Top Stories
All Sections
Finance
About
14 results for "diagnosis"
Microsoft's GPT-5-based medical AI achieved nearly double the diagnostic accuracy of emergency room physicians on structured cases — but 91% of patients say AI should require their explicit consent before diagnosing them.
Nine in ten patients require explicit consent before AI is used in their diagnosis, while 64% of providers are deploying AI for claims management — a trust gap with significant regulatory consequences.
Sen. Bill Cassidy introduced the PATIENT AI Act to expand AI in healthcare with patient safety guardrails, as a new survey shows 91% of patients want explicit consent required before AI is used in their diagnosis.
The REDMOD AI system identifies pancreatic cancer in CT scans an average of 475 days before conventional diagnosis, achieving nearly twice the sensitivity of experienced radiologists.
80% of U.S. hospitals now use AI, but fewer than 20% report sustained success in core clinical diagnosis — a Stanford-Harvard report quantifies the gap between pilot and production.
150 unionized physicians at Allina Health struck for four days demanding contractual control over how AI is deployed in diagnosis, care, and billing—the most visible AI governance labor dispute in U.S. healthcare.
Google DeepMind released a free public database of precomputed predictions for all 9 billion possible human DNA mutations — potentially compressing rare disease diagnosis from months to hours.
Tempus AI's $1.5 billion acquisition of Personalis combines AI-powered cancer diagnosis with molecular residual disease testing to create an integrated surveillance platform for post-treatment recurrence monitoring.
Mayo Clinic and Microsoft are jointly training a domain-specific frontier AI model on Mayo's clinical datasets — targeting multimodal reasoning across imaging, labs, and notes for earlier diagnosis and personalized treatment.
The American Medical Association published its first practical patient guide for AI chatbot use in healthcare, endorsing AI as a preparation tool while warning against using it for diagnosis or treatment decisions.
A new study finds patients consistently withhold symptoms from AI health chatbots, creating a diagnostic gap that undermines real-world accuracy even as AI outperforms doctors on benchmarks.
Boston teaching hospitals are drafting formal AI diagnostic protocols after studies showed AI matching or outperforming ER physicians, making Massachusetts a national bellwether for clinical AI governance.
Massachusetts doctors are caught between AI tools patients bring to appointments and AI systems hospitals are deploying — and neither side is clearly in control of how those tools shape diagnosis.
An OpenAI reasoning model outperformed two experienced ER physicians in a real-world test at Beth Israel Deaconess Medical Center — one of the first head-to-head comparisons conducted with live clinical data rather than curated research benchmarks.