures, can increase the risk of transmission causing heightened safety concerns for both dental health care workers (DHCWs) and patients. These concerns have resulted in the reduction in patient volume and the available workforce within dental practices across the United States. Standardized methods for COVID-19 triage and testing may lead to increased safety and perceptions of safety for DHCWs and their patients and promote willingness to provide and access oral health care services. Objective: This study is designed to develop procedures that test the feasibility of enhanced COVID-19 triage and testing in dental offices. It will provide preliminary data to support a larger network-wide study grant application aimed at developing protocols to address safety concerns of patients and DHCWs in a peri--COVID-19 pandemic era. Methods: The feasibility study is being conducted in 4 private dental practices, each of which has a dentist member of the National Dental Practice--Based Research Network. Participants include the DHCWs and patients of the dental practice. Study procedures include completion of COVID-19 triage, completion of COVID-19 testing (point-of-care [POC] or laboratory-based [LAB] SARS-CoV-2 viral, antigen, and antibody tests based on office designation), and administration of perception and attitude surveys for participating DCHWs and patients of the dental practice over a defined study period. The office designation and the participant's role in the practice determines which testing protocol is executed within the office. There are 4 study groups following 4 distinct protocols: (1) POC DHCWs, (2) POC patients, (3) LAB DHCWs, and (4) LAB patients. Results: Data collection began in December of 2021 and concluded in March 2022. Study results are expected to be published in fall 2022. Conclusions: The results of this feasibility study will help identify the viability and functionality of COVID-19 triage and testing in dental practices and inform a larger network-wide study grant application that develops protocols that address safety concerns of patients and DHCWs in a COVID-19 environment. Trial Registration: ClinicalTrials.gov NTC05123742; https://clinicaltrials.gov/ct2/show/NCT05123742?term=NCT05123742 International Registered Report Identifier (IRRID): DERR1-10.2196/38386 ",
doi="10.2196/38386",
url="https://www.researchprotocols.org/2022/8/e38386",
url="http://www.ncbi.nlm.nih.gov/pubmed/35944181"
}


@Article{info:doi/10.2196/33531,
author="Keizer, Julia
and Bente, E. Britt
and Al Naiemi, Nashwan
and Van Gemert-Pijnen, JEWC Lisette
and Beerlage-De Jong, Nienke",
title="Improving the Development and Implementation of Audit and Feedback Systems to Support Health Care Workers in Limiting Antimicrobial Resistance in the Hospital: Scoping Review",
journal="J Med Internet Res",
year="2022",
month="Mar",
day="11",
volume="24",
number="3",
pages="e33531",
keywords="scoping review",
keywords="audit and feedback",
keywords="eHealth",
keywords="development",
keywords="implementation",
keywords="antimicrobial resistance",
keywords="antibiotic stewardship",
keywords="infection control",
abstract="Background: For eHealth technologies in general and audit and feedback (AF) systems specifically, integrating interdisciplinary theoretical underpinnings is essential, as it increases the likelihood of achieving desired outcomes by ensuring a fit among eHealth technology, stakeholders, and their context. In addition, reporting on the development and implementation process of AF systems, including substantiations of choices, enables the identification of best practices and accumulation of knowledge across studies but is often not elaborated on in publications. Objective: This scoping review aims to provide insights into the development and implementation strategies for AF systems for a real-world problem that threatens modern health care---antimicrobial resistance---and provide an interdisciplinary conceptual framework that can serve as a checklist and guidance for making informed choices in the development and implementation of future AF systems. Methods: A scoping review was conducted by querying PubMed, Scopus, Web of Science, IEEE Xplore Digital Library, and Embase (?2010) for studies describing either the development or implementation process, or both, of an AF system for antimicrobial resistance or infections in hospitals. Studies reporting only on effectiveness or impact were excluded. A total of 3 independent reviewers performed the study selection, and 2 reviewers constructed the conceptual framework through the axial and selective coding of often-used theories, models, and frameworks (TMFs) from the literature on AF and eHealth development and implementation. Subsequently, the conceptual framework was used for the systematic extraction and interpretation of the studies' descriptions of AF systems and their development and implementation. Results: The search resulted in 2125 studies that were screened for eligibility, of which 12 (0.56\%); 2012-2020) were included. These studies described the development and implementation processes