A survey of how AI is already used in medicine — mostly cancer, neurology and cardiology — and what still blocks its use in real clinics.
Deep learning can turn messy biomedical data into better health predictions, but its "black box" nature must be fixed before clinicians will trust it.
A review argues AI can outperform clinicians in tasks like diagnosis and dosing, but ethical, legal and expertise gaps still block safe adoption.
Hospitals can train shared medical AI without sharing patient data — federated learning moves the model to the data, not the data to the model.
A review arguing machine learning can ease overburdened health systems by speeding diagnosis, personalising treatment, cutting costs and spotting outbreaks early.
Chasing models that work everywhere can block machine learning that would actually help patients in a specific hospital — usefulness at the bedside should come first.
Simple, fast classical machine-learning models can power real-time digital twins of breast cancer for monitoring, diagnosis and prediction inside the metaverse.
Hospitals can share trained AI models instead of patient data, letting them build digital twins for clinical decisions without exposing anyone's records.
A review of a decade of studies finds only six rigorous papers on machine learning for healthcare system management, mostly covering records, chatbots and disease prediction.
Hundreds of AI models exist to spot alcohol, opioid, and cannabis use disorders, but almost none have made it into routine clinical care.
A new Europe-wide research network aims to make genetic testing routine for prescribing heart drugs, using AI, shared guidelines and policy reform.
Smart-home health monitoring works but is concentrated in wealthy European and Asian regions, with most systems still far from truly intelligent, adaptive care.
Wearables plus AI can flag disease early, but reported 85%+ accuracies come from small, controlled studies that rarely prove real-world clinical value.
Patients in a tirzepatide weight-loss app who actively engaged — via coaching, chatbot, or self-tracking — lost about 4.6% more body weight at 6 months than disengaged users.
AI for diagnosing Alzheimer's has moved from hand-engineered machine learning to deep learning and now large language models that read speech and clinical notes.
AI and remote monitoring can cut orthodontic appointments and sharpen diagnosis, but almost all 23 studies reviewed came from urban clinics, not underserved areas.
A simple rules-based triage chatbot beat AI-powered versions on accuracy (71.8% vs 30.8-41.0%), yet testers preferred the smoother-talking but less accurate AI ones.
AI can automatically measure coronary calcium on ordinary chest CT scans, and those scores reliably predict heart attacks and death.
AI can help spot risky pregnancies and newborn illness earlier in poor countries, but only alongside real investment in data, infrastructure and regulation.
Clinicians can now build medical and dental imaging AI without coding, and 138 studies show it works reasonably well — but external validation is often missing.
AI can spot neglected tropical diseases in images, but black-box models block clinical trust — this review proposes a framework making such systems explainable for low-resource clinics.