Spectral CT Radiomics Model Promises Sharper Preoperative Pancreatic Tumor Classification
Chinese researchers achieve 90.5% validation accuracy distinguishing aggressive neuroendocrine carcinomas from indolent tumors using physics-informed AI that integrates into standard imaging workflows.
Why Your Fitbit Needs a Full Year to Predict Your Disease Risk: NIH Study Reveals the Power of Long-Term Wearable Monitoring
Analysis of 11 million participant-days shows year-long activity tracking detects 44% more disease associations than single-day measurements, transforming consumer devices into clinical prediction tools.
Private Equity Hospitals Match Nonprofits in AI Adoption While Independent For-Profits Fall Behind
New research reveals surprising parity in clinical AI implementation between PE-owned and nonprofit hospitals, but questions remain about whether technology investments prioritize patient outcomes or investor returns.
Hybrid AI Architecture Tackles Ultrasound's Biggest Image Quality Problem Without Inventing Fake Anatomy
South Korean researchers combine Vision Transformers with CNNs to eliminate speckle noise while avoiding the hallucinated features that make generative AI dangerous in clinical settings.
Why One AI Chip Giant Says Cancer Elimination Beats Doomsday Talk
Cerebras Systems CEO Andrew Feldman argues the AI industry should spotlight healthcare breakthroughs over existential threats as his company powers drug discovery for pharmaceutical giants.
MIT Spin-Off Brings 24-Billion Parameter AI to Consumer Laptops, Unlocking Privacy-First Healthcare Applications
Liquid AI's new LFM2.5-24B-A2B model activates just 2 billion parameters per token, enabling local deployment that could transform how healthcare organizations handle sensitive patient data.
The Oversight Gap: As AI Takes the Wheel in Clinical Trials, Regulators Struggle to Keep Up
From patient-built research assistants to AI-drafted protocols, artificial intelligence is reshaping drug development faster than validation frameworks can adapt.
Epilepsy Patients Train Their Own AI: Penn Medicine's Breakthrough in Self-Learning Seizure Detection
A first-of-its-kind platform enables patients to improve seizure detection algorithms through smartphone feedback, bypassing the need for expert intervention and transforming passive monitoring into active collaboration.
Combining X-Rays with Patient Records Boosts AI's Ability to Detect Severe Gum Disease
New multimodal deep learning system achieves 81% diagnostic accuracy by fusing dental imaging with clinical metadata, outperforming image-only approaches in detecting advanced periodontal bone loss.
AI Safety Stance Triggers Federal Blacklist: Anthropic's Pentagon Battle Tests Limits of Ethical Guardrails
The maker of Claude AI is asking a federal appeals court to reconsider a ruling that upheld the Pentagon's designation of the company as a supply chain risk after it refused to allow its models for mass surveillance and autonomous weapons.
Johns Hopkins Partners with AI Platform to Reimagine Medical Training for the Algorithm Age
The institution that shaped modern medical education a century ago is now collaborating with OpenEvidence to prepare physicians for AI-augmented clinical practice while preserving core diagnostic reasoning skills.
Digital Breakthrough Targets Schizophrenia's Most Stubborn Symptoms as FDA Clears First Smartphone-Based Treatment
Click Therapeutics' Motivista becomes the first FDA-cleared prescription digital therapeutic specifically designed to treat negative symptoms affecting 60% of schizophrenia patients.
AI Models Achieve 85% Accuracy Predicting Clinical Trial Outcomes Before First Patient Enrolled
IQVIA's new predictive platform, powered by NVIDIA technology, promises to help drugmakers identify protocol flaws and optimize trial design through virtual simulation.
Radiology AI Gets a Custom Fit: How Two Platforms Are Democratizing Foundation Models for Imaging Departments
CARPL.ai and HOPPR partnership enables healthcare providers to build institution-specific radiology AI applications using their own imaging data, bypassing traditional computational and data barriers.
Why Healthcare AI Predictions Mean Nothing Without Proof They Actually Helped Patients
A new framework argues that measuring AI accuracy misses the point—what matters is tracking whether recommendations translate into completed actions and better outcomes.
Anthropic Thwarts Massive Data Theft Operation in AI Model Distillation Campaign
New security defenses slash extraction attacks by up to 99% after detecting nearly 200 million attempts to steal Claude AI's capabilities in campaigns spanning May through July 2024.
