
AI agents beat static databases in kidney care
Adding medical guidelines to an AI does not make it a better doctor, but teaching it to argue with itself does.
Discover the newest research about AI innovations in Research.

Adding medical guidelines to an AI does not make it a better doctor, but teaching it to argue with itself does.

A new commercial retinal implant challenges the boundary between biological sight and digital translation, forcing healthcare to rethink how we treat blindness.

A new human-AI framework shows that the best way to clean up messy electronic health records is to let algorithms and doctors correct each other.

NHS England is deploying ambient voice technology to 70,000 clinicians in its largest regional rollout yet, testing whether AI can finally solve the healthcare system’s administrative crisis.

A new composite AI model can spot structural heart disease from a standard ECG before symptoms even appear, but its real value lies in predicting future risk.

A new machine learning model proves that how your blood pressure fluctuates over 24 hours is far more dangerous than a single high reading at the clinic.

The rush to digitize GLP-1 prescribing is exposing a dangerous rift between venture-backed growth targets and basic clinical caution.

A new benchmark reveals that how we format electronic health records for large language models completely alters their clinical accuracy.

A massive consolidation in cancer diagnostics reveals the steep financial price of dominating the liquid biopsy market.

Deep learning models trained to spot Alzheimer’s disease are systematically blind to atypical forms of brain decay, raising doubts about their readiness for real-world clinics.