Yesil Science / Blog
Blog
Every article we have published: research summaries, product thinking and developments in health AI.
Latest articles

AI tracks Parkinson’s using simple video
A new 3D tracking system turns standard patient videos into precise data that can estimate how long someone has lived with Parkinson's...

Fixing NHS Pathology Without More Mergers
Paperwork and structural reshuffles are draining NHS pathology budgets when simple digital integration could save £450 million annually.

AI reconstructs 3D beating hearts from ECGs
A new AI model reconstructs three-dimensional, moving structures of the human heart using nothing but a standard electrocardiogram.

Tracking Pathogens Under the World Cup
A massive wastewater surveillance project at the World Cup is testing whether pandemic-era tracking tools can actually stop outbreaks before they start.

Medical AI fails at real-world clinical reasoning
A new benchmark reveals that medical artificial intelligence aces multiple-choice tests but stumbles when faced with real patient cases.

Stopping Collapsed Lungs Before the Needle Leaves
A proactive seal for lung biopsies could finally eliminate one of the healthcare system's most expensive diagnostic complications.

AI Pinpoints Precise Biomarker Thresholds for Kidney Injury
A massive multi-center analysis reveals that standard lab ranges may hide the earliest signs of acute kidney injury.

AI scribes shift malpractice risk to doctors
As hospitals rush to adopt ambient AI scribes, clinicians are quietly signing off on a massive liability shift.

Hybrid AI ranks rare disease mutations accurately
A new ensemble AI cuts through genomic noise to find rare disease mutations, shifting the burden of diagnostics from human experts to...

AI Search Models Target the Clinical Workflow
Medical AI is moving past generic chatbots to deliver specialized search tools that clinicians actually trust.

MISP-Bench: Decomposing User-Provided False Priors into Answer, Rationale, and Guard Effects
A new benchmark reveals that prompting AI to double-check its reasoning often backfires, forcing the system to agree with a patient's self-diagnosis.

FDA bypasses authorization for generative AI devices
The federal government is letting medical artificial intelligence reach patients first and prove its safety later.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.