Abstract 4362263: Factors Associated with Physician Modifications to Automated ECG Interpretations

Abstract

Introduction: Accurate automated diagnoses contribute to the improvement of clinical workflows and the enhancement of patient care. Commercially available automated electrocardiogram (ECG) interpretation systems often requires physician manual modification despite its widespread use. This study investigates the frequency and characteristics of the modifications from automated ECG report in routine clinical practice. Methods and Results: We retrospectively analyzed 769,093 ECGs from 2011 to 2023 and compared automated ECG reports generated by the Marquette 12SL ECG analysis program with physician-finalized reports. A modification was defined as any textual difference between the initial and final reports. Our analysis revealed that 25.5% of all ECG reports underwent some forms of modification by physicians. We analyzed the frequency of 90 pre-defined ECG-related terms before and after physician review, categorizing modifications as unchanged, deleted, or newly added. Modifications were more frequent for ECGs performed during off-hours, in patients with higher ventricular rates and longer QRS durations. At the term level, critical diagnoses such as "prolonged QT interval" (newly-added from 10.6% of original reports) and "atrial fibrillation" (newly-added from 4.0% of original reports) were frequently added by physicians, while general terms like "normal EKG" and "abnormal ECG" were frequently deleted from automated ECG reports (79.6% and 44.9% automated reports with these terms required the removal). Modification rates varied by ECG term category, physician experience, and ECG acquisition year. Conclusion: This large-scale real-world study demonstrated the high frequency of physicians’ modification in automated ECG interpretation. The identified patterns of modifications, including the addition of specific diagnoses and the removal of non-specific terms, highlight the limitations of current rule-based systems in handling complex cases and nuanced ECG findings.