Microsoft Unveils Maia 300 AI Chip for 2027 Deployments
Third-generation Azure Maia accelerator delivers 40% efficiency improvement and seven-fold throughput increase for AI inference workloads.
Specialty EHR Giant Ditches Proprietary AI for Dual-Vendor Marketplace in Front-Office Automation Bet
Nextech's strategic pivot to embedded third-party AI platforms signals a fundamental shift in how healthcare IT vendors approach conversational automation—and what specialty practices can expect from their EHR investments.
AI Pathology Firm Lunit Embeds Technology in Pharma Drug Trials Through Lab Services Deal
Korean medical AI company partners with Discovery Life Sciences to integrate its SCOPE platform into biomarker analysis workflows supporting over 350 active clinical trial programs.
Meta Releases Muse Wonder AI Models for Agentic Workflows Across Law, Finance, and Health
New models introduce cross-conversation memory and error recovery for multi-step professional tasks, though early benchmarks show mixed performance against Anthropic and OpenAI competitors.
What's the Deal With AI Data Centers?
A practical guide to the infrastructure behind AI, the local trade-offs it creates, and why U.S. communities are reaching sharply different conclusions.
Life Sciences Software Giant Bets Big on Embedded AI as Investor Caution Grows
Veeva Systems expands AI-powered clinical and regulatory tools across 175+ biotech clients, but analysts project margin compression and potential downside ahead.
Tracking Patient Drift: New AI Predicts ICU Deaths by Mapping Physiological Journeys, Not Just Vital Signs
A novel framework that visualizes critically ill patients as moving points in multidimensional space identified those who wandered from stable patterns faced up to 16 times higher mortality rates across nearly a quarter-million ICU stays.
Discarded Bile Fluid Detects Pancreatic and Bile Duct Cancers More Than a Year Before Standard Diagnosis
Ultra-low-pass genome sequencing of routinely discarded bile achieves 96% specificity at a fraction of conventional liquid biopsy costs, identifying cancer DNA up to 499 days earlier than traditional methods.
Microsoft CEO Calls for Emergency Brakes in AI Models, Urging Industry to Assume Compromise
Satya Nadella advocates for containment measures and human override capabilities in AI systems, calling for transparent audit trails and the ability to shut down models mid-task.
Inside the Private Slack Channel Where Tech Giants Shape Medicare's Digital Health Future
A federal investigation reveals how 1,700 industry representatives gained direct access to CMS officials promoting commercial health apps to Medicare beneficiaries, raising transparency concerns about regulatory capture.
AI Surveillance Tool Hunts Hidden Heart Disease in Hospital Records Before Symptoms Turn Deadly
Multicenter study validates machine learning algorithm that screens electronic health records to catch cardiac amyloidosis years earlier than traditional diagnosis.
OpenAI Democratizes Advanced AI: Free Users Gain Access to GPT-6 Luna's Interactive Healthcare Tools
The latest model delivers responses 44% faster and generates interactive medical visualizations automatically, but compliance questions remain for clinical deployment.
Hidden Jawbone Infections Meet Their Match: New AI Sees Through Dental Anatomy to Detect What Clinicians Miss
A multi-task deep learning system achieves near-perfect discrimination of apical periodontitis on routine X-rays by learning to navigate the anatomical clutter that confounds human observers.
California Bans Autonomous AI Medical Decisions in First-of-Its-Kind Healthcare Law
Assembly Bill 1979 prohibits healthcare facilities from allowing artificial intelligence to independently prescribe medications or order tests, requiring licensed clinicians to maintain independent judgment over algorithmic recommendations.
When Medical AI Goes Rogue: How 2026's Cyberattacks and Bioweapon Attempts Are Forcing Healthcare's Reckoning
A Nature commentary reveals documented incidents of AI-powered hospital attacks and biological weapons research that have transformed theoretical risks into an urgent industry crisis.
Machine Learning Finds Heart Disease Clues Hidden in Routine Pediatric ECG Reports
New AI model achieves 93.5% negative predictive value by analyzing structured ECG data from hospitalized children, offering a potential triage tool that works within existing hospital systems.
Dual-Vision AI Outperforms Traditional Staging by Reading MRI Scans and Tissue Slides Together to Forecast Cancer Treatment Success
A multimodal deep learning system achieved 80% accuracy predicting chemotherapy response in nasopharyngeal carcinoma by simultaneously analyzing imaging and pathology data before treatment begins.
