Latest news
140 articles · 20 / page
Multicenter Validation Suggests MySurgeryRisk Can Accurately Predict Major Postoperative Complications and In-Hospital Mortality Across Diverse Hospitals
In a 14-institution cohort of more than 508,000 operations, MySurgeryRisk maintained high discrimination for ICU admission, mechanical ventilation, acute kidney injury, and in-hospital mortality using routine electronic health record data.
AI Model Shows Moderate Accuracy for Predicting Complete Response After Total Neoadjuvant Therapy in Locally Advanced Rectal Cancer
A fine-tuned ensemble of tabular foundation models moderately predicted pathological complete response after TNT and showed potential to support watch-and-wait selection after recalibration.
Computer-Aided Detection Increased Adenoma Detection in a Large Pragmatic Cluster Randomized Colonoscopy Study
In a large Veterans Health Administration cluster randomized study, CADe availability increased adenoma detection during colonoscopy without changing withdrawal time or nonadenomatous lesion detection.
Phenotyping Preeclampsia Using Unsupervised Machine Learning: A Prospective Cohort Study
Unsupervised machine learning identified three distinct preeclampsia phenotypes linked to timing of delivery, placental dysfunction, fetal growth, and complications, suggesting a path toward more personalized risk assessment and management.
Choosing a Stem Cell Donor: Why Age Matters More in Some Transplants Than Others
A major 2026 study suggests donor age affects survival differently in haploidentical and matched unrelated stem cell transplants, offering a more practical framework for choosing the best donor.
ChatGPT Assigned Different Traits to “Great Surgeons” by Race, Gender, and Sexual Orientation, Exposing Stereotypes Relevant to Academic Surgery
A qualitative study found that ChatGPT 3.5 described “great surgeons” differently by demographic identity, echoing stereotypes that may shape evaluations, leadership perceptions, and inclusion in surgery.
AI-ECG Identified Left Ventricular Systolic Dysfunction in Kenya With High Sensitivity and Excellent Rule-Out Performance
In Kenyan outpatient clinics, an AI-enabled ECG algorithm showed strong discrimination for left ventricular systolic dysfunction, with 95.6% sensitivity and 99.1% negative predictive value against echocardiography.
Ambient AI Scribes Reduced Emergency Department Documentation Time, but Early Adoption Was Limited and Highly Concentrated
In a real-world academic emergency department, ambient AI scribe use was uncommon and concentrated among a small group of physicians, but when used it was associated with shorter documentation and total EHR time.
AI Radiomics Detects Visually Occult Pancreatic Cancer on CT Nearly 16 Months Before Diagnosis and Outperforms Radiologists
A multi-institutional AI model identified pre-diagnostic pancreatic cancer on routine CT with meaningful lead time, higher sensitivity than radiologists, longitudinal stability, and externally validated specificity in a low-prevalence setti
AI vs. Human Clinicians: Study Reveals Gaps in AI-Generated Clinical Notes
A cross-sectional evaluation of AI-generated clinical notes found significant quality deficits compared to human-produced notes, particularly in thoroughness, organization, and usefulness.
Adaptive AI Transforms Cardiovascular Event Adjudication: New Algorithm Achieves Near-Human Accuracy Across Multiple Endpoints
Researchers developed and validated ADAPT-CEC, an artificial intelligence algorithm that can adjudicate cardiovascular events across different trial definitions. A hybrid approach combining AI with selective human review achieved 95.6% accu
Beyond Immersion: Why Combining Action Observation with Virtual Reality is a Game-Changer for Post-Stroke Hand Recovery
A multicenter randomized controlled trial reveals that integrating action observation with virtual reality significantly improves paretic hand dexterity in stroke patients, with benefits persisting six months post-intervention, offering a s
Precision Prediction of Incident Heart Failure: The Clinical Integration of AI-Enabled Electrocardiography
This review evaluates the breakthrough ECG2HF model, a publicly available AI tool that outperforms standard clinical scores in predicting 10-year heart failure risk using 12-lead ECG waveforms.
Breaking the Hardware Barrier: How Domain-Shift AI Enables Vendor-Agnostic 3D OCT Macular Disease Detection
A multicenter study in JAMA Ophthalmology introduces a deep learning model using domain-shift technology to accurately detect macular diseases across different OCT hardware vendors, achieving high negative predictive value and establishing
AI-Supported Mammography Outperforms Standard Double Reading: Insights from the MASAI Trial
The MASAI trial demonstrates that AI-supported mammography screening achieves higher sensitivity and non-inferior interval cancer rates compared to standard double reading, while maintaining specificity and significantly reducing radiologis
AI-Enabled Stethoscopes in Primary Care: Why Implementation Science Matters More Than Algorithm Accuracy
The TRICORDER trial demonstrates that while AI stethoscopes are capable of detecting heart failure, atrial fibrillation, and valvular disease, their real-world implementation in UK primary care did not yield a statistically significant incr
Telesurgery Breaks the Distance Barrier: Landmark RCT Confirms Non-Inferiority to Local Robotic Urology
A multicentre randomized controlled trial demonstrates that robotic telesurgery over distances up to 2800 km is non-inferior to local surgery for urological procedures, maintaining high success rates, low latency, and equivalent safety prof
Human-AI Collaboration Enhances Clinical Reasoning in Ophthalmology but Risks Overconfidence and Automation Bias
A crossover study involving 30 ophthalmologists and trainees reveals that while Claude-3.5-Sonnet collaboration improves diagnostic accuracy in complex cases, it also increases confidence in incorrect decisions and fails to reach the perfor
Precision Oncology Meets Artificial Intelligence: Navigating Ancestry-Associated Variability in Digital Pathology for EGFR Prediction
This review evaluates the generalizability of AI pathology models in predicting EGFR mutations, highlighting significant performance variations across genetic ancestries and specimen types, and their role in clinical triage.
Browse by specialty
Open language-specific specialty feeds and department pages.