What AI has done in medicine

A randomised trial of more than 100,000 women found AI-supported mammography detected 29% more cancers with no rise in false positives, and the FDA now lists more than 1,600 AI-enabled medical devices.

  1. AI-supported mammography found 29% more cancers with no increase in false positives

    29% more cancers detected; 44% less screen-reading workload

    The MASAI trial randomised over 100,000 women in Sweden to AI-supported screening or standard double reading. The AI arm detected 29% more cancers without more false positives, and radiologists' screen-reading workload fell by 44%.

    Source: AI-supported mammography screening results in fewer aggressive and advanced breast cancers, finds full results from first randomized controlled trial (The Lancet), The Lancet, via EurekAlert, 2026-01-29. Checked 2026-09-06.

  2. The same trial found 12% fewer cancers surfacing between screenings

    1.55 vs 1.76 interval cancers per 1,000 women

    Interval cancers, the ones found between screening rounds, ran at 1.55 per 1,000 women in the AI group against 1.76 per 1,000 in the control group, a 12% reduction, with fewer of them having unfavourable characteristics.

    Source: Interval cancer, sensitivity, and specificity comparing AI-supported mammography screening with standard double reading (MASAI), The Lancet, 2026-01-29. Checked 2026-09-06.

  3. The first AI-discovered drug to report a randomised Phase 2a result improved lung function where placebo declined

    FVC +98.4 mL (60 mg daily) vs -20.3 mL (placebo) at 12 weeks

    Rentosertib, a TNIK inhibitor whose target and molecule were produced with Insilico Medicine's generative AI platform, was tested in 71 patients with idiopathic pulmonary fibrosis across 22 sites. At 12 weeks the 60 mg once-daily arm gained a mean 98.4 mL of forced vital capacity while placebo lost 20.3 mL. Published in Nature Medicine.

    Source: A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial (Nature Medicine), Nature Medicine, via EurekAlert, 2025-06-03. Checked 2026-09-06.

  4. More than 1,600 AI-enabled medical devices are on the FDA's authorised list

    1,600+ entries; most recent decision dated 2026-09-04

    The U.S. Food and Drug Administration keeps a public list of AI-enabled medical devices it has authorised for marketing. Counted on 2026-09-06, the list held over 1,600 entries, with decisions running from 1995 to 4 September 2026.

    Source: Artificial Intelligence-Enabled Medical Devices (FDA list), U.S. Food and Drug Administration, 2026-09-04. Checked 2026-09-06.

Frequently Asked Questions

A randomised trial of more than 100,000 women found AI-supported mammography detected 29% more cancers with no rise in false positives, and the FDA now lists more than 1,600 AI-enabled medical devices.

Each entry links to the primary source it was read from: the journal, agency, or organisation that published the result. The date the source was checked is printed on every entry, and the whole ledger can be downloaded as CSV or JSON from the data page.

Results only. The ledger records things that have already happened and been measured or certified: trial outcomes, regulatory lists, operational systems, published counts. Forecasts about what AI will do are not on this site.