How CT Scanners Are Training X-Ray AI to Diagnose Lung Disease in Data-Starved Clinics
A new knowledge distillation framework transfers CT expertise to chest X-ray models, boosting accuracy by 10 percentage points with as few as 500 training images.
Digital Therapy Breaks New Ground as First FDA-Authorized Treatment for Schizophrenia's Most Debilitating Symptoms
Click Therapeutics' smartphone-delivered intervention targets negative symptoms that have long eluded effective treatment, demonstrating 62% improvement over control in pivotal trial.
Why Healthcare AI Keeps Failing Patients: The Hidden Architecture Problem No One Is Talking About
A solution architect argues the real barrier to effective healthcare AI isn't data volume—it's the inability to distinguish current operational truth from historical transaction noise.
How AI Is Closing the Evidence Gap in Fast-Moving Digital Health Research
New framework using large language models automates systematic reviews with accuracy matching human experts, potentially transforming how digital health interventions reach clinical practice.
Microsoft's New AI Aims to Solve Healthcare's Model Selection Problem in Milliseconds
Tech giant unveils specialized decision-making model designed to route tasks between AI systems, potentially streamlining clinical workflow bottlenecks.
Ophthalmology Practices Turn to Specialized AI Agents to Tackle Scheduling Complexity General Chatbots Can't Handle
Assort Health and Nextech partner to automate the intricate patient access workflows unique to eye care, with early adopters reporting 60% call time savings and 97% resolution rates.
University of Texas System Scales AI Medical Scribes Across Eight Institutions After Pilot Shows 73% Clinician Adoption Surge
Following a successful trial, the UT System is deploying Abridge's ambient documentation platform enterprise-wide to support nearly 12 million annual patient visits.
AI-Assisted Prostate Imaging Could Spare Thousands of Men from Unnecessary Biopsies
International study finds DeepHealth's AI system reduces prostate biopsies by nearly one-fifth while maintaining 98.4% cancer detection accuracy across diverse clinical settings.
Medical AI's Guardrails Take Shape as Physicians Confront 90% Hallucination Rates in Complex Cases
The American College of Physicians establishes ethical framework for clinical AI as evidence reveals dramatic accuracy gaps between simple queries and medical literature reviews.
AI's 94% Failure Rate: Why Most Computer-Designed Cancer Proteins Never Make It Past the Cell Door
A landmark competition testing 12,000 AI-designed protein binders in living human T cells reveals a hidden translation crisis undermining computational drug discovery workflows.
Illumina's New AI Model Predicts Hidden Genetic Disease Culprits Without Expensive RNA Testing
SpliceAI2 identifies 17% more disease-causing variants than competing models by analyzing how DNA mutations affect gene splicing, potentially ending diagnostic odysseys for rare disease patients.
AI Model Uncovers Hidden Security Flaws in Epic's Patient Portal That Eluded Human Reviewers for Years
Epic Systems halted new product development for six weeks after Anthropic's Mythos AI discovered untraceable access vulnerabilities affecting over 320 million patient records.
AI Scribe Meets Medical Encyclopedia: Suki Embeds Evidence-Based Answers Directly Into Patient Encounters
New clinical decision support feature powered by UpToDate delivers patient-specific insights 83% of the time, merging ambient documentation with real-time medical reference.
Anthropic Launches Critical Infrastructure AI Security Program With Free Open-Source Vulnerability Scanner
Anthropic's new Cyber Mission deploys Claude AI models to security companies protecting power grids, water systems, and industrial facilities, alongside a free vulnerability scanner that has already identified thousands of flaws in open-source software.
South Korea Launches $13.5M AI Project to Predict and Prevent Elderly Mental Health Crises in Under One Second
A national consortium led by Samsung Seoul Hospital is developing a closed-loop brain monitoring system that measures, analyzes, and intervenes in geriatric mental health conditions in real time.
OpenAI's Self-Starting AI Agent Promises to Act Before You Ask—But Healthcare Faces Critical Compliance Questions
The GPT-6 Astra-powered Dots assistant autonomously manages tasks across 4,000+ applications, raising both efficiency hopes and compliance questions for health systems.
OpenAI Launches GPT-6 Astra Ultrafast with 8x Speed Boost on NVIDIA Blackwell GPUs
New model variant leverages inference optimizations and NVIDIA's programmable GPU platform to accelerate agent workflows and interactive applications.