AI spots esophageal cancer in routine noncontrast CT scans: 80,612-patient study hits 98.5% specificity
pattyneta · x · 2026-10-01
A Nature Medicine study shows an AI model can detect esophageal cancer and precancerous lesions from ordinary noncontrast chest CT scans — previously considered impossible.
- Covered 80,612 patients across 12 centers
- External cohorts: 98.5% specificity and 90.0% sensitivity for cancer
- 52.5% sensitivity for precancerous lesions
Open access paper suggests routine CT scans could be repurposed for large-scale, near-zero-cost esophageal cancer screening.
More from Research
- FutureSim Q3: LLMs now genuinely improve from experience, Opus 5.5 tops at 50% — rickasaurus · 2026-11-16
- Dataset Distillation via Drifting Compresses ImageNet Classes to Just 10 Images — giannis_daras · 2026-11-16
- Why divide by n-1: a 2-minute explainer on Bessel's correction — JFPuget · 2026-11-16
- In business, Type 2 errors often cost more than Type 1 errors — mdancho84 · 2026-11-16
- In risk management, missing a real risk can sink the business — mdancho84 · 2026-11-16
- Thread defines Type 2 error: false negative means missing a real effect — mdancho84 · 2026-11-16