heterogeneously in terms of study aims, study targets, target groups, methods, and theoretical underpinnings. Few studies have explicitly explained how choices for the development and implementation of AF systems were substantiated by the TMFs. The conceptual framework provided insights into what is reported on the development and implementation process and revealed underreported AF system constructs (eg, AF system design; engagement with the AF system; and comparison, goal setting, and action planning) and development and implementation (eg, champions) constructs. Conclusions: This scoping review showed the current heterogeneous reporting of AF systems and their development and implementation processes and exemplified how interdisciplinary TMFs can (and should) be balanced in a conceptual framework to capture relevant AF systems and development and implementation constructs. Thereby, it provides a concrete checklist and overall guidance that supports the professionalization and harmonization of AF system development and implementation. For the development and implementation of future AF systems and other eHealth technologies, researchers and health care workers should be supported in selecting and integrating TMFs into their development and implementation process and encouraged to explicitly report on theoretical underpinnings and the substantiation of choices. ",
doi="10.2196/33531",
url="https://www.jmir.org/2022/3/e33531",
url="http://www.ncbi.nlm.nih.gov/pubmed/35275082"
}


@Article{info:doi/10.2196/32384,
author="Hadian, Kimia
and Fernie, Geoff
and Roshan Fekr, Atena",
title="A New Performance Metric to Estimate the Risk of Exposure to Infection in a Health Care Setting: Descriptive Study",
journal="JMIR Form Res",
year="2022",
month="Feb",
day="2",
volume="6",
number="2",
pages="e32384",
keywords="hand hygiene",
keywords="health care-acquired",
keywords="infection control",
keywords="compliance",
keywords="electronic monitoring",
keywords="exposure",
keywords="risk",
keywords="hygiene",
keywords="monitoring",
keywords="surveillance",
keywords="performance",
keywords="metric",
keywords="method",
keywords="estimate",
keywords="predict",
keywords="development",
abstract="Background: Despite several measures to monitor and improve hand hygiene (HH) in health care settings, health care-acquired infections (HAIs) remain prevalent. The measures used to calculate HH performance are not able to fully benefit from the high-resolution data collected using electronic monitoring systems. Objective: This study proposes a novel parameter for quantifying the HAI exposure risk of individual patients by considering temporal and spatial features of health care workers' HH adherence. Methods: Patient exposure risk is calculated as a function of the number of consecutive missed HH opportunities, the number of unique rooms visited by the health care professional, and the time duration that the health care professional spends inside and outside the patient's room without performing HH. The patient exposure risk is compared to the entrance compliance rate (ECR) defined as the ratio of the number of HH actions performed at a room entrance to the total number of entrances into the room. The compliance rate is conventionally used to measure HH performance. The ECR and the patient exposure risk are analyzed using the data collected from an inpatient nursing unit for 12 weeks. Results: The analysis of data collected from 59 nurses and more than 25,600 records at a musculoskeletal rehabilitation unit at the Toronto Rehabilitation Institute, KITE, showed that there is no strong linear relation between the ECR and patient exposure risk (r=0.7, P<.001). Since the ECR is calculated based on the number of missed HH actions upon room entrance, this parameter is already included in the patient exposure risk. Therefore, there might be scenarios that these 2 parameters are correlated; however, in several cases, the ECR contrasted with the reported patient exposure risk. Generally, the patients in rooms with a significantly high ECR can be potentially exposed to a considerable risk of infection. By contrast, small ECRs do not necessarily result in a high patient exposure risk. The results clearly explained the important role of the factors incorporated in patient exposure risk for quantifying the risk of infection for the patients. Conclusions: Patient exposure risk might provide a more reliable estimation of the risk of developing HAIs compared to ECR by considering both the temporal and spatial aspects of HH records. ",
doi="10.2196/32384",
url="https://formative.jmir.org/2022/2/e32384",
url="http://www.ncbi.nlm.nih.gov/pubmed/35107424"
}


@Article{info:doi/10.2196/33296,
author="Izadi, Neda
and Etemad, Koorosh
and Mehrabi, Yadollah
and Eshrati, Babak
and Hashemi Nazari, Saeed Seyed",
title="The Standardization of Hospital-Acquired Infection Rates Using Prediction Models in Iran: Observational Study of National Nosocomial Infection Registry Data",
journal="JMIR Public Health Surveill",
year="2021",
month="Dec",
day="7",
volume="7",
number="12",
pages="e33296",
