Patient Stratification for Improving Acute Chest Pain Management and Mitigating Emergency Department Crowding: Machine Learning Model Development and Validation.
Artificial neural networks model detected acute coronary syndrome with high sensitivity at emergency triage
Patient Stratification for Improving Acute Chest Pain Management and Mitigating Emergency Department Crowding: Machine Learning Model Development and Validation.
Acute chest pain (acute chest pain) is one of the most common chief complaints in the emergency department (emergency department), accounting for approximately 8% of all emergency department visits.
These models aim to accurately detect acute coronary syndrome and reliably identify low-risk patients based on a single high-sensitivity cardiac troponin T test result.
We conducted a retrospective study using single-center data from a tertiary teaching hospital between January 2016 and December 2022.
Rendering prediction based on 24 feature variables (2 demographics, 6 vital signs, 4 blood test results, and 12 medical history), all artificial neural networks models demonstrated strong testing AUROC (95% CI) performance of 0.942 (0.920-0.965) for GA classification, 0.824 (0.808-0.841) for GB1, and 0.893 (0.884-0.902) for GB2.
A sensitivity-prioritized variant, artificial neural networks-S3-L, increased acute coronary syndrome sensitivity to 0.966 (95% CI 0.94-0.991) and negative predictive value to 0.998 (95% CI 0.996-0.999), but at the cost of lower specificity and reduced low-risk sensitivity, indicating a safety-efficiency trade-off.
These findings suggest that artificial neural networks-based classifiers can effectively support clinical risk stratification and disposition decision-making in acute chest pain care for patients presenting ≥3 hours after symptom onset.
However, because even the sensitivity-prioritized artificial neural networks-S3-L variant falls short of the stringent sensitivity threshold (>0.99) typically required for a standalone emergency department rule-out tool, this system should be interpreted as a clinical decision-support aid rather than an independent rule-out strategy.