The Diagnostic Efficacy of an App-based Diagnostic Health Care Application in the Emergency Room: eRadaR-Trial. A prospective, Double-blinded, Observational Study

Abstract

OBJECTIVE: To evaluate the diagnostic accuracy of the app-based diagnostic tool Ada and the impact on patient outcome in the emergency room (ER). BACKGROUND: Artificial intelligence-based diagnostic tools can improve targeted processes in health care delivery by integrating patient information with a medical knowledge base and a machine learning system, providing clinicians with differential diagnoses and recommendations. METHODS: Patients presenting to the ER with abdominal pain self-assessed their symptoms using the Ada-App under supervision and were subsequently assessed by the ER physician. Diagnostic accuracy was evaluated by comparing the App-diagnoses with the final discharge diagnoses. Timing of diagnosis and time to treatment were correlated with complications, overall survival, and length of hospital stay. RESULTS: In this prospective, double-blinded study, 450 patients were enrolled and followed up until day 90. Ada suggested the final discharge diagnosis in 52.0% (95% CI [0.47, 0.57]) of patients compared with the classic doctor-patient interaction, which was significantly superior with 80.9% (95% CI [0.77, 0.84], P <0.001). However, when diagnostic accuracy of both were assessed together, Ada significantly increased the accuracy rate (87.3%, P <0.001), when compared with the ER physician alone. Patients with an early time point of diagnosis and rapid treatment allocation exhibited significantly reduced complications ( P< 0.001) and length of hospital stay ( P< 0.001). CONCLUSION: Currently, the classic patient-physician interaction is superior to an AI-based diagnostic tool applied by patients. However, AI tools have the potential to additionally benefit the diagnostic efficacy of clinicians and improve quality of care.