May 07, 2026

LLM Explanations: Steps Matter in Radiology

Radiologists assigned to receive step-by-step explanations from a large language model achieved higher diagnostic accuracy in a randomized vignette study, while differential-diagnosis outputs may have increased inappropriate reliance on incorrect model suggestions.

Conexiant

May 04, 2026

FDA Cleared ≠ FDA Validated

Most AI medical devices reach the market without independent evidence of safety or effectiveness.

Conexiant

April 28, 2026

AI in Surgery: Debate Highlights Benefits, Gaps

Surgeons and researchers clash over whether current AI systems are ready for clinical use — and what responsible adoption would require.

Conexiant

April 27, 2026

CT Perfusion Detects Tissue at Risk in Mild Stroke

Perfusion imaging adds prognostic information in patients with low National Institutes of Health Stroke Scale scores.

Conexiant

April 23, 2026

Medical Oddities: Chew on This Cancer Prevention Idea

From gum to gut to memory—medicine gets weirdly clever fast 

Conexiant

April 21, 2026

Psychedelics Increase Brain Network Integration

Mega-analysis found stronger connectivity between higher-order and sensorimotor networks, with variable and often minimal within-network changes.

Conexiant

April 17, 2026

AI Scribes Lag Clinicians on Note Quality

A VHA study across 11 vendors finds AI-generated primary care notes score lower than clinician-written notes, with the largest deficits in thoroughness, organization, and usefulness

Conexiant

April 17, 2026

Lactate–Albumin Ratio Tied to TBI Mortality

Admission biomarker showed prognostic value alongside clinical scoring systems in pediatric intensive care

Conexiant

April 16, 2026

Mandatory Training Modules Deserve a Harder Look

A JAMA Viewpoint argues that 4 million physician-hours spent on compliance modules each year warrants institutional reassessment.

Conexiant

April 13, 2026

AI Falls Short on Differential Dx

New PrIME-LLM benchmark shows strong diagnostic accuracy but persistent gaps in clinical reasoning across 21 large language models

Conexiant