Validation of Self-Assessment-Based Chest Pain Algorithm (DETAK) as An Early Identification Tool for Acute Coronary Syndrome

Background: The most common reason for prehospital delay in acute coronary syndrome (ACS) patients is a lack of symptoms awareness. Patient-oriented machine learning algorithms may help the patient recognize ACS symptoms, reducing the prehospital delay that determines the clinical outcome of ACS patients. Objective: Assessing the accuracy of the self-assessment chest pain algorithm (DETAK) in identifying ACS Methods: This study was conducted from August 2021 to June 2022 and included seven hospitals: five PCI-capable hospitals and two non-PCI-capable hospitals. All patients with chest pain who visited the hospital and used the DETAK algorithm were included. Patients with unstable angina, as well as those who died or declined to participate in this study, were excluded. The area under the curve receiver operating characteristic (AUROC) was used to verify DETAK's performance in identifying ACS. We compare the DETAK algorithm's diagnosis with the definitive diagnosis based on ECG and/or troponin results. Result: A total of 539 patients (mean age 58 years) participated, with a higher proportion of male patients (n = 424). An AUC value of 0.854 was obtained. The cut-point accuracy of DETAK in identifying ACS for the entire sample had a sensitivity of 89.5% and a specificity of 81.2%. The algorithm's specificity decreased in certain subgroups, including type 2 diabetes, women, and hypertensive patients. The algorithm reliability test obtained moderate to strong levels of agreement. Conclusion: As a leap in the digital era, DETAK's self-assessment-based chest pain algorithm offers excellent diagnostic performance to identify ACS symptoms and reduce prehospital delays for patients.