healthcare

A tweet highlights work at EveryCure, referencing a New York Times story where an AI model searched existing drugs and identified a combination that put a patient with a rare blood disease into remission.

Almanac Health is launching an AI agent platform that helps doctors delegate administrative and research tasks, thereby increasing time for patient care.

The article explores a positive future where AI cures major diseases, citing recent AI achievements in math and medicine as promising signs.

The article discusses how AI could dramatically accelerate biomedical research, creating a bottleneck where current clinical trial and regulatory processes may delay patient access to new treatments, calling for urgent adaptation to the pace of AI-driven discoveries.

The article argues that in enterprise AI, the AI model is often the easiest part, with greater challenges in data trust, governance, and workflow integration, especially in regulated industries like healthcare.

LangSmith is helping healthcare organizations transform expert reviews into reusable evaluations for AI agents, improving patient care workflows.

Personal Medical Analyst is an AI agent that helps users interpret symptoms, lab results, and medications, providing personalized guidance and source-backed reasoning based on their health history.

This paper introduces OpTFM, a comparative evaluation framework for tabular foundation models in healthcare, assessing models across six clinically meaningful dimensions like generalization and fairness, and applies it to two use cases to demonstrate context-dependent rankings.

The study systematically assesses algorithmic fairness in machine learning models for predicting treatment retention in medication for opioid use disorder, finding performance gaps across patient subgroups and evaluating bias mitigation techniques with trade-offs.

The article reflects on the suffering caused by inadequate healthcare and medical progress, calling for technological advancements to free humanity from fear and inequality.

A project analyzing NHANES survey data to classify coronary heart disease risk, emphasizing data leakage audit and calibration checks while comparing machine learning models.

A discussion questioning the timeline for achieving physical AGI, contrasting it with digital AGI expectations, and mentioning Elon Musk's Optimus robot in the context of future healthcare affordability.

This paper proposes a new unified pre-training framework for medical code sequences that captures hierarchical structures and complex interactions, demonstrating superior performance in clinical event prediction and drug repositioning case studies for Alzheimer's disease.

Included Health built Dot, an AI-powered federated multi-agent healthcare guide, using LangGraph and Deep Agents, resulting in a 75% increase in chat engagement and over 99% high-risk detection.

The article argues that despite progress, AI is not currently a primary driver in drug development, highlighting its limitations and the current state of the field.

The paper proposes Adaptive Bayesian Partner Selection (ABPS), a peer-to-peer federated learning framework that adaptively selects collaboration partners using Bayesian methods to reduce communication costs while maintaining accuracy in heterogeneous healthcare settings.

本文分享了个人接受飞秒激光手术的体验，手术费用约16,000元，恢复迅速且效果良好，推荐进行此类视力矫正手术。

This paper evaluates neural, workflow, and agentic systems for ICD-10-CM coding, identifies failure modes on rare and complex codes, and shows that tool-augmented agentic configurations can recover performance on specific subsets.

LangChain's guide explores how organizations like Madrigal Pharma, Abridge, and Vizient are scaling AI agents in healthcare and life sciences to accelerate research and reduce documentation burden, focusing on infrastructure for reliability and compliance.

The paper introduces MedSNIP, a snippet-level approach for medical fact verification, and MedSNIP-Bench, a human-annotated benchmark, demonstrating improvements in preserving clinical structure and reducing verifier calls.