Impact of Deep Learning-Based Computer-Aided Detection and Electronic Notification System for Pneumothorax on Time to Treatment: Clinical Implementation.

Abstract

Objective: To assess whether the implementation of deep learning (DL) computer-aided detection (CAD) that screens for suspected pneumothorax (PTX) on chest radiography (CXR) combined with an electronic notification system (ENS) that simultaneously alerts both the radiologist and the referring clinician would affect time to treatment (TTT) in a real-world clinical practice.

Methods: In May 2022, a commercial DL-based CAD and ENS was introduced for all CXRs at an 818-bed general hospital, with 33 attending doctors and their residents using ENS, while 155 others used only CAD. We used difference-in-differences estimates to compare TTT between the CAD and ENS group and the CAD-only group for the period from January 2018 to April 2022 and from May 2022 to April 2023.

Results: A total of 603,028 CXRs from 140,841 unique patients were included, with a PTX prevalence of 2.0%. There was a significant reduction in TTT for supplemental oxygen therapy for the CAD and ENS group compared with the CAD-only group in the postimplementation period (-143.8 min; 95% confidence interval [CI], -277.8 to -9.9; P = .035). However, there was no significant difference in TTT for other treatments, including aspiration or tube thoracostomy (14.4 min; 95% CI, -35.0 to 63.9) and consultation with the thoracic and cardiovascular surgery department (86.3 min; 95% CI, -175.1 to 347.6).

Conclusion: The introduction of a DL-based CAD and ENS reduced the time to initiate oxygen supplementation for patients with PTX.