SPICED-ACS: Study of the potential impact of a computer-generated ECG diagnostic algorithmic certainty index in STEMI diagnosis: Towards transparent AI

Abstract

BackgroundComputerised electrocardiogram (ECG) interpretation diagnostic algorithms have been developed to guide clinical decisions like with ST segment elevation myocardial infarction (STEMI) where time in decision making is critical. These computer-generated diagnoses have been proven to strongly influence the final ECG diagnosis by the clinician; often called automation bias. However, the computerised diagnosis may be inaccurate and could result in a wrong or delayed treatment harm to the patient. We hypothesise that an algorithmic certainty index alongside a computer-generated diagnosis might mitigate automation bias.The impact of reporting a certainty index on the final diagnosis is not known. PurposeTo ascertain whether knowledge of the computer-generated ECG algorithmic certainty index influences operator diagnostic accuracy. MethodologyClinicians who regularly analyse ECGs such as cardiology or acute care doctors, cardiac nurses and ambulance staff were invited to complete an online anonymous survey between March and April 2019. The survey had 36 ECGs with a clinical vignette of a typical chest pain and which were either a STEMI, normal, or borderline (but do not fit the STEMI criteria) along with an artificially created certainty index that was either high, medium, low

Demographics and Characteristics of Patients Admitted With Acute Coronary Syndrome to the Coronary Care Unit at King Abdulaziz University

“…In ACS, an increase in these cardiac enzymes provides further diagnostic relevance [62]. Previous studies have suggested that ECGs proved invaluable in the CCU setting [63], as was the case in the CCU of KAUH.…”

Accuracy of Physicians’ Electrocardiogram Interpretations

“…In this systematic review and meta-analysis, of the 1138 articles initially identified, 78 studies (enrolling a total of 10 056 participants) reported accuracy data (Figure 1). For 2 studies, data were reported in several different publications; in each case, we abstracted 1 report (the most complete). The eTable in the Supplement summarizes the key features of study designs and tests.…”

“…Forty-one studies involved medical students (n = 4256 participants), 42 studies involved postgraduate physicians (n = 2379), 11 studies involved noncardiologist practicing physicians (n = 1074), and 10 studies involved cardiologists or cardiology fellows (n = 2094); 4 mixed-participant studies did not report training level–specific sample sizes (n = 253). Twenty-six studies were randomized trials, 11 studies were 2-group nonrandomized comparisons, 19 studies were single-group pre-post comparisons, and 22 studies were cross-sectional (single time point). Twenty-two studies were identified as surveys .…”

“…Twenty-two studies were identified as surveys . Of the 47 studies reporting posttraining data, the training interventions included face-to-face lectures or seminars (22 studies), computer tutorials (20 studies), independent study materials (7 studies), clinical training activities (4 studies), and 7 other miscellaneous activities (some studies used >1 intervention type). On further quality appraisal, all studies reported an objective outcome of learning (ie, accuracy), 54 studies had high (≥75%) follow-up, 16 studies involved more than 1 institution, and 66 studies…”

ECG Monitoring Systems: Review, Architecture, Processes, and Key Challenges

“…In general, most of the systems use wireless and wearable devices for data acquisition and were designed for diagnosis purposes [166][167][168]. Other ECG monitoring systems mainly focus on the interpretation of diagnostic algorithms [88,166,169,170]. Arrhythmia diagnosis is one of the most common diseases diagnosed based on ECG signals [171][172][173][174].…”