Development and Validation of a Machine Learning Model to Predict Oral Anticoagulant Use in Stroke From Prothrombin Time-International Normalized Ratio and Activated Partial Thromboplastin Time

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Neural network AUROC: 0.933 (VKA), 0.841 (DOAC)

• Primary Outcome: Diagnostic accuracy for anticoagulant classification

• Nnt Or Sensitivity: High discrimination with preserved calibration across clinically relevant probability thresholds

• Confidence Interval: VKA: 95% CI 0.908-0.955; DOAC: 95% CI 0.822-0.858

Clinical Application

Highly feasible - uses routine PT-INR and aPTT available in all hospitals with simple heat map interface Directly applicable to Australian EDs. Could integrate with existing stroke protocols and support PBS anticoagulant prescribing decisions. Aligns with National Stroke Foundation guidelines for rapid assessment Emergency department patients with acute stroke where medication history is unknown or unreliable

Abstract

BACKGROUND: Timely recognition of oral anticoagulant use is critical in acute stroke but is often hampered by impaired consciousness and unavailable medication history. We investigated whether routinely available coagulation tests, prothrombin time-international normalized ratio and activated partial thromboplastin time, paired with machine learning can identify anticoagulant exposure at presentation. METHODS: We performed a multicenter diagnostic modeling study using the Japan Stroke Data Bank. Adults with ischemic or hemorrhagic stroke admitted in 2016 to 2021 comprised the derivation cohort; those in 2022 formed a temporally distinct validation cohort. Three models (random forest, extreme gradient boosting, and neural network) used prothrombin time-international normalized ratio and activated partial thromboplastin time as predictors to classify anticoagulant status: vitamin K antagonist, direct oral anticoagulant, or none. Discrimination (area under the receiver operating characteristic curve and area under the precision-recall curve), calibration, and decision curve analysis were assessed. Model outputs were implemented as bedside probability heat maps. RESULTS: Among 30 767 patients (derivation n=24 857; validation n=5910), vitamin K antagonist/direct oral anticoagulant use was 4.5%/8.2% in derivation and 2.8%/9.5% in validation. In the validation cohort, the neural network yielded the best performance: area under the receiver operating characteristic curve, 0.933 (95% CI, 0.908-0.955) and area under the precision-recall curve, 0.52 (95% CI, 0.44-0.61) for vitamin K antagonist; area under the receiver operating characteristic curve, 0.841 (95% CI, 0.822-0.858) and area under the precision-recall curve, 0.39 (95% CI, 0.35-0.43) for direct oral anticoagulant, with preserved calibration and highest net benefit across clinically relevant thresholds. Heat maps summarized class probabilities over the prothrombin time-international normalized ratio×activated partial thromboplastin time space to support rapid inference. CONCLUSIONS: A simple machine learning model using only prothrombin time-international normalized ratio and activated partial thromboplastin time classified vitamin K antagonist and direct oral anticoagulant exposure with high accuracy and practical clinical utility. This tool assists emergency decision-making when medication history is unknown, supporting the safety and timeliness of acute stroke care.

References

1. 1.Fujiwara, G., Nagakane, Y., Murakami, N., Suehiro, E., Hashimoto, N., Yoshimura, S., Toyoda, K., & Okada, Y. (2026). Development and validation of a machine learning model to predict oral anticoagulant use in stroke from prothrombin time-international normalized ratio and activated partial thromboplastin time. Journal of the American Heart Association, 15(7), e047432. https://doi.org/10.1161/JAHA.125.047432