Explore JAMA Network Open’s Health Informatics collection, including open access science about electronic health records, approaches to Big Data, and more.
This Viewpoint discusses the use of artificial intelligence in health care and its potential effect on how patients access care and how physicians and patients make decisions.
This cohort study develops and validates a deep learning algorithm using longitudinal electronic health records to predict mortality risk as a proxy indicator for identifying patients with dementia who may benefit from palliative care.
This case-control study describes the development and validation of a risk score, the Stopping Opioids After Surgery Score, for sustained prescription opioid use after surgery in a population of patients participating in a US Department of Defense insurance program.
This comparative effectiveness study of a nationwide clinical registry of percutaneous coronary intervention (PCI) determines whether machine learning techniques better predict post-PCI major bleeding compared with the existing National Cardiovascular Data Registry (NCDR) models.
This study describes a quantitative retinopathy of prematurity severity score derived using a deep learning algorithm designed to evaluate plus disease and assess its utility for objectively monitoring retinopathy of prematurity progression.
This cohort study uses clinical images collected for the Imaging and Informatics in Retinopathy of Prematurity consortium to assess whether an automated retinopathy of prematurity vascular severity score obtained from a deep learning–based algorithm plus disease classifier can objectively monitor disease progression and regression after treatment among infants with treatment-requiring disease.
This cross-sectional study uses machine reading to estimate the magnitude of female underrepresentation in clinical studies worldwide.
This prognostic study develops and validates a multivariable prediction model for assessing inpatient violence risk, using machine learning techniques applied to clinical notes written in patients’ electronic health records.
This study compares the use of machine learning optimal classification trees with the Pediatric Emergency Care Applied Research Network (PECARN) guidelines to determine the need for computed tomography imaging in children with clinically important traumatic brain injury.
This pilot randomized clinical trial assesses the feasibility and acceptability of a computer-facilitated screening questionnaire for substance use and practitioner-delivered brief intervention vs usual care among youths at primary care clinics.
This Viewpoint describes the use of artificial intelligence models for phenotyping and assessing sepsis risk as well as enhancing surgical decision making.
This meta-analysis evaluates the accuracy of computerized systems in the diagnosis of melanoma in patients with skin lesions.
In this Viewpoint, Ezekiel Emanuel and Robert Wachter discuss reasons for the hype surrounding the use of artificial intelligence (AI) in health care and emphasize the need for changes in structures and culture that can change behaviors of clinicians if AI-derived evidence is to be effectively translated into practice.
This diagnostic study assesses a convolutional neural network to enhance the detection of pathologic morphological features in duodenal tissue among children with environmental enteropathy, celiac disease, and no disease.
This study assesses the validity of an automated diabetic retinopathy system compared with manual grading across 2 sites in India.
This diagnostic study investigates the use of a neural network segmentation model to assist clinicians in the detection of intracranial aneurisms.
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: