George, Peter M.

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 [MI 3 ]) 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. MI 3 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 MI 3 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. MI 3 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 MI 3 thresholds identifying low- and high-risk patients in the training set were 1.6 and 49.7, respectively. In the test set, MI 3 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, MI 3 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, MI 3 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.

Background: Efforts to safely reduce length of stay for emergency department patients with symptoms suggestive of acute coronary syndrome (ACS) have had mixed success. Few system-wide efforts affecting multiple hospital emergency departments have ever been evaluated. We evaluated the effectiveness of a nationwide implementation of clinical pathways for potential ACS in disparate hospitals. Methods: This was a multicenter pragmatic stepped-wedge before-and-after trial in 7 New Zealand acute care hospitals with 31 332 patients investigated for suspected ACS with serial troponin measurements. The implementation was a clinical pathway for the assessment of patients with suspected ACS that included a clinical pathway document in paper or electronic format, structured risk stratification, specified time points for electrocardiographic and serial troponin testing within 3 hours of arrival, and directions for combining risk stratification and electrocardiographic and troponin testing in an accelerated diagnostic protocol. Implementation was monitored for >4 months and compared with usual care over the preceding 6 months. The main outcome measure was the odds of discharge within 6 hours of presentation Results: There were 11 529 participants in the preimplementation phase (range, 284–3465) and 19 803 in the postimplementation phase (range, 395–5039). Overall, the mean 6-hour discharge rate increased from 8.3% (range, 2.7%–37.7%) to 18.4% (6.8%–43.8%). The odds of being discharged within 6 hours increased after clinical pathway implementation. The odds ratio was 2.4 (95% confidence interval, 2.3–2.6). In patients without ACS, the median length of hospital stays decreased by 2.9 hours (95% confidence interval, 2.4–3.4). For patients discharged within 6 hours, there was no change in 30-day major adverse cardiac event rates (0.52% versus 0.44%; P =0.96). In these patients, no adverse event occurred when clinical pathways were correctly followed. Conclusions: Implementation of clinical pathways for suspected ACS reduced the length of stay and increased the proportions of patients safely discharged within 6 hours. Clinical Trial Registration: URL: https://www.anzctr.org.au/ (Australian and New Zealand Clinical Trials Registry). Unique identifier: ACTRN12617000381381.