PT  - JOURNAL ARTICLE
AU  - Karabacak, Mert
AU  - Ozkara, Burak Berksu
AU  - Faizy, Tobias D.
AU  - Hardigan, Trevor
AU  - Heit, Jeremy J.
AU  - Lakhani, Dhairya A.
AU  - Margetis, Konstantinos
AU  - Mocco, J.
AU  - Nael, Kambiz
AU  - Wintermark, Max
AU  - Yedavalli, Vivek S.
TI  - Data-Driven Prognostication in Distal Medium Vessel Occlusions Using Explainable Machine Learning
AID  - 10.3174/ajnr.A8547
DP  - 2025 Apr 01
TA  - American Journal of Neuroradiology
PG  - 725--732
VI  - 46
IP  - 4
4099  - http://www.ajnr.org/content/46/4/725.short
4100  - http://www.ajnr.org/content/46/4/725.full
SO  - Am. J. Neuroradiol.2025 Apr 01; 46
AB  - BACKGROUND AND PURPOSE: Distal medium vessel occlusions (DMVOs) are estimated to cause acute ischemic stroke in 25%–40% of cases. Prognostic models can inform patient counseling and research by enabling outcome predictions. However, models designed specifically for DMVOs are lacking.MATERIALS AND METHODS: This retrospective study developed a machine learning model to predict 90-day unfavorable outcome (defined as an mRS score of 3–6) in 164 patients with primary DMVO. A model developed with the TabPFN algorithm used selected clinical, laboratory, imaging, and treatment data with the least absolute shrinkage and selection operator feature selection. Performance was evaluated via 5-repeat 5-fold cross-validation. Model discrimination and calibration were evaluated. SHapley Additive Explanations (SHAP) identified influential features. A Web application deployed the model for individualized predictions.RESULTS: The model achieved an area under the receiver operating characteristic curve of 0.815 (95% CI, 0.79–0.841) for predicting unfavorable outcome, demonstrating good discrimination, and a Brier score of 0.19 (95% CI, 0.177–0.202), demonstrating good calibration. SHAP analysis ranked admission NIHSS score, premorbid mRS, type of thrombectomy, modified TICI score, and history of malignancy as top predictors. The Web application enables individualized prognostication.CONCLUSIONS: Our machine learning model demonstrated good discrimination and calibration for predicting 90-day unfavorable outcomes in primary DMVO strokes. This study demonstrates the potential for personalized prognostic counseling and research to support precision medicine in stroke care and recovery.AISacute ischemic strokeAUPRCarea under the PRCAUROCarea under the ROC curveDMVOdistal medium vessel occlusionERemergency departmentIVTIV thrombolysiskNNk-nearest neighborLASSOleast absolute shrinkage and selection operatormTICImodified TICIPDPpartial dependence plotPRCprecision-recall curveROCreceiver operating characteristicSHAPSHapley Additive ExPlanationsSTstroke thrombectomy