Background
Current Acute Coronary Syndromes (ACS) rule-out algorithms rely on a combination of clinical assessment and measuring troponin levels. It can take several hours for troponin levels to rise after a myocardial infarction, so initial testing may not show detectable levels. In order to rule out a false negative result, troponin levels are typically tested again several hours later to look for rising values, meaning patients are admitted for observation which has a large resource implication. We aimed to develop a machine learning model to improve early discharge of hospitalised patients at initial assessment. Methods
We trained and tuned a machine learning model (Rapid-RO) using patient data from two separate hospitals to rule-out ACS with simple routine demographic or clinical measurements. The model was then tested for its predictive accuracy in cohorts of patients at four different hospitals from separate time periods using their initial blood tests only. The model was then assessed against troponin threshold guided management as recommended by the European Society of Cardiology clinical guidelines. Patients were classified as having experienced an ACS based on the assigned ICD-10 primary diagnostic codes. Results
The Rapid-RO model was trained and tuned on 38,129 and 20,386 patients respectively. The model primarily used initial troponin levels, complemented by the 10 other most important input variables identified during permutation feature importance: age, C-reactive protein, urea, platelet count, eGFR, white cell count, haemoglobin, heart failure, diabetes, and hypertension. Of the 35,262 patients derived for testing the Rapid-RO model identified 12,037 (35.69%) very low risk patients on top of standard clinical assessment who could have been discharged early, compared with 8,967 (26.58%) identified by a troponin threshold approach alone (p < 0.001), with significantly fewer missed ACS cases (27 (0.22%) vs. 108 (1.20%), p < 0.001) and similarly low observed mortality rates (2 (0.02%) vs. 4 (0.04%) at 30 days). The Rapid-RO model demonstrated a consistently higher rule-out rate for ACS with a lower missed ACS rate across patient subsets, including patients with and without chest pain or Covid-19. Conclusion
The Rapid-RO machine learning model, which uses patient history and initial blood tests, offers a significant advancement in the risk stratification process, presenting a reliable tool for clinicians to rapidly rule out ACS and potentially reduce unnecessary hospital admissions. Its robust performance in diverse patient groups across different time periods, underscores its potential utility in a real-world clinical setting.