Deep learning improves physician accuracy in the comprehensive detection of abnormalities on chest X-rays.

Autor: Anderson PG; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA. pami.anderson@imagen.ai., Tarder-Stoll H; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA., Alpaslan M; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA., Keathley N; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA., Levin DL; Department of Radiology, Stanford University School of Medicine, 453 Quarry Rd, Palo Alto, CA, 94305, USA., Venkatesh S; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA., Bartel E; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA., Sicular S; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA.; The Mount Sinai Hospital, 1 Gustave L. Levy Place, New York, NY, 10029, USA., Howell S; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA., Lindsey RV; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA., Jones RM; Imagen Technologies, 224 W 35th St Ste 500, New York, NY, 10001, USA.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2024 Oct 24; Vol. 14 (1), pp. 25151. Date of Electronic Publication: 2024 Oct 24.
DOI: 10.1038/s41598-024-76608-2
Abstrakt: Chest X-rays are the most commonly performed medical imaging exam, yet they are often misinterpreted by physicians. Here, we present an FDA-cleared, artificial intelligence (AI) system which uses a deep learning algorithm to assist physicians in the comprehensive detection and localization of abnormalities on chest X-rays. We trained and tested the AI system on a large dataset, assessed generalizability on publicly available data, and evaluated radiologist and non-radiologist physician accuracy when unaided and aided by the AI system. The AI system accurately detected chest X-ray abnormalities (AUC: 0.976, 95% bootstrap CI: 0.975, 0.976) and generalized to a publicly available dataset (AUC: 0.975, 95% bootstrap CI: 0.971, 0.978). Physicians showed significant improvements in detecting abnormalities on chest X-rays when aided by the AI system compared to when unaided (difference in AUC: 0.101, p < 0.001). Non-radiologist physicians detected abnormalities on chest X-ray exams as accurately as radiologists when aided by the AI system and were faster at evaluating chest X-rays when aided compared to unaided. Together, these results show that the AI system is accurate and reduces physician errors in chest X-ray evaluation, which highlights the potential of AI systems to improve access to fast, high-quality radiograph interpretation.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje