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

Nearly One Million Clinicians Rely on Querying AI
Over 700,000 clinicians actively query medical AI engines for treatment decisions each month, rapidly outstripping formal clinical validation.

AI tool automates rare disease phenotyping from text
A new end-to-end framework extracts and ranks rare disease terms directly from clinical text to streamline undiagnosed case reviews.

NLP Finds Three Times More Screening Candidates
Relying solely on structured electronic health records leaves millions of eligible lung cancer patients without life-saving screenings.

950,000 Clinicians Rely on AI for Treatment Decisions
Doctors are turning to artificial intelligence for complex treatment decisions rather than basic diagnostic tasks.

AI Voice Scribes Enter NHS Wards at Scale
A Leicester hospital trust is deploying AI voice scribes to thousands of clinicians following an eight-minute consultation time saving in pilot testing.

Doctors Stop Using ED AI As Shifts Progress
A prospective trial shows that high accuracy cannot save emergency department AI if exhausted doctors stop clicking on it.

NHS Expands Radiology Software to Cut Backlogs
Nine NHS trusts are deploying workflow software to accelerate diagnostic scan reporting as radiology shortages intensify.

AI safety net catches missed liver tumors
Deploying AI as a routine backstop in radiology departments caught dozens of overlooked liver lesions and forced immediate changes in patient care.

NHS Integrates Drug Robotics into Patient Records
Nurses no longer need to switch between separate software platforms to dispense critical medications.

AI Model Outperforms Traditional Heart Amyloidosis Staging
A machine learning model predicts death and heart failure hospitalizations in cardiac amyloidosis better than standard clinical staging tools.

Merging Mental Health Records Across NHS Trusts
Connecting community care and mental health records in Birmingham removes critical blind spots for 80,000 service users.

AI model adapts adult X-rays for neonates
A decentralized training strategy lets hospitals repurpose adult radiology AI for vulnerable newborns without sharing patient data.
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.