keywords="hospital-acquired infections",
keywords="standardized infection ratio",
keywords="prediction model",
keywords="Iran",
abstract="Background: Many factors contribute to the spreading of hospital-acquired infections (HAIs). Objective: This study aimed to standardize the HAI rate using prediction models in Iran based on the National Healthcare Safety Network (NHSN) method. Methods: In this study, the Iranian nosocomial infections surveillance system (INIS) was used to gather data on patients with HAIs (126,314 infections). In addition, the hospital statistics and information system (AVAB) was used to collect data on hospital characteristics. First, well-performing hospitals, including 357 hospitals from all over the country, were selected. Data were randomly split into training (70\%) and testing (30\%) sets. Finally, the standardized infection ratio (SIR) and the corrected SIR were calculated for the HAIs. Results: The mean age of the 100,110 patients with an HAI was 40.02 (SD 23.56) years. The corrected SIRs based on the observed and predicted infections for respiratory tract infections (RTIs), urinary tract infections (UTIs), surgical site infections (SSIs), and bloodstream infections (BSIs) were 0.03 (95\% CI 0-0.09), 1.02 (95\% CI 0.95-1.09), 0.93 (95\% CI 0.85-1.007), and 0.91 (95\% CI 0.54-1.28), respectively. Moreover, the corrected SIRs for RTIs in the infectious disease, burn, obstetrics and gynecology, and internal medicine wards; UTIs in the burn, infectious disease, internal medicine, and intensive care unit wards; SSIs in the burn and infectious disease wards; and BSIs in most wards were >1, indicating that more HAIs were observed than expected. Conclusions: The results of this study can help to promote preventive measures based on scientific evidence. They can also lead to the continuous improvement of the monitoring system by collecting and systematically analyzing data on HAIs and encourage the hospitals to better control their infection rates by establishing a benchmarking system. ",
doi="10.2196/33296",
url="https://publichealth.jmir.org/2021/12/e33296",
url="http://www.ncbi.nlm.nih.gov/pubmed/34879002"
}


@Article{info:doi/10.2196/27880,
author="Wang, Chaofan
and Jiang, Weiwei
and Yang, Kangning
and Yu, Difeng
and Newn, Joshua
and Sarsenbayeva, Zhanna
and Goncalves, Jorge
and Kostakos, Vassilis",
title="Electronic Monitoring Systems for Hand Hygiene: Systematic Review of Technology",
journal="J Med Internet Res",
year="2021",
month="Nov",
day="24",
volume="23",
number="11",
pages="e27880",
keywords="hand hygiene",
keywords="hand hygiene compliance",
keywords="hand hygiene quality",
keywords="electronic monitoring systems",
keywords="systematic review",
keywords="mobile phone",
abstract="Background: Hand hygiene is one of the most effective ways of preventing health care--associated infections and reducing their transmission. Owing to recent advances in sensing technologies, electronic hand hygiene monitoring systems have been integrated into the daily routines of health care workers to measure their hand hygiene compliance and quality. Objective: This review aims to summarize the latest technologies adopted in electronic hand hygiene monitoring systems and discuss the capabilities and limitations of these systems. Methods: A systematic search of PubMed, ACM Digital Library, and IEEE Xplore Digital Library was performed following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were initially screened and assessed independently by the 2 authors, and disagreements between them were further summarized and resolved by discussion with the senior author. Results: In total, 1035 publications were retrieved by the search queries; of the 1035 papers, 89 (8.60\%) fulfilled the eligibility criteria and were retained for review. In summary, 73 studies used electronic monitoring systems to monitor hand hygiene compliance, including application-assisted direct observation (5/73, 7\%), camera-assisted observation (10/73, 14\%), sensor-assisted observation (29/73, 40\%), and real-time locating system (32/73, 44\%). A total of 21 studies evaluated hand hygiene quality, consisting of compliance with the World Health Organization 6-step hand hygiene techniques (14/21, 67\%) and surface coverage or illumination reduction of fluorescent substances (7/21, 33\%). Conclusions: Electronic hand hygiene monitoring systems face issues of accuracy, data integration, privacy and confidentiality, usability, associated costs, and infrastructure improvements. Moreover, this review found that standardized measurement tools to evaluate system performance are lacking; thus, future research is needed to establish standardized metrics to measure system performance differences among electronic hand hygiene monitoring systems. Furthermore, with sensing technologies and algorithms continually advancing, more research is needed on their implementation to improve system performance and address other hand hygiene--related issues. ",
doi="10.2196/27880",
url="https://www.jmir.org/2021/11/e27880",
url="http://www.ncbi.nlm.nih.gov/pubmed/34821565"
}


