Explore JAMA Network Open’s Health Informatics collection, including open access science about electronic health records, approaches to Big Data, and more.
This Viewpoint reviews conventional ways of assessing performance of machine learning models to diagnose or predict outcomes, but emphasizes that if machine learning is to improve patient care the models must be evaluated for their utility in improving clinical decisions taking into account the range of decisions clinicians can take, the cost and efficacy of those options, and the likelihood that patients will follow the recommended decisions.
This qualitative analysis using interviews with physicians determines barriers and facilitators in electronic health record inbox management and suggestions for improvement.
This Viewpoint proposes a template for thinking about physician malpractice liability arising from use of artificial intelligence (AI) in clinical practice, and identifies scenarios with and without injury and liability vs based on alignment of AI recommendations with standards of care, AI accuracy, and physician decisions in response.
This cross-sectional study investigates the association of surgical skin markings in dermoscopic images with the diagnostic performance of a deep learning convolutional neural network in 3 image sets of 130 melanocytic lesions each.
This cross-sectional study compares the diagnostic accuracy of a smartphone-based artificial intelligence system vs ophthalmologist judgement in patients with referable diabetic retinopathy or any diabetic retinopathy in Mumbai, India.
This cohort study examines the use of deep natural language processing in extraction of information on cancer outcomes from the medical records of patients with lung cancer.
This Viewpoint uses Dinerstein v Google, a class action complaint in Illinois alleging that an academic medical center violated patient privacy by giving timestamped electronic health record (EHR) data to Google for development of their novel EHR system, to review the ways privacy laws like HIPAA are based on outdated technologies and data transfer standards and to call for a rethinking of data sharing governance appropriate to contemporary infrastructure and expectations of interoperability.
This cluster randomized trial evaluates whether electronic medication reconciliation reduces medication discrepancies, adverse drug events, and other adverse outcomes compared with usual care.
This case series study examines how closely documentation in electronic health records matches the review of systems and physical examination performed by emergency physicians.
This qualitative study examines physician attitudes toward and perceptions of social media use for therapeutic trial recruitment of patients with cancer.
This cross-sectional study compares the sensitivity and specificity of automated classification of glaucomatous optic neuropathy on retinal fundus images by a deep-learning system with classification by human experts, using Chinese, multiethnic, and website-based datasets.
This article describes innovations in explainable artificial intelligence and machine learning techniques.
This diagnostic study uses machine learning models to assess the prevalence of low-yield inpatient laboratory tests.
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: