Search Articles

View query in Help articles search

Search Results (1 to 10 of 284 Results)

Download search results: CSV END BibTex RIS


Machine Learning Models for Frailty Classification of Older Adults in Northern Thailand: Model Development and Validation Study

Machine Learning Models for Frailty Classification of Older Adults in Northern Thailand: Model Development and Validation Study

The study results were reported in accordance with the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis plus Artificial Intelligence (TRIPOD+AI) statement [45]. Baseline characteristics of participants in this study are shown in Table 1. The participants in the internal validation dataset had a mean age of 71.0 years. Most of the participants were male and had finished primary school.

Natthanaphop Isaradech, Wachiranun Sirikul, Nida Buawangpong, Penprapa Siviroj, Amornphat Kitro

JMIR Aging 2025;8:e62942

The Importance of Comparing New Technologies (AI) to Existing Tools for Patient Education on Common Dermatologic Conditions: A Commentary

The Importance of Comparing New Technologies (AI) to Existing Tools for Patient Education on Common Dermatologic Conditions: A Commentary

Reference 1: The comparative sufficiency of ChatGPT, Google Bard, and Bing AI in answering diagnosis,diagnosis

Parker Juels

JMIR Dermatol 2025;8:e71768

AI-Derived Blood Biomarkers for Ovarian Cancer Diagnosis: Systematic Review and Meta-Analysis

AI-Derived Blood Biomarkers for Ovarian Cancer Diagnosis: Systematic Review and Meta-Analysis

The conventional diagnosis of OC principally depends on imaging techniques (encompassing ultrasound, computed tomography, and magnetic resonance imaging); serum biomarkers (such as cancer antigen 125, carcinoembryonic antigen, and human epididymis protein 4); along with the invasive procedure (histological biopsy) [3,4]. However, the sensitivity and specificity of imaging techniques and biomarkers are restricted [5]. Furthermore, the histopathological test is inherently invasive [3].

He-Li Xu, Xiao-Ying Li, Ming-Qian Jia, Qi-Peng Ma, Ying-Hua Zhang, Fang-Hua Liu, Ying Qin, Yu-Han Chen, Yu Li, Xi-Yang Chen, Yi-Lin Xu, Dong-Run Li, Dong-Dong Wang, Dong-Hui Huang, Qian Xiao, Yu-Hong Zhao, Song Gao, Xue Qin, Tao Tao, Ting-Ting Gong, Qi-Jun Wu

J Med Internet Res 2025;27:e67922

Lessons Learned From European Health Data Projects With Cancer Use Cases: Implementation of Health Standards and Internet of Things Semantic Interoperability

Lessons Learned From European Health Data Projects With Cancer Use Cases: Implementation of Health Standards and Internet of Things Semantic Interoperability

These projects include the following: Chameleon: a project focused on developing AI algorithms for cancer diagnosis and prognosis. Eu Can Image: a project aimed at creating a large-scale cancer image database. Pro CAncer-I: a project focused on developing AI-based tools for personalized cancer treatment. Incisive: a project contributing a significant amount of cancer image data to EUCAIM. Primage: a project focused on developing AI-based image analysis techniques for cancer diagnosis.

Amelie Gyrard, Somayeh Abedian, Philip Gribbon, George Manias, Rick van Nuland, Kurt Zatloukal, Irina Emilia Nicolae, Gabriel Danciu, Septimiu Nechifor, Luis Marti-Bonmati, Pedro Mallol, Stefano Dalmiani, Serge Autexier, Mario Jendrossek, Ioannis Avramidis, Eva Garcia Alvarez, Petr Holub, Ignacio Blanquer, Anna Boden, Rada Hussein

J Med Internet Res 2025;27:e66273

Evaluating the Diagnostic Accuracy of ChatGPT-4 Omni and ChatGPT-4 Turbo in Identifying Melanoma: Comparative Study

Evaluating the Diagnostic Accuracy of ChatGPT-4 Omni and ChatGPT-4 Turbo in Identifying Melanoma: Comparative Study

