Search Articles

View query in Help articles search

Search Results (1 to 10 of 322 Results)

Download search results: CSV END BibTex RIS

CSV download: Download all 322 search results (up to 5,000 articles maximum)

Diagnostic Performance of Deep Learning and Radiomics in Extracranial Carotid Plaque Detection: Systematic Review and Meta-Analysis

Diagnostic Performance of Deep Learning and Radiomics in Extracranial Carotid Plaque Detection: Systematic Review and Meta-Analysis

In recent years, research on the application of these methods in the fields of plaque diagnosis, stability assessment, and symptomatic plaque identification has increased significantly. Although these advancements have significantly improved the diagnosis of carotid plaques, variations in data dependency and imaging configurations among different models create inconsistencies in diagnostic accuracy.

Lingjie Ju, Yongsheng Guo, Haiyong Guo, Ruijuan Liu, Yiyang Wang, Siyu Wang, Na Ma, Junhong Ren

J Med Internet Res 2026;28:e77092


Accuracy of Deep Learning in Diagnosing Chronic Obstructive Pulmonary Disease: Systematic Review and Meta-Analysis

Accuracy of Deep Learning in Diagnosing Chronic Obstructive Pulmonary Disease: Systematic Review and Meta-Analysis

In this context, some studies have used DL for the automatic diagnosis of COPD, such as DL-based chest X-ray (CXR), for the classification of COPD [10] and DL-based cough sound signal analysis [11]. Nevertheless, systematic evidence of the actual performance and comparative advantages of different DL frameworks in the diagnosis of COPD is lacking. Therefore, we conducted a systematic review and meta-analysis of diagnostic test accuracy studies on DL models for COPD.

Hui Yang, Yijiu Wu, Tong Wu, Jingyan Ji, Sitao Lei, Weibin Xu

J Med Internet Res 2026;28:e83459


AI-Supported Digital Microscopy Diagnostics in Primary Health Care Laboratories: Scoping Review

AI-Supported Digital Microscopy Diagnostics in Primary Health Care Laboratories: Scoping Review

English Non-English Published peer-reviewed studies Diagnostic test accuracy studies Non–peer reviewed studies Not diagnostic test accuracy studies Humans Studies performed on animals AIa techniques applied as a diagnostic tool on microscopy Final slide-level diagnosis was performed and compared with a standard microscopist Outcome valuable for clinicians Studies that applied AI models on images not conventionally analyzed in microscopy No final slide diagnosis Performed at primary health care laboratory (tier

Joar von Bahr, Antti Suutala, Vinod Diwan, Andreas Mårtensson, Johan Lundin, Nina Linder

J Med Internet Res 2026;28:e78500


Newly Designed Optical Coherence Tomography Catheter for Optimizing Bladder Cancer Diagnosis and Treatment: Protocol for a Feasibility Study

Newly Designed Optical Coherence Tomography Catheter for Optimizing Bladder Cancer Diagnosis and Treatment: Protocol for a Feasibility Study

Feasibility based on image use will be evaluated as the percentage of images suitable for diagnosis out of the total number of OCT images obtained. A percentage greater than 80% is regarded as feasible.

Marinka Jolinde Remmelink, Jakko A Nieuwenhuijzen, Daniel Martijn de Bruin, Jorg R Oddens

JMIR Res Protoc 2025;14:e76644


Impact of AI on Breast Cancer Detection Rates in Mammography by Radiologists of Varying Experience Levels in Singapore: Preliminary Comparative Study

Impact of AI on Breast Cancer Detection Rates in Mammography by Radiologists of Varying Experience Levels in Singapore: Preliminary Comparative Study

Mammograms are a critical tool in breast cancer diagnosis; however, interpreting them is inherently challenging. Expertise is acquired only after lengthy training; however, there is a shortage of seasoned senior radiologists [1] due to workforce aging and rising demand for breast cancer screening and diagnosis. The scarcity of skilled professionals in this field is particularly critical in health care systems that increasingly prioritize health screening and primary prevention.

