How is AI helping doctors and patients today?
Short answer: AI is helping doctors read medical images, cut paperwork and monitor patients. The FDA says it has authorized over 1,600 AI-enabled medical devices as of September 2026, and recent studies show AI helping clinicians outline tumours more accurately and about 24 percent faster, spot treatable weaknesses in cancer, keep fetal MRI scans sharp and track ICU patients' recovery.
AI in medicine breakthroughs we have covered
- AI spots a treatable weakness in ovarian cancer from ordinary tissue images. King's College London's HRDPath model reads microscope images of tumour tissue to find faulty DNA repair, a flaw some drugs can exploit, without a genomic test. (King's College London)
- Claude designs protein binders against scorpion toxins, a first step toward new antivenoms. Working mostly on its own for 64 hours, an internal Claude research model designed protein binders against four dangerous scorpion neurotoxins. Lab tests confirmed 17 of 211 designs. (Anthropic)
- MIT AI keeps fetal brain MRI scans sharp even when the baby moves. E(3)-Pose tracks a moving fetus's head during MRI so scans stay complete, which could mean earlier diagnoses and fewer repeat hospital visits. (MIT News)
- AI summaries lighten the load for cancer clinicians before first visits. At the Netherlands Cancer Institute, an AI tool that turns messy records into structured summaries cut clinicians' perceived workload in a real world study. (npj Digital Medicine)
- Stanford AI helps clinicians follow ICU patients' activity across a whole hospital stay. TRACER combines bedside video with health records so doctors and nurses can see how a patient's movement and behavior change over an ICU stay. (Stanford AI Lab Blog)
- AI helps new radiation oncologists outline prostates more accurately and faster. In a randomized trial presented at ASTRO 2026, trainees using AI generated contours matched expert outlines more closely and finished about 24 percent faster. (ASCO AI in Oncology)
- Patients help train their own seizure detectors by chatting with an AI app. In a Penn Medicine study of 13 people with epilepsy, a phone app let patients ask about their brain activity and flag false alarms so the system could learn. (Penn Medicine)
See also: the biggest positive AI breakthroughs of 2026.
Frequently asked questions
How many AI medical devices has the FDA authorized?
The U.S. Food and Drug Administration says it has authorized over 1,600 AI-enabled medical devices for marketing in the United States as of September 2026. Its examples include systems that detect diabetic retinopathy from retinal images, software that uses deep learning to sharpen images, and algorithms that automate insulin dosing from continuous glucose monitor readings.
Does AI help doctors work faster?
In a randomized trial presented at ASTRO 2026, radiation oncology trainees using AI generated contours matched expert outlines more closely and finished about 24 percent faster. At the Netherlands Cancer Institute, an AI tool that turns messy records into structured summaries cut clinicians’ perceived workload before first visits.
How is AI helping with cancer?
King's College London's HRDPath model reads microscope images of tumour tissue to find faulty DNA repair in ovarian cancer, a flaw some drugs can exploit, without a genomic test. AI contouring is also helping clinicians plan prostate radiation treatment more accurately.
Can patients use AI in their own care?
In a Penn Medicine study of 13 people with epilepsy, a phone app let patients ask about their brain activity and flag false alarms so their seizure detector could learn from them.
Is AI replacing doctors?
In the studies Bloomer has covered, AI supports clinicians rather than replacing them: it drafts contours that doctors check, summarizes records before visits, and helps nurses and doctors follow ICU patients over a hospital stay.
Sources
- U.S. FDA: Artificial Intelligence-Enabled Medical Devices
- U.S. FDA: List of AI-Enabled Medical Devices
- King's College London: AI spots a treatable weakness in ovarian cancer from ordinary tissue images
- Anthropic: Claude designs protein binders against scorpion toxins, a first step toward new antivenoms
- MIT News: MIT AI keeps fetal brain MRI scans sharp even when the baby moves
- npj Digital Medicine: AI summaries lighten the load for cancer clinicians before first visits
- Stanford AI Lab Blog: Stanford AI helps clinicians follow ICU patients' activity across a whole hospital stay
- ASCO AI in Oncology: AI helps new radiation oncologists outline prostates more accurately and faster
- Penn Medicine: Patients help train their own seizure detectors by chatting with an AI app