Validation of the myocardial-ischaemic-injury-index machine learning algorithm to guide the diagnosis of myocardial infarction in a heterogenous population: a prespecified exploratory analysis

Dimitrios Doudesis, Kuan Ken Lee, Jason Yang, Ryan Wereski, Anoop Sv Shah, Thanasis Tsanas, Atul Anand, John W Pickering, Martin P Than, Nicholas L Mills, High-STEACS Investigators

Research output: Contribution to journalArticlepeer-review

Abstract

Background: We recently introduced the myocardial-ischemic-injury-index (MI3), a machine learning algorithm that predicts the likelihood of myocardial infarction in patients with suspected acute coronary syndrome. Whether this algorithm performs well in routine clinical practice or predicts subsequent events is unknown.
Methods: MI3 was validated in a prespecified exploratory analysis from a multi-centre randomised trial that included consecutive patients with suspected acute coronary syndrome undergoing serial high-sensitivity cardiac troponin I measurement. Patients with ST-segment elevation myocardial infarction were excluded. MI3 incorporates age, sex, and two troponin measurements to compute a value (0-100) reflecting an individual’s likelihood of myocardial infarction during the index visit and estimates diagnostic performance metrics at the computed score. Model performance for an index diagnosis of myocardial infarction, and for subsequent myocardial infarction or cardiovascular death at one year was determined using previously defined low- and high-probability MI3 thresholds (1·6 and 49·7, respectively).
Findings: In total, 20,761 patients (64±16 years, 46% women) were included of whom 3,272 (15·8%) had myocardial infarction. MI3 had an area under the receiver-operating-characteristic curve of 0·949 (95% confidence interval 0·946-0·952) identifying 12,983 (62·5%) patients as low-probability (sensitivity 99·3% [99·0-99·6%], negative predictive value 99·8% [99·8-99·9%]), and 2,961 (14·3%) as high-probability (specificity 95·0% [94·6-95·3%], positive predictive value 70·4% [68·7-72·0%]). At one year, subsequent myocardial infarction or cardiovascular death occurred more often in high-probability compared to low-probability patients (17·6% [520/2,961] versus 1·5% [197/12,983], P<0·001).
Interpretation: In consecutive patients undergoing serial cardiac troponin measurement for suspected acute coronary syndrome, the MI3 algorithm accurately estimates the likelihood of myocardial infarction and predicts subsequent adverse cardiovascular events.
Original languageEnglish
Pages (from-to)e300
Number of pages9
JournalThe Lancet Digital Health
Early online date20 Apr 2022
DOIs
Publication statusE-pub ahead of print - 20 Apr 2022

Keywords

  • Myocardial infarction
  • acute coronary syndrome
  • machine learning
  • troponin

Fingerprint

Dive into the research topics of 'Validation of the myocardial-ischaemic-injury-index machine learning algorithm to guide the diagnosis of myocardial infarction in a heterogenous population: a prespecified exploratory analysis'. Together they form a unique fingerprint.

Cite this