Search Articles

View query in Help articles search

Search Results (1 to 10 of 195 Results)

Download search results: CSV END BibTex RIS


Proposal for Using AI to Assess Clinical Data Integrity and Generate Metadata: Algorithm Development and Validation

Proposal for Using AI to Assess Clinical Data Integrity and Generate Metadata: Algorithm Development and Validation

We then compared the results of each model in a table that included accuracy, precision, recall, and scoring. Multiple machine learning algorithms were evaluated for predicting the quality of echocardiography data, with LR serving as the baseline model. LR achieved an accuracy of 73.0% (0.73/1), precision of 57.1% (0.571/1), recall of 73.0% (0.73/1), F1-score of 64.1% (0.641/1), and an AUC-ROC score of 52.4% (0.524/1).

Caroline Bönisch, Christian Schmidt, Dorothea Kesztyüs, Hans A Kestler, Tibor Kesztyüs

JMIR Med Inform 2025;13:e60204

A Companion Robot for Children With Asthma: Descriptive Development and Feasibility Pilot Study

A Companion Robot for Children With Asthma: Descriptive Development and Feasibility Pilot Study

In-depth interviews were conducted with a semistructured format to gain information about caregivers’ perceptions of the asthma management app and the pediatric asthma model. This approach facilitated a nuanced exploration of caregivers’ attitudes, including barriers and facilitators to app. The interview consisted of 7 main questions developed to prompt discussion on previous experiences with similar technologies, willingness to use the asthma model, and opinions on the model’s design.

Jinnaphat Sangngam, Somsiri Rungamornrat, Rungnapa Santipipat, Kunchira Ponthanee

JMIR Pediatr Parent 2025;8:e68943

Artificial Intelligence in Patch Testing: Comprehensive Review of Current Applications and Future Prospects in Dermatology

Artificial Intelligence in Patch Testing: Comprehensive Review of Current Applications and Future Prospects in Dermatology

Summary of articles included in this comprehensive review of artificial intelligence in patch testing. a Genetic Algo Rithm for biomarker selection in high-dimensional Omics with RF-based classifier. b Tuning set refers to a subset of data used to fine-tune the parameters of a machine learning model. In this study, the tuning set was used to optimize the hyperparameters of RF and LR models before final evaluation on the validation dataset.

Hilary S Tang, Joseph Ebriani, Matthew J Yan, Shannon Wongvibulsin, Mehdi Farshchian

JMIR Dermatol 2025;8:e67154

Transformer-Based Language Models for Group Randomized Trial Classification in Biomedical Literature: Model Development and Validation

Transformer-Based Language Models for Group Randomized Trial Classification in Biomedical Literature: Model Development and Validation

The outcome of this fine-tuning process is a model that provides a high level of sensitivity and specificity in classifying and differentiating various types of randomized trial publications. In our study, we initially established a baseline model for classifying publications using traditional machine learning and word embedding techniques to demonstrate the effectiveness of employing a transformer-based model in identifying publications based on nested designs.

Elaheh Aghaarabi, David Murray

JMIR Med Inform 2025;13:e63267

Comparing Diagnostic Accuracy of Clinical Professionals and Large Language Models: Systematic Review and Meta-Analysis

Comparing Diagnostic Accuracy of Clinical Professionals and Large Language Models: Systematic Review and Meta-Analysis

The Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to evaluate the risk of bias and applicability of all included studies [8]. PROBAST assesses risk of bias across 4 domains: study participants, predictors, outcomes, and statistical analysis, while applicability is evaluated through the first 3 domains.

Guxue Shan, Xiaonan Chen, Chen Wang, Li Liu, Yuanjing Gu, Huiping Jiang, Tingqi Shi

JMIR Med Inform 2025;13:e64963

Public Disclosure of Results From Artificial Intelligence/Machine Learning Research in Health Care: Comprehensive Analysis of ClinicalTrials.gov, PubMed, and Scopus Data (2010-2023)

Public Disclosure of Results From Artificial Intelligence/Machine Learning Research in Health Care: Comprehensive Analysis of ClinicalTrials.gov, PubMed, and Scopus Data (2010-2023)

Clearly, significant challenges exist even before introducing the added complexities of multicenter studies, which involve substantial clustering (eg, across multiple centers, regions, or countries) and require more rigorous design, analysis, and reporting methods compared to standard prediction model studies [50].

Shoko Maru, Ryohei Kuwatsuru, Michael D Matthias, Ross J Simpson Jr

J Med Internet Res 2025;27:e60148

Assessing the Diagnostic Accuracy of ChatGPT-4 in Identifying Diverse Skin Lesions Against Squamous and Basal Cell Carcinoma

Assessing the Diagnostic Accuracy of ChatGPT-4 in Identifying Diverse Skin Lesions Against Squamous and Basal Cell Carcinoma

The model showed significant bias in SCC classification, frequently misclassifying SCC as BCC with a high rate of false-positive results. This aligns with previous research that observed SCC is often mistaken for BCC, particularly when features like pigmentation or rolled borders overlap [8]. Chat GPT’s performance worsened in Prompt 2, where SCC was frequently misclassified as AK.

Nitin Chetla, Matthew Chen, Joseph Chang, Aaron Smith, Tamer Rajai Hage, Romil Patel, Alana Gardner, Bridget Bryer

JMIR Dermatol 2025;8:e67299

ChatGPT’s Performance on Portuguese Medical Examination Questions: Comparative Analysis of ChatGPT-3.5 Turbo and ChatGPT-4o Mini

ChatGPT’s Performance on Portuguese Medical Examination Questions: Comparative Analysis of ChatGPT-3.5 Turbo and ChatGPT-4o Mini

Chat GPT, the large language model (LLM) chatbot, developed by Open AI [4], that started the AI boom in November 2022, became the most popular AI tool of 2023, accounting for over 60.2% of visits between September 2022 and August 2023, with a total of 14.6 billion website visits [5].

Filipe Prazeres

JMIR Med Educ 2025;11:e65108