Machine Learning to Predict the Likelihood of Acute Myocardial Infarction

Abstract

Background: Variations in cardiac troponin concentrations by age, sex, and time between samples in patients with suspected myocardial infarction are not currently accounted for in diagnostic approaches. We aimed to combine these variables through machine learning to improve the assessment of risk for individual patients.

Methods: A machine learning algorithm (myocardial-ischemic-injury-index [MI³]) incorporating age, sex, and paired high-sensitivity cardiac troponin I concentrations, was trained on 3013 patients and tested on 7998 patients with suspected myocardial infarction. MI³ uses gradient boosting to compute a value (0-100) reflecting an individual's likelihood of a diagnosis of type 1 myocardial infarction and estimates the sensitivity, negative predictive value, specificity and positive predictive value for that individual. Assessment was by calibration and area under the receiver operating characteristic curve. Secondary analysis evaluated example MI³ thresholds from the training set that identified patients as low risk (99% sensitivity) and high risk (75% positive predictive value), and performance at these thresholds was compared in the test set to the 99th percentile and European Society of Cardiology rule-out pathways.

Results: Myocardial infarction occurred in 404 (13.4%) patients in the training set and 849 (10.6%) patients in the test set. MI³ was well calibrated with a very high area under the receiver operating characteristic curve of 0.963 [0.956-0.971] in the test set and similar performance in early and late presenters. Example MI³ thresholds identifying low- and high-risk patients in the training set were 1.6 and 49.7, respectively. In the test set, MI³ values were <1.6 in 69.5% with a negative predictive value of 99.7% (99.5-99.8%) and sensitivity of 97.8% (96.7-98.7%), and were ≥49.7 in 10.6% with a positive predictive value of 71.8% (68.9-75.0%) and specificity of 96.7% (96.3-97.1%). Using these thresholds, MI³ performed better than the European Society of Cardiology 0/3-hour pathway (sensitivity, 82.5% [74.5-88.8%]; specificity, 92.2% [90.7-93.5%]) and the 99th percentile at any time point (sensitivity, 89.6% [87.4-91.6%]); specificity, 89.3% [88.6-90.0%]).

Conclusions: Using machine learning, MI³ provides an individualized and objective assessment of the likelihood of myocardial infarction, which can be used to identify low- and high-risk patients who may benefit from earlier clinical decisions.

Clinical trial registration: URL: https://www.anzctr.org.au. Unique identifier: ACTRN12616001441404.

Keywords: acute coronary syndrome; machine learning; myocardial infarction; troponin.

Figure 1.

Calibration and discrimination of the myocardial-ischemic-injury-index (MI³) algorithm. Calibration of the MI³ algorithm with the observed proportion of patients with type 1 myocardial infarction in the test data set (A). Each point represents 100 patients. The dashed lines represent perfect calibration. Receiver operating characteristic curve showing discrimination of the MI³ algorithm in the test data set (B). Some MI³ values shown for illustrative purposes only.

Figure 2.

Performance of the myocardial-ischemic-injury-index (MI³) algorithm compared with the European Society of Cardiology (ESC) 3-hour algorithm. Performance of MI³ at example thresholds (A) and the ESC 3-hour algorithm (B) for high-sensitivity cardiac troponin I (hs-cTnI) in 1652 patients with ≥2.5 hours between serial samples in the test set. URL indicates upper reference limit.

Figure 3.

Performance of the myocardial-ischemic-injury-index (MI³) algorithm compared with the European Society of Cardiology (ESC) 1-hour algorithm. Performance of MI³ at sample thresholds (A) and the ESC 1-hour algorithm (B) for high-sensitivity cardiac troponin I (hs-cTnI) in 336 patients with >0.5 hour but ≤1.5 hours between serial samples in the test set.

Figure 4.

Myocardial-ischemic-injury-index (MI³) clinical decision support tool to estimate the likelihood of myocardial infarction for individual patients. The figure shows a mockup of how the MI³ algorithm may be presented to physicians and patients. The top row illustrates a low-risk patient, the middle row illustrates an intermediate-risk patient, and the bottom row illustrates a high-risk patient, using the sample MI³ values of 0.9, 8.2, and 68.2, respectively. The screens on the left are for data input and return the MI³ value and estimated diagnostic metrics for an individual patient. A screen swipe presents the data in a natural frequency number and graphical format for the patient.