GPT-4 Omni and GPT-4 Turbo demonstrate low accuracy and low specificity for melanoma diagnosis. Accuracy of Chat GPT-4o in diagnosing melanoma and “not melanoma” with binary versus nonbinary prompting. Currently, GPT engines demonstrate low accuracy for diagnosing melanoma. Higher diagnostic accuracies have been achieved using neural networks such as Moleanalyzer pro (87.7%) and Chat GPT Vision (85%); however, these studies included much smaller sample sizes of 100 and 60 images, respectively [7,8].

Samantha S. Sattler, Nitin Chetla, Matthew Chen, Tamer Rajai Hage, Joseph Chang, William Young Guo, Jeremy Hugh

JMIR Dermatol 2025;8:e67551

The Utilization of Electronic Consultations (eConsults) to Address Emerging Questions Related to Long COVID-19 in Ontario, Canada: Mixed Methods Analysis

The Utilization of Electronic Consultations (eConsults) to Address Emerging Questions Related to Long COVID-19 in Ontario, Canada: Mixed Methods Analysis

In response to the pandemic, an e Consult service operating in Ontario, Canada, launched a long COVID specialist group, allowing PCPs to connect with specialists across multiple disciplines with expertise in long COVID to help with the diagnosis and management of their patients. Previous studies assessing this e Consult service in Ontario have demonstrated improved access to specialty care, reduced need for face-to-face specialist visits, cost savings, and high physician satisfaction [4-8].

Jatinderpreet Singh, Michael Quon, Danica Goulet, Erin Keely, Clare Liddy

JMIR Hum Factors 2025;12:e58582

Stroke Diagnosis and Prediction Tool Using ChatGLM: Development and Validation Study

Stroke Diagnosis and Prediction Tool Using ChatGLM: Development and Validation Study

The objective of this study was to develop an acute stroke diagnosis tool that guides key therapies based on Chat GLM-6 B and to verify its accuracy in diagnosing and predicting strokes. The application of this model in primary care could enhance the standard workflow for stroke diagnosis, identify patients who could benefit from recanalization, and facilitate risk prediction.

Xiaowei Song, Jiayi Wang, Feifei He, Wei Yin, Weizhi Ma, Jian Wu

J Med Internet Res 2025;27:e67010

Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study

Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study

We aimed to identify the clinical features that are associated with earlier diagnosis of dementia from the first memory loss complaints. Results indicated that the location of the first complaints made and the diagnosis, as well as the relation of the primary caregiver, were significantly associated with earlier diagnosis of dementia.

Hunki Paek, Richard H Fortinsky, Kyeryoung Lee, Liang-Chin Huang, Yazeed S Maghaydah, George A Kuchel, Xiaoyan Wang

JMIR Aging 2025;8:e65221

Establishing Syndromic Surveillance of Acute Coronary Syndrome, Myocardial Infarction, and Stroke: Registry Study Based on Routine Data From German Emergency Departments

Establishing Syndromic Surveillance of Acute Coronary Syndrome, Myocardial Infarction, and Stroke: Registry Study Based on Routine Data From German Emergency Departments

It included ICD-10-GM discharge diagnoses (further referred to as “hospital discharge diagnoses”), as well as information on diagnosis certainty and whether they were labeled as the “main diagnosis.” The information was routinely collected during inpatient treatment according to the German social laws regulating the billing of inpatient services and obliging hospitals to transmit billing data to a federal agency (§ 21 Krankenhausentgeltgesetz, KHEntg G).

Madlen Schranz, Mirjam Rupprecht, Annette Aigner, Leo Benning, Carmen Schlump, Nesrine Charfeddine, Michaela Diercke, Linus Grabenhenrich, Alexander Ullrich, Hannelore Neuhauser, Birga Maier, AKTIN Research Group, Felix Patricius Hans, Sabine Blaschke

JMIR Public Health Surveill 2025;11:e66218