Clinical multi-agent systems launder demographic triage disparity
On 120 MIMIC-IV cases, all 20 model-topology cells gave Black patients more acute triage; pooling perspectives cut the gap 67–94%.
Stories per day · 30 days
4 RSS
Relatedbenchmark2ehr2healthcare2mimic-iv2multimodal2acceptance-gate1adress1agents1algorithmic-bias1alignment1anthropic1class-imbalance1cross-fitting1data-leakage1dementia-detection1diagnostics1disease-trajectories1embeddings1
21 stories, newest first · one card per story
Stories tagged #clinical-ai
Clinical selective prediction misreads imbalance as uncertainty
Across 56 synthetic settings and three disease cohorts, standard entropy failed to protect minority patients.
Fed-Universe proposes negotiated alignment for federated learners
A synthetic binational clinical simulation cut a minority node's loss from 0.857 to 0.340 despite under 3% of the data.
Microsoft says MAI-DxO beat generalist doctors on hard cases
In a simulation of complex NEJM cases, MAI-DxO was correct 83% of the time versus 36% for generalists.
Doctors’ ad-backed AI tool OpenEvidence draws mixed clinical evidence
A Mayo Clinic sample of five cases was favorable, while a Nature paper found it trailed Gemini and GPT on clinical benchmarks.
1
BRIDGE gate blocks false model-update gains in retrospective tests
False-improvement rates fell from about 12–26% under a naive rule to 0–1.7% across five dataset groups.
NarraSpace ties picture-description speech to dementia scores
On the 48-participant ADReSS test set, a fixed SVM reached 80.88% mean accuracy over fifty seeds.
LeakBench audits clinical agents for prediction-time leakage
DeepSeek Flash and GPT-6-astra leaked in 10 of 10 unconstrained September runs and in none when an admission-time constraint was set.
TRACE models daily clinical trajectories for inpatient risk prediction
On nearly 180,000 stays from MIMIC-IV, eICU, and MIMIC-III, authors report the highest AUROC in all nine settings.
MindEval2: Clinically Grounded Patients and Rubrics for Evaluating Language Models in Mental Health Support
MindEval2 benchmarks 18 language models on mental-health support using clinician rubrics and realistic simulated patients.
AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions
AI Consilium shows model choice beats format for clinical LLM second opinions on NEJM cases.
A Two-Level Clinical Novelty Prioritization Framework for Disease Trajectories Discovered from Longitudinal Electronic Health Records
A two-level framework ranks 99,527 MIMIC-IV disease trajectories by literature novelty and clinical priority.
Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis
PRISM reports high AUROCs for emergency diagnosis, deterioration, ICU admission, and mortality.
Clinician use of language models diverges from how the models are evaluated
Study of 127,833 clinician queries finds LLM benchmarks poorly match real clinical assistant use.
Healthleap raises $38M for its AI that flags hospital patients who may need a closer look
Healthleap raised $38 million to scale hospital AI that flags patients who may have undiagnosed conditions.
3
Incidental information contaminates patient notes and disrupts clinical reasoning in large language models
Frontier LLMs insert small talk into 35% of clinical notes and sometimes treat it as clinical fact.
Beyond Accuracy: Counterfactual Fragility and Demographic Bias in Clinical Evaluation of LLMs
Clinical LLM tests find accuracy outruns counterfactual validity, with frequent answer changes under demographic prefixes.
OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories
OpenTumorBoard benchmarks LLMs on 611 real multidisciplinary tumor-board cases and discussions.
K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
Clinician-calibrated K-Bench evaluates 125 LLM configurations on 200 high-risk mental health vignettes, exposing wide variation in suicide and violence risk handling.
Performance of Clinical AI System and Physicians and Frontier Language Models in primary care diagnostics
Clinical AI system Doctorina achieved 82.0% primary-care diagnostic concordance versus 57.0% for physicians across 150 synthetic consultations.
AMIE, our research medical AI system, demonstrates real-time clinical video consultation capabilities in a first-of-its-kind study.
Google's AMIE research medical AI system demonstrates real-time clinical video consultations in a first-of-its-kind simulated study.