📣 Publication Spotlight | Yale NCSP Alumni

Congratulations to Yale NCSP alum Ben Howell, MD, MHS (2016–2017), on a new publication in JAMA Network Open!

Read the full article: jamanetwork.com/journals/jam...

#YaleNCSP #JAMANetworkOpen #HealthPolicy #AccessToCare

Vulnerability of Large Language Models to Prompt Injection When Providing Medical Advice Dec 19, 2025 MedicalScholarlyArticle by Ro Woon Lee, MD

This quality improvement study evaluates the susceptibility of commercial large language models (LLMs) to prompt-injection attacks that may induce unsafe clinical advice contraindicated treatments. #JAMANetworkOpen

Large Language Models and Communication of Medical Probabilities Dec 17, 2025 MedicalScholarlyArticle by Nicholas J. Jackson, BS

This diagnostic study investigates how chatbots interpret probability terms, such as rare, common, and possible, when describing medical risk. #JAMANetworkOpen

Uptake of Generative AI Integrated With Electronic Health Records in US Hospitals Dec 12, 2025 MedicalScholarlyArticle by Jordan Everson, PhD, MPP

This survey study describes the current and planned implementation of generative artificial intelligence (AI) in nonfederal acute care US hospitals. #JAMANetworkOpen

Development and Validation of a Hybrid Machine Learning Model to Predict Lung Transplant Outcomes Nov 25, 2025 MedicalScholarlyArticle by Gaurav Sharma, PhD, MBA

This prognostic study uses United Network for Organ Sharing data to develop, validate, and assess the clinical utility of an interpretable hybrid machine learning model to predict time to death or retransplant at 1, 5, and 10 years after a lung transplant. #JAMANetworkOpen

Chatbot-Delivered Real-Time Support to Improve HIV Self-Testing Rates: A Randomized Clinical Trial Nov 24, 2025 MedicalScholarlyArticle by Siyu Chen, PhD

This randomized clinical trial of men who have sex with men investigates whether a chatbot-delivered HIV self-testing service is similar to a self-testing service with online real-time support by human administrators in increasing self-testing uptake and counseling support. #JAMANetworkOpen

Digital Detection of Dementia in Primary Care: A Randomized Clinical Trial Nov 10, 2025 MedicalScholarlyArticle by Malaz A. Boustani, MD, MPH

This randomized clinical trial evaluates the effectiveness of an approach combining the Quick Dementia Rating System and Passive Digital Marker machine learning algorithm for the detection of Alzheimer disease and other related dementias in primary care. #JAMANetworkOpen

FDA Approval of Artificial Intelligence and Machine Learning Devices in Radiology: A Systematic Review Nov 07, 2025 MedicalScholarlyArticle by Ram Sivakumar, MD

This sytematic review examines US Food and Drug Administration (FDA) premarket clearances for artificial intelligence and machine learning devices in radiology with emphasis on testing. #JAMANetworkOpen

Use of Generative AI for Mental Health Advice Among US Adolescents and Young Adults Nov 07, 2025 MedicalScholarlyArticle by Ryan K. McBain, PhD, MPH

This cross-sectional study surveyed US adolescents and young adults on their use of generative artificial intelligence (AI) for mental health advice, including frequency and perceived helpfulness. #JAMANetworkOpen

Machine Learning Model for Response to Internet-Delivered CBT vs Antidepressant Medication Nov 06, 2025 MedicalScholarlyArticle by Chi Tak Lee, PhD

This prognostic study describes the development and validation of a machine learning model to predict patient response to internet-delivered cognitive behavioral therapy (CBT) and tests its specificity against antidepressant medications. #JAMANetworkOpen

Brief Digital Interventions for Psychological Distress: An AI-Enhanced Response-Adaptive Randomized Clinical Oct 31, 2025 MedicalScholarlyArticle by Jill Newby, PhD

This randomized clinical trial compares the effectiveness of 3 brief smartphone app–based interventions (physical activity, mindfulness, and sleep hygiene) or an active control (ecological momentary assessment) for reducing mild, moderate, and severe psychological distress among co… #JAMANetworkOpen

Prediction of Cardiopulmonary Resuscitation Outcomes for Arrest in Surgical Settings Oct 28, 2025 MedicalScholarlyArticle by Lucy Chen, MD, PhD

This prognostic study generates and internally validates predictive models for 30-day mortality and nonhome discharge using routinely available preoperative data. #JAMANetworkOpen

Syndromic Analysis of Sepsis Cohorts Using Large Language Models Oct 24, 2025 MedicalScholarlyArticle by Theodore R. Pak, MD, PhD

This cohort study compares the performance of a large language model against manual medical record review for extracting presenting signs and symptoms data from hospital admission notes and uses these data to examine their associations with different sepsis syndromes and mortality.… #JAMANetworkOpen

Extracting Symptoms of Sepsis From Admission Notes With LLM—Maybe AI Knows Something That We Do Not Oct 24, 2025 MedicalScholarlyArticle by Jonathan D. Baghdadi, MD, PhD

Clinicians hate sepsis because it is common, associated with a high risk of mortality, and hard to define. Almost any symptom can be associated with sepsis, 1 which means no symptom can be used to rule the diagnosis in or out. Basically, if a clinician suspects a patient might have… #JAMANetworkOpen

Adolescent Vulnerability to Consumer Chatbots—Artificial Agents and Genuine Risk Oct 23, 2025 MedicalScholarlyArticle by Alison Giovanelli, PhD

In their evaluation of consumer chatbots, Brewster et al 1 highlight critical gaps in how generative artificial intelligence (AI) platforms respond to simulated adolescent health crises, with companion chatbots performing especially poorly. These findings are particularly concernin… #JAMANetworkOpen