@Article{info:doi/10.2196/33576,
author="Leal-Neto, Onicio
and Egger, Thomas
and Schlegel, Matthias
and Flury, Domenica
and Sumer, Johannes
and Albrich, Werner
and Babouee Flury, Baharak
and Kuster, Stefan
and Vernazza, Pietro
and Kahlert, Christian
and Kohler, Philipp",
title="Digital SARS-CoV-2 Detection Among Hospital Employees: Participatory Surveillance Study",
journal="JMIR Public Health Surveill",
year="2021",
month="Nov",
day="22",
volume="7",
number="11",
pages="e33576",
keywords="digital epidemiology",
keywords="SARS-CoV-2",
keywords="COVID-19",
keywords="health care workers",
abstract="Background: The implementation of novel techniques as a complement to traditional disease surveillance systems represents an additional opportunity for rapid analysis. Objective: The objective of this work is to describe a web-based participatory surveillance strategy among health care workers (HCWs) in two Swiss hospitals during the first wave of COVID-19. Methods: A prospective cohort of HCWs was recruited in March 2020 at the Cantonal Hospital of St. Gallen and the Eastern Switzerland Children's Hospital. For data analysis, we used a combination of the following techniques: locally estimated scatterplot smoothing (LOESS) regression, Spearman correlation, anomaly detection, and random forest. Results: From March 23 to August 23, 2020, a total of 127,684 SMS text messages were sent, generating 90,414 valid reports among 1004 participants, achieving a weekly average of 4.5 (SD 1.9) reports per user. The symptom showing the strongest correlation with a positive polymerase chain reaction test result was loss of taste. Symptoms like red eyes or a runny nose were negatively associated with a positive test. The area under the receiver operating characteristic curve showed favorable performance of the classification tree, with an accuracy of 88\% for the training data and 89\% for the test data. Nevertheless, while the prediction matrix showed good specificity (80.0\%), sensitivity was low (10.6\%). Conclusions: Loss of taste was the symptom that was most aligned with COVID-19 activity at the population level. At the individual level---using machine learning--based random forest classification---reporting loss of taste and limb/muscle pain as well as the absence of runny nose and red eyes were the best predictors of COVID-19. ",
doi="10.2196/33576",
url="https://publichealth.jmir.org/2021/11/e33576",
url="http://www.ncbi.nlm.nih.gov/pubmed/34727046"
}


@Article{info:doi/10.2196/16901,
author="Fan, Yunzhou
and Wu, Yanyan
and Cao, Xiongjing
and Zou, Junning
and Zhu, Ming
and Dai, Di
and Lu, Lin
and Yin, Xiaoxv
and Xiong, Lijuan",
title="Automated Cluster Detection of Health Care--Associated Infection Based on the Multisource Surveillance of Process Data in the Area Network: Retrospective Study of Algorithm Development and Validation",
journal="JMIR Med Inform",
year="2020",
month="Oct",
day="23",
volume="8",
number="10",
pages="e16901",
keywords="health care--associated infection",
keywords="cluster detection",
keywords="early warning",
keywords="multi sources surveillance",
keywords="process data",
abstract="Background: The cluster detection of health care--associated infections (HAIs) is crucial for identifying HAI outbreaks in the early stages. Objective: We aimed to verify whether multisource surveillance based on the process data in an area network can be effective in detecting HAI clusters. Methods: We retrospectively analyzed the incidence of HAIs and 3 indicators of process data relative to infection, namely, antibiotic utilization rate in combination, inspection rate of bacterial specimens, and positive rate of bacterial specimens, from 4 independent high-risk units in a tertiary hospital in China. We utilized the Shewhart warning model to detect the peaks of the time-series data. Subsequently, we designed 5 surveillance strategies based on the process data for the HAI cluster detection: (1) antibiotic utilization rate in combination only, (2) inspection rate of bacterial specimens only, (3) positive rate of bacterial specimens only, (4) antibiotic utilization rate in combination + inspection rate of bacterial specimens + positive rate of bacterial specimens in parallel, and (5) antibiotic utilization rate in combination + inspection rate of bacterial specimens + positive rate of bacterial specimens in series. We used the receiver operating characteristic (ROC) curve and Youden index to evaluate the warning performance of these surveillance strategies for the detection of HAI clusters. Results: The ROC curves of the 5 surveillance strategies were located above the standard line, and the area under the curve of the ROC was larger in the parallel strategy than in the series strategy and the single-indicator strategies. The optimal Youden indexes were 0.48 (95\% CI 0.29-0.67) at a threshold of 1.5 in the antibiotic utilization rate in combination--only strategy, 0.49 (95\% CI 0.45-0.53) at a threshold of 0.5 in the inspection rate of bacterial specimens--only strategy, 0.50 (95\% CI 0.28-0.71) at a threshold of 1.1 in the positive rate of bacterial specimens--only strategy, 0.63 (95\% CI 0.49-0.77) at a threshold of 2.6 in the parallel strategy, and 0.32 (95\% CI 0.00-0.65) at a threshold of 0.0 in the series strategy. The warning performance of the parallel strategy was greater than that of the single-indicator strategies when the threshold exceeded 1.5. Conclusions: The multisource surveillance of process data in the area network is an effective method for the early detection of HAI clusters. The combination of multisource data and the threshold of the warning model are 2 important factors that influence the performance of the model. ",
