SkinMind uses graph probing for dermatology retrieval-augmented generation
Authors report average gains of 8.70 and 8.89 points with GPT-5.4-mini and Gemini-2.5-Flash on six VQA benchmarks.
Stories per day · 30 days
2 RSS
Relateddermatology2llm-evaluation2multimodal2benchmark1benchmarks1bert1care-pathway1clinical-benchmark1competing-risks1deep-learning1dermoscopy1diagnosis1ecg1foundation-model1health1inception-v31knowledge-graph1model-evaluation1
15 stories, newest first · one card per story
Stories tagged #medical-ai
NPCBench benchmark evaluates multimodal care-pathway reasoning for nasopharyngeal carcinoma
NPCBench includes 4,777 items and a 100-patient CarePath cohort with 417 scored tasks, revealing composition gaps where strong individual model performance does not ensure jointly correct diagnostic and care answers.
Medical AI agents access PHI silently without disclosure
Silent access to PHI by AI agents remains invisible to output-only evaluations; pre-execution gates nearly eliminate it.
NPC-RubricBench shows LLM cancer-care errors reverse by phase
Across 405 patients, strong diagnosis did not carry into later care, and prompt style traded quality against faithfulness.
Fine-tuned Inception v3 beats GPT-6 Astra and Claude on skin cancer
On 200 biopsy-proven MILK10k lesions, the CNN named the diagnosis for 125 cases versus 84 and 85 for the LLMs.
1
Study finds medical models adopt incorrect patient diagnoses
Nine models accepted an incorrect patient belief 23.2% of the time, rising to 43.0% for a rare-disease persona.
QECGBERT tokenizes ECG waveforms for BERT-style pretraining
It is pretrained on more than 800,000 unlabeled MIMIC-IV ECGs and fine-tuned on three labeled datasets.
MMedAgent-Plus coordinates 18 specialist models across medical tasks
End-to-end final-answer accuracy is 0.98, matching the dedicated specialist and above a 0.28 baseline.
The Loss or the Architecture? What Matters in Survival Analysis with Competing Risks
A 23-dataset benchmark finds cumulative-incidence loss, not backbone choice, drives competing-risks performance.
Utah to let AI examine patients and prescribe medication without human oversight
Utah will let Nolla Health's AI examine acne and prescribe topical medication with limited physician oversight.
2
Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI
A model-agnostic memory framework lets frozen medical LLMs and VLMs improve online by up to 34.2%.
From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning
CASE trains compact medical agents to gather longitudinal evidence, with an 8B model outperforming larger frontier systems.
Bristol researchers say medicine already knows how to handle black boxes and AI could learn from it
Bristol researchers propose a drug-style dossier for testing medical AI reliability before clinical use.
1
CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation
CARDEA, a vision-language model trained only on public data, matches cardiologists on coronary angiography complexity assessment while exposing auditable bounding-box evidence.
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.