Characteristics and Safety of Consumer Chatbots for Emergent Adolescent Health Concerns Oct 23, 2025 MedicalScholarlyArticle by Ryan C. L. Brewster, MD

This cross-sectional study examines content policies and assesses behaviors of consumer chatbots in response to adolescent health crises. #JAMANetworkOpen

Diabetic Retinopathy Screening Among Federally Qualified Health Center Patients Using Point-of-Care AI: Oct 21, 2025 MedicalScholarlyArticle by Edgar A. Diaz, MD

This trial protocol describes a multicomponent randomized clinical trial that integrated an artificial intelligence (AI)–powered diabetic retinopathy screening workflow to improve screening rates, detection of early-stage disease, and timely eye specialist follow-up. #JAMANetworkOpen

Clinical Integration of Local AI Assistants Into Emergency Department Discharge Documentation Oct 21, 2025 MedicalScholarlyArticle by Jared Silberlust, MD, MPH

Song et al 1 have reported the development and in silico evaluation of a locally hosted large language model (LLM) assistant for generating discharge documentation in the emergency department (ED). The system—the Your Knowledgeable Navigator of Treatment ED discharge note generatio… #JAMANetworkOpen

Large Language Model Assistant for Emergency Department Discharge Documentation Oct 21, 2025 MedicalScholarlyArticle by Ji Woo Song

This comparative effectiveness study investigates a large language model designed to assist emergency department physicians with writing discharge notes and evaluates its effectiveness on documentation quality and workflow efficiency compared with manual note writing. #JAMANetworkOpen

Development of a Clinical Prediction Model for Anastomotic Leakage in Colorectal Surgery Oct 20, 2025 MedicalScholarlyArticle by Vincent Ochs

This prognostic study evaluates a meta-model that integrates logits from different existing predictive models combined with patient-specific features to predict anastomotic leakage risk after colorectal surgery. #JAMANetworkOpen

Machine Learning for Anastomotic Leak Prediction in Colorectal Surgery—Between Validation and Clinical Oct 20, 2025 MedicalScholarlyArticle by Kamacay Cira, MD

Despite decades of research and the proposal of numerous risk scores and prediction models, reliably identifying patients at risk for anastomotic leakage (AL) remains challenging—even for experienced surgeons. 1 , 2 AL contributes substantially to postoperative morbidity, mortality… #JAMANetworkOpen

Sodium Reduction Program Incorporating Genetic Profile and an AI-Based App: A Randomized Clinical Trial Oct 16, 2025 MedicalScholarlyArticle by Koryu Sato, MPH, PhD

This randomized clinical trial evaluates the effectiveness of a sodium reduction program incorporating a genetic profile and an artificial intelligence (AI)–based mobile app at reducing salt intake among adults with elevated blood pressure and a sodium-sensitive genotype. #JAMANetworkOpen

#BreastCancerResearch #AdjuvantTherapy #CancerOutcomes #OncologyResearch #RadiationTherapy #CancerTreatment #MSKResearch #ClinicalOncology #CancerSurvivorship #MSKInnovation #JAMANetworkOpen

A Hybrid Chatbot to Promote Pneumococcal Vaccination Among Older Adults: A Randomized Clinical Trial Oct 08, 2025 MedicalScholarlyArticle by Zixin Wang, PhD

This randomized clinical trial compares the relative efficacy of a hybrid chatbot delivering tailored interventions and providing real-time answers with a chatbot delivering the standard intervention to increase pneumococcal vaccination uptake among adults 65 years of age or older.… #JAMANetworkOpen

AI-Augmented Electron Microscopy for Glomerular Disease Diagnosis Oct 07, 2025 MedicalScholarlyArticle by Wisit Cheungpasitporn, MD

Accurate diagnosis of glomerular diseases remains essential for guiding patient treatment yet remains challenging in many complex cases. This study by Ma et al 1 presents a promising digital pathology tool using transmission electron microscopy (TEM) images, known as TEM-AID. This … #JAMANetworkOpen

AI-Based System for Analysis of Electron Microscope Images in Glomerular Disease Oct 07, 2025 MedicalScholarlyArticle by Pengcheng Ma, PhD

This diagnostic study describes the development and validation of an artificial intelligence (AI) model using transmission electron microscopy for the diagnosis of glomerular disease. #JAMANetworkOpen

Use of AI in Identification of Sexually Transmitted Infections and Anogenital Dermatoses: A Systematic Review Oct 03, 2025 MedicalScholarlyArticle by Nyi Nyi Soe, MPH

This systematic review and meta-analysis investigates the performance of artificial intelligence (AI) algorithms in detecting sexually transmitted infections and anogenital dermatoses from clinical images. #JAMANetworkOpen

AI-Driven Clinical Decision Support to Reduce Hospital-Acquired Venous Thromboembolism: A Trial Protocol Oct 03, 2025 MedicalScholarlyArticle by Colin G. Walsh, MD, MA

This trial protocol describes a randomized clinical trial to assess artificial intelligence (AI)–driven clinical decision support in reducing hospital-acquired venous thromboembolism incidence in hospitalized adults across urban and rural settings in Tennessee. #JAMANetworkOpen

AI-Enhanced Analysis of Built Environment Imagery and Neighborhood Obesity in US Cities Sep 30, 2025 MedicalScholarlyArticle by Zhuo Chen, PhD

This cross-sectional study investigates the association of artificial intelligence (AI)–enhanced analysis of geospatial built environment images with estimates of neighborhood obesity prevalence. #JAMANetworkOpen

Sociodemographic Bias in Large Language Model–Assisted Gastroenterology Sep 24, 2025 MedicalScholarlyArticle by Asaf Levartovsky, MD

This quality improvement study investigates the association of demographic characteristics with large language model–generated recommendations for simulated gastroenterology clinic cases. #JAMANetworkOpen