doi="10.2196/16901",
url="http://medinform.jmir.org/2020/10/e16901/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32965228"
}


@Article{info:doi/10.2196/17242,
author="Martin, S{\'e}bastien
and Maeder, Nirina Muriel
and Gon{\c{c}}alves, Rita Ana
and Pedrazzini, Baptiste
and Perdrix, Jean
and Rochat, Carine
and Senn, Nicolas
and Mueller, Yolanda",
title="An Online Influenza Surveillance System for Primary Care Workers in Switzerland: Observational Prospective Pilot Study",
journal="JMIR Public Health Surveill",
year="2020",
month="Sep",
day="10",
volume="6",
number="3",
pages="e17242",
keywords="influenza",
keywords="surveillance system",
keywords="primary care",
keywords="online",
keywords="nosocomial",
keywords="transmission",
abstract="Background: A better understanding of the influenza epidemiology among primary care workers could guide future recommendations to prevent transmission in primary care practices. Therefore, we designed a pilot study to assess the feasibility of using a work-based online influenza surveillance system among primary care workers. Such an approach is of particular relevance in the context of the coronavirus disease (COVID-19) pandemic, as its findings could apply to other infectious diseases with similar mechanisms of transmission. Objective: This study aims to determine the feasibility of using a work-based online influenza surveillance system for primary care workers in Switzerland. Methods: Physicians and staff of one walk-in clinic and two selected primary care practices were enrolled in this observational prospective pilot study during the 2017-2018 influenza season. They were invited to record symptoms of influenza-like illness in a weekly online survey sent by email and to self-collect a nasopharyngeal swab in case any symptoms were recorded. Samples were tested by real-time polymerase chain reaction for influenza A, influenza B, and a panel of respiratory pathogens. Results: Among 67 eligible staff members, 58\% (n=39) consented to the study and 53\% (n=36) provided data. From the time all participants were included, the weekly survey response rate stayed close to 100\% until the end of the study. Of 79 symptomatic episodes (mean 2.2 episodes per participant), 10 episodes in 7 participants fitted the definition of an influenza-like illness case (attack rate: 7/36, 19\%). One swab tested positive for influenza A H1N1 (attack rate: 3\%, 95\% CI 0\%-18\%). Swabbing was considered relatively easy. Conclusions: A work-based online influenza surveillance system is feasible for use among primary care workers. This promising methodology could be broadly used in future studies to improve the understanding of influenza epidemiology and other diseases such as COVID-19. This could prove to be highly useful in primary care settings and guide future recommendations to prevent transmission. A larger study will also help to assess asymptomatic infections. ",
doi="10.2196/17242",
url="http://publichealth.jmir.org/2020/3/e17242/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32909955"
}


@Article{info:doi/10.2196/18855,
author="Baxter, L. Sally
and Klie, R. Adam
and Radha Saseendrakumar, Bharanidharan
and Ye, Y. Gordon
and Hogarth, Michael",
title="Text Processing for Detection of Fungal Ocular Involvement in Critical Care Patients: Cross-Sectional Study",
journal="J Med Internet Res",
year="2020",
month="Aug",
day="14",
volume="22",
number="8",
pages="e18855",
keywords="fungemia",
keywords="fungal endophthalmitis",
keywords="fungal ocular involvement",
keywords="electronic health records",
keywords="diagnosis codes",
keywords="regular expressions",
keywords="natural language processing",
keywords="unstructured data",
abstract="Background: Fungal ocular involvement can develop in patients with fungal bloodstream infections and can be vision-threatening. Ocular involvement has become less common in the current era of improved antifungal therapies. Retrospectively determining the prevalence of fungal ocular involvement is important for informing clinical guidelines, such as the need for routine ophthalmologic consultations. However, manual retrospective record review to detect cases is time-consuming. Objective: This study aimed to determine the prevalence of fungal ocular involvement in a critical care database using both structured and unstructured electronic health record (EHR) data. Methods: We queried microbiology data from 46,467 critical care patients over 12 years (2000-2012) from the Medical Information Mart for Intensive Care III (MIMIC-III) to identify 265 patients with culture-proven fungemia. For each fungemic patient, demographic data, fungal species present in blood culture, and risk factors for fungemia (eg, presence of indwelling catheters, recent major surgery, diabetes, immunosuppressed status) were ascertained. All structured diagnosis codes and free-text narrative notes associated with each patient's hospitalization were also extracted. Screening for fungal endophthalmitis was performed using two approaches: (1) by querying a wide array of eye- and vision-related diagnosis codes, and (2) by utilizing a custom regular expression pipeline to identify and collate relevant text matches pertaining to fungal ocular involvement. Both approaches were validated using manual record review. The main outcome measure was the documentation of any fungal ocular involvement. Results: In total, 265 patients had culture-proven fungemia, with Candida albicans (n=114, 43\%) and Candida glabrata (n=74, 28\%) being the most common fungal species in blood culture. The in-hospital mortality rate was 121 (46\%). In total, 7 patients were identified as having eye- or vision-related diagnosis codes, none of whom had fungal endophthalmitis based on record review. There were 26,830 free-text narrative notes associated with these 265 patients. A regular expression pipeline based on relevant terms yielded possible matches in 683 notes from 108 patients. Subsequent manual record review again demonstrated that no patients had fungal ocular involvement. Therefore, the prevalence of fungal ocular involvement in this cohort was 0\%. Conclusions: MIMIC-III contained no cases of ocular involvement among fungemic patients, consistent with prior studies reporting low rates of ocular involvement in fungemia. This study demonstrates an application of natural language processing to expedite the review of narrative notes. This approach is highly relevant for ophthalmology, where diagnoses are often based on physical examination findings that are documented within clinical notes. ",
doi="10.2196/18855",
url="https://www.jmir.org/2020/8/e18855",
url="http://www.ncbi.nlm.nih.gov/pubmed/32795984"
}


@Article{info:doi/10.2196/15182,
author="Sendak, P. Mark
and Ratliff, William
and Sarro, Dina
and Alderton, Elizabeth
and Futoma, Joseph
and Gao, Michael
and Nichols, Marshall
and Revoir, Mike
and Yashar, Faraz
and Miller, Corinne
and Kester, Kelly
and Sandhu, Sahil
and Corey, Kristin
and Brajer, Nathan
and Tan, Christelle
and Lin, Anthony
and Brown, Tres
and Engelbosch, Susan
and Anstrom, Kevin
and Elish, Clare Madeleine
and Heller, Katherine
and Donohoe, Rebecca
and Theiling, Jason
and Poon, Eric
and Balu, Suresh
and Bedoya, Armando
and O'Brien, Cara",
title="Real-World Integration of a Sepsis Deep Learning Technology Into Routine Clinical Care: Implementation Study",
journal="JMIR Med Inform",
year="2020",
month="Jul",
day="15",
volume="8",
number="7",
pages="e15182",
keywords="machine learning",
keywords="translational medicine",
keywords="sepsis",
keywords="innovation, organizational",
keywords="change",
keywords="deep learning",
abstract="Background: Successful integrations of machine learning into routine clinical care are exceedingly rare, and barriers to its adoption are poorly characterized in the literature. Objective: This study aims to report a quality improvement effort to integrate a deep learning sepsis detection and management platform, Sepsis Watch, into routine clinical care. Methods: In 2016, a multidisciplinary team consisting of statisticians, data scientists, data engineers, and clinicians was assembled by the leadership of an academic health system to radically improve the detection and treatment of sepsis. This report of the quality improvement effort follows the learning health system framework to describe the problem assessment, design, development, implementation, and evaluation plan of Sepsis Watch. Results: Sepsis Watch was successfully integrated into routine clinical care and reshaped how local machine learning projects are executed. Frontline clinical staff were highly engaged in the design and development of the workflow, machine learning model, and application. Novel machine learning methods were developed to detect sepsis early, and implementation of the model required robust infrastructure. Significant investment was required to align stakeholders, develop trusting relationships, define roles and responsibilities, and to train frontline staff, leading to the establishment of 3 partnerships with internal and external research groups to evaluate Sepsis Watch. Conclusions: Machine learning models are commonly developed to enhance clinical decision making, but successful integrations of machine learning into routine clinical care are rare. Although there is no playbook for integrating deep learning into clinical care, learnings from the Sepsis Watch integration can inform efforts to develop machine learning technologies at other health care delivery systems. ",
doi="10.2196/15182",
url="http://medinform.jmir.org/2020/7/e15182/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32673244"
}


@Article{info:doi/10.2196/18186,
author="Chen, Weijia
and Lu, Zhijun
and You, Lijue
and Zhou, Lingling
and Xu, Jie
and Chen, Ken",
title="Artificial Intelligence--Based Multimodal Risk Assessment Model for Surgical Site Infection (AMRAMS): Development and Validation Study",
journal="JMIR Med Inform",
year="2020",
month="Jun",
day="15",
volume="8",
number="6",
pages="e18186",
keywords="surgical site infection",
keywords="machine learning",
keywords="deep learning",
keywords="natural language processing",
keywords="artificial intelligence",
keywords="risk assessment model",
keywords="routinely collected data",
keywords="electronic medical record",
keywords="neural network",
keywords="word embedding",
abstract="Background: Surgical site infection (SSI) is one of the most common types of health care--associated infections. It increases mortality, prolongs hospital length of stay, and raises health care costs. Many institutions developed risk assessment models for SSI to help surgeons preoperatively identify high-risk patients and guide clinical intervention. However, most of these models had low accuracies. Objective: We aimed to provide a solution in the form of an Artificial intelligence--based Multimodal Risk Assessment Model for Surgical site infection (AMRAMS) for inpatients undergoing operations, using routinely collected clinical data. We internally and externally validated the discriminations of the models, which combined various machine learning and natural language processing techniques, and compared them with the National Nosocomial Infections Surveillance (NNIS) risk index. Methods: We retrieved inpatient records between January 1, 2014, and June 30, 2019, from the electronic medical record (EMR) system of Rui Jin Hospital, Luwan Branch, Shanghai, China. We used data from before July 1, 2018, as the development set for internal validation and the remaining data as the test set for external validation. We included patient demographics, preoperative lab results, and free-text preoperative notes as our features. We used word-embedding techniques to encode text information, and we trained the LASSO (least absolute shrinkage and selection operator) model, random forest model, gradient boosting decision tree (GBDT) model, convolutional neural network (CNN) model, and self-attention network model using the combined data. Surgeons manually scored the NNIS risk index values. Results: For internal bootstrapping validation, CNN yielded the highest mean area under the receiver operating characteristic curve (AUROC) of 0.889 (95\% CI 0.886-0.892), and the paired-sample t test revealed statistically significant advantages as compared with other models (P<.001). The self-attention network yielded the second-highest mean AUROC of 0.882 (95\% CI 0.878-0.886), but the AUROC was only numerically higher than the AUROC of the third-best model, GBDT with text embeddings (mean AUROC 0.881, 95\% CI 0.878-0.884, P=.47). The AUROCs of LASSO, random forest, and GBDT models using text embeddings were statistically higher than the AUROCs of models not using text embeddings (P<.001). For external validation, the self-attention network yielded the highest AUROC of 0.879. CNN was the second-best model (AUROC 0.878), and GBDT with text embeddings was the third-best model (AUROC 0.872). The NNIS risk index scored by surgeons had an AUROC of 0.651. Conclusions: Our AMRAMS based on EMR data and deep learning methods---CNN and self-attention network---had significant advantages in terms of accuracy compared with other conventional machine learning methods and the NNIS risk index. Moreover, the semantic embeddings of preoperative notes improved the model performance further. Our models could replace the NNIS risk index to provide personalized guidance for the preoperative intervention of SSIs. Through this case, we offered an easy-to-implement solution for building multimodal RAMs for other similar scenarios. ",
doi="10.2196/18186",
url="http://medinform.jmir.org/2020/6/e18186/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32538798"
}


@Article{info:doi/10.2196/16195,
author="Al-Orainan, Nourah
and EL-Shabasy, Mohamed Adel
and Al-Shanqiti, Alamin Khawlah
and Al-Harbi, Awad Rawan
and Alnashri, Rajeh Hadeel
and Rezqallah, Ahmed Raghad
and Mirghani, Abdallah Alanoud",
title="Public Awareness of Sepsis Compared to Acute Myocardial Infarction and Stroke in Jeddah, Saudi Arabia: Questionnaire Study",
journal="Interact J Med Res",
year="2020",
month="Jun",
day="15",
volume="9",
number="2",
pages="e16195",
keywords="sepsis",
keywords="public awareness",
keywords="survey",