Serene Si Ning Goh, Hao Du, Loon Ying Tan, Edward Zhen Yu Seah, Wai Keat Lau, Alvin Hong Zhi Ng, Shi Wei Desmond Lim, Han Yang Ong, Samuel Lau, Yi Liang Tan, Mun sze Khaw, Chee Woei Yap, Kei Yiu Douglas Hui, Wei Chuan Tan, Haziz Siti Rozana Binti Abdul, Vanessa Mei Hui Khoo, Shuliang Ge, Felicity Jane Pool, Yun Song Choo, Yi Wang, Pooja Jagmohan, Premilla Pillay Gopinathan, Mikael Hartman, Mengling Feng

JMIR Form Res 2025;9:e66931


Teledermatology to Support Self-Care in Chronic Spontaneous Urticaria

Teledermatology to Support Self-Care in Chronic Spontaneous Urticaria

Given the rich structural and topological elements associated with symptoms (eg, hives, itch), there is natural interest in the use of imaging technologies coupled with computational tools to improve diagnosis [7]. In one recent teledermatological study involving over 16,000 cases, a deep learning system was deployed on photographic images and demonstrated high diagnostic accuracy [8].

Laura Schuehlein, Martin Peters, Graham Jones

JMIR Dermatol 2025;8:e81830


Comparing Generative Artificial Intelligence and Mental Health Professionals for Clinical Decision-Making With Trauma-Exposed Populations: Vignette-Based Experimental Study

Comparing Generative Artificial Intelligence and Mental Health Professionals for Clinical Decision-Making With Trauma-Exposed Populations: Vignette-Based Experimental Study

Trauma-related diagnostic overshadowing for these likelihood ratings was defined as lower ratings for the target diagnosis (ie, OCD or SUD) or higher ratings for a PTSD diagnosis when trauma exposure was present versus absent. Respondents were then asked to select the primary diagnosis they would assign from the list of diagnoses.

Katherine E Wislocki, Sabahat Sami, Gahl Liberzon, Alyson K Zalta

JMIR Ment Health 2025;12:e80801


Differential Diagnosis Assessment in Ambulatory Care With a Digital Health History Device: Pseudorandomized Study

Differential Diagnosis Assessment in Ambulatory Care With a Digital Health History Device: Pseudorandomized Study

Among these devices is “DIANNA” (diagnosis and anamnesis), which has undergone substantial improvements since its initial development. A previous randomized controlled trial provided early insights into the tool’s impact on diagnostic accuracy and efficiency. Building on this foundation, DIANNA now includes a body pictogram feature to better select symptomatic areas, making it more intuitive and comprehensive for clinicians [4,5].

Beth Healey, Adrien Schwitzguebel, Herve Spechbach

JMIR Form Res 2025;9:e56384


Large Language Models in Lung Cancer: Systematic Review

Large Language Models in Lung Cancer: Systematic Review

In recent years, integrated full-cycle management—covering prevention, screening, diagnosis, treatment, and supportive care—has been promoted to improve both survival and quality of life [7,8]. However, this approach requires complex workflows and large-scale data processing, placing heavy demands on medical resources and personnel. Artificial intelligence, particularly large language models (LLMs), offers a potential solution.

Ruikang Zhong, Siyi Chen, Zexing Li, Tangke Gao, Yisha Su, Wenzheng Zhang, Dianna Liu, Lei Gao, Kaiwen Hu

J Med Internet Res 2025;27:e74177


Diagnostic and Screening AI Tools in Brazil’s Resource-Limited Settings: Systematic Review

Diagnostic and Screening AI Tools in Brazil’s Resource-Limited Settings: Systematic Review

RQ1: Is the tool used for diagnosis or screening? This question helps clarify the primary objective of each intervention. This distinction is essential, as screening focuses on maximizing sensitivity to ensure few actual cases are missed, while diagnosis aims to confirm or rule out a condition in individuals already identified as at risk, requiring a balance between sensitivity and specificity. RQ2: What is the context and location of the tool’s application?

Leticia Medeiros Mancini, Luiz Eduardo Vanderlei Torres, Jorge Artur P de M Coelho, Nichollas Botelho da Fonseca, Pedro Fellipe Dantas Cordeiro, Samara Silva Noronha Cavalcante, Diego Dermeval

JMIR AI 2025;4:e69547