Koshy AN et al: Accuracy of blinded clinician interpretation of single-lead smartphone electrocardiograms and a proposed clinical workflow. Am Heart J 205 (2018) 149-153
A paucity of data exists on the accuracy of primary care physicians’ (PCP) interpretation of KardiaMobile ECGs compared with the device’s automated diagnosis. Using 408 ECGs in 51 patients, before and after elective cardioversion, this study demonstrated variable accuracy in clinician interpretation, with a mean accuracy of 91% for the review by cardiologists, and 85% accuracy for the review by PCPs. With exclusion of Unclassified ECGs, the algorithm accuracy had a sensitivity and specificity of 100% and 95%, respectively. Accurate diagnosis of a KardiaMobile Unclassified ECG was established in 10⁄12 when assessed by a cardiologist, and 9⁄12 on review by a primary care physician. Combining the automated algorithm with cardiologist interpretation of only Unclassified traces yielded excellent results and provides an efficient, cost-effective workflow for the utilization of a smartphone-based ECG in clinical practice.