abstract="Background: Sepsis is a state of organ dysfunction caused by an impaired host response to infection. It is one of the leading causes of death globally. Sepsis, acute myocardial infarction (AMI), and stroke share the primary management requirement of rapid intervention. This could be achieved through early presentation to the hospital, which demands previous knowledge of the disease to ensure better outcomes. Objective: Our study aimed to assess the level of public awareness of sepsis compared with AMI and stroke. Methods: This was a cross-sectional survey study performed in June and July 2018, with 1354 participants from Jeddah, Saudi Arabia, aged ?18 years. Data entry was performed using Microsoft Excel and statistical analysis including chi-square tests and multilogistic regression was performed using SPSS software. Results: A total of 1354 participants were included. Only 56.72\% (768/1354) had heard of the term ``sepsis'' and 48.44\% (372/768) of these participants were able to correctly identify it. In addition, 88.33\% (1196/1354) had heard the term ``myocardial infarction'' and 64.63\% (773/1196) knew the correct definition of that condition. Stroke was recognized by 81.46\% (1103/1354) of participants and 59.20\% (653/1103) of these participants correctly identified the condition. The difference between those who had heard of these diseases and those who knew the correct definition significantly differed from the values for awareness of sepsis and its definition. Conclusions: We found that public awareness and knowledge of sepsis are poor amongst the population of Jeddah compared with the awareness and knowledge of AMI and stroke. This lack of knowledge may pose a serious obstruction to the prompt management needed to limit fatal outcomes. ",
doi="10.2196/16195",
url="http://www.i-jmr.org/2020/2/e16195/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32538794"
}


@Article{info:doi/10.2196/12272,
author="Skelton, Felicia
and Martin, Ann Lindsey
and Evans, T. Charlesnika
and Kramer, Jennifer
and Grigoryan, Larissa
and Richardson, Peter
and Kunik, E. Mark
and Poon, Oiyee Ivy
and Holmes, Ann S.
and Trautner, W. Barbara",
title="Determining Best Practices for Management of Bacteriuria in Spinal Cord Injury: Protocol for a Mixed-Methods Study",
journal="JMIR Res Protoc",
year="2019",
month="Feb",
day="14",
volume="8",
number="2",
pages="e12272",
keywords="spinal cord injury",
keywords="urinary tract infection",
keywords="patient-focused care",
keywords="qualitative evaluation",
keywords="antimicrobial stewardship",
abstract="Background: Bacteriuria, either asymptomatic (ASB) or symptomatic, urinary tract infection (UTI), is common in persons with spinal cord injury (SCI). Current Veterans Health Administration (VHA) guidelines recommend a screening urinalysis and urine culture for every veteran with SCI during annual evaluation, even when asymptomatic, which is contrary to other national guidelines. Our preliminary data suggest that a positive urine culture (even without signs or symptoms of infection) drives antibiotic use. Objective: Through a series of innovative studies utilizing mixed methods, administrative databases, and focus groups, we will gain further knowledge about the attitudes driving current urine testing practices during the annual exam, as well as quantitative data on the clinical outcomes of these practices. Methods: Aim 1 will identify patient, provider, and facility factors driving bacteriuria testing and subsequent antibiotic use after the SCI annual evaluation through qualitative interviews and quantitative surveys. Aim 2 will use national VHA databases to identify the predictors of urine testing and subsequent antibiotic use during the annual examination and compare the clinical outcomes of those who received antibiotics with those who did not. Aim 3 will use the information gathered from the previous 2 aims to develop the Test Smart, Treat Smart intervention, a combination of patient and provider education and resources that will help stakeholders have informed conversations about urine testing and antibiotic use; feasibility will be tested at a single site. Results: This protocol received institutional review board and VHA Research and Development approval in July 2017, and Veterans Affairs Health Services Research and Development funding started on November 2017. As of submission of this manuscript, 10/15 (67\%) of the target goal of provider interviews were complete, and 77/100 (77\%) of the goal of surveys. With regard to patients, 5/15 (33\%) of the target goal of interviews were complete, and 20/100 (20\%) of the target goal of surveys had been completed. Preliminary analyses are ongoing; the study team plans to present these results in April 2019. Database analyses for aim 2 will begin in January 2019. Conclusions: The negative consequences of antibiotic overuse and antibiotic resistance are well-documented and have national and even global implications. This study will develop an intervention aimed to educate stakeholders on evidence-based management of ASB and UTI and guide antibiotic stewardship in this high-risk population. The next step will be to refine the intervention and test its feasibility and effectiveness at multiple sites as well as reform policy for management of this common but burdensome condition. International Registered Report Identifier (IRRID): DERR1-10.2196/12272 ",
doi="10.2196/12272",
url="https://www.researchprotocols.org/2019/2/e12272/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30762584"
}