Live intelligence

Latest AI updates

7 updates
Research

Hx2Dx ARENA benchmarks LLMs on interactive clinical diagnosis

Researchers introduce Hx2Dx ARENA, an interactive benchmark of 1,000 clinical cases from the New England Journal of Medicine that simulates encounters from initial presentation through history taking, physical examination and diagnostic workup. Open- and closed-source LLMs are evaluated under multiple configurations. Every evaluated model loses diagnostic accuracy in the interactive setting compared with a static setting where the full case is presented upfront, and the ability to ask targeted questions accounts for much of the variation between models and the accuracy loss. The work highlights a gap between reasoning over available clinical data and hypothesis-driven information gathering.

LLMsclinical diagnosisbenchmarking
Research

Google tests cuffless hypertension detection using standard smartwatch sensors

Google Research developed an AI system that identifies signs of high blood pressure using pulse and motion data from a standard smartwatch. In a 196-person study, it achieved a 65.8% detection rate and reportedly outperformed traditional in-office measurement. The feature is available in the Google Health app but is not a substitute for a formal diagnosis.

Google Researchhypertension detectionwearable health monitoring
Research

InnerLogic-Surg: An Open Surgical Foundation Model via Continual Pretraining

Researchers present InnerLogic-Surg, an open family of surgical vision encoders (21M–300M parameters) obtained by continually pretraining a transformer on millions of surgical images from nearly 3,000 hours of video spanning over fifteen procedure types. The method inherits DINOv3's pretraining stage and adds a learned feature-upsampling module for efficient high-resolution dense prediction. Across 20 surgical tasks including workflow, instrument and anatomy recognition, segmentation, detection, and depth estimation, the largest model achieves the best linear-probe performance under the same architecture. The work demonstrates that surgical continual pretraining yields transferable representations that generalize across procedures and task types, offering a scalable alternative to procedure-specific approaches.

surgical computer visionfoundation modelsmedical AI
Research

MedGraph: Graph Memory for Long-Term Medical Dialogue

MedGraph is a graph-based memory system for LLM medical assistants that tracks patient state across visits. It addresses three common memory errors: outdated evidence, mixing other people's health facts, and missing safety facts. On MedMemoryBench, MedGraph outperforms five baselines by 10.5 and 10.4 points with GPT and Qwen backbones, respectively.

medical AImemory systemsdialogue systems
Research Editor selected

Trick-or-Treat: Adversarial Multimodal Medical Benchmark Exposes Hallucinations in Frontier Models

Researchers introduced Trick-or-Treat, an adversarial multimodal medical benchmark pairing real chest radiographs with synthetic clinical photographs to test cross-modal reasoning. In mismatched pairs, frontier models hallucinated clinically significant findings in 45-57.5% of cases, up from 25-37.5% when photographs were shown alone. The study demonstrates a concerning error pattern and validates synthetic images for adversarial evaluation.

Why it matters: This paper provides concrete evidence of hallucination in medical AI and introduces a novel evaluation method with synthetic images, offering immediate value for AI safety and medical reasoning research.

AI safetymedical AImultimodal reasoning
Research

Deep Learning Polyp Matching for Colon Capsule Endoscopy

This study introduces a contrastive learning-based Siamese neural network for matching polyps across colon capsule endoscopy images, trained on 5,103 same-polyp and 5,103 different-polyp pairs from the Danish CareForColon2015 trial. Using ResNet, DenseNet, and EfficientNet backbones with cosine distance, the model achieves up to 92% accuracy and AUC near 0.98. The approach aims to reduce polyp over-counting and unnecessary follow-up colonoscopies.

polyp matchingcontrastive learningcolon capsule endoscopy