A new machine learning algorithm with high interpretability for improving the safety and efficiency of thrombolysis for stroke patients: A hospital-based pilot study

Enhancing ischemic stroke management: leveraging machine learning models for predicting patient recovery after Alteplase treatment

AIM

Ischemic stroke remains a leading global cause of morbidity and mortality, emphasizing the need for timely treatment strategies. This study aimed to develop a machine learning model to predict clinical outcomes in ischemic stroke patients undergoing Alteplase therapy.

METHODS

Data from 457 ischemic stroke patients were analyzed, including 50 demographic, clinical, laboratory, and imaging variables. Five machine learning algorithms - k-nearest neighbors (KNN), support vector machines (SVM), Naïve Bayes (NB), decision trees (DT), and random forest (RF) - were applied for constructing models. Additional feature importance analysis were p to identify high-impact predictors.

RESULTS

The Random Forest model showed the highest predictive reliability, outperforming other algorithms in sensitivity (0.97 ± 0.02) and F-measure (0.96 ± 0.02). feature importance analysis identified NIH1C (LOC commands (eye and hand movements)), NIH1B (LOC questions (birthday and age recall)), and NIH_noValue (the absence of any stroke characteristics) as the most influential predictors. Using only the top-ranked features identified from the feature importance analysis, the model maintained comparable performance, suggesting a streamlined yet effective predictive approach.

CONCLUSION

Our findings highlight the potential of machine learning in optimizing ischemic stroke treatment outcomes. Random Forest, in particular, proved effective as a decision-support tool, offering clinicians valuable insights for more tailored treatment approaches.

Uncertainty-aware deep learning for trustworthy prediction of long-term outcome after endovascular thrombectomy

Acute ischemic stroke (AIS) is a leading global cause of mortality and morbidity. Improving long-term outcome predictions after thrombectomy can enhance treatment quality by supporting clinical decision-making. With the advent of interpretable deep learning methods in recent years, it is now possible to develop trustworthy, high-performing prediction models. This study introduces an uncertainty-aware, graph deep learning model that predicts endovascular thrombectomy outcomes using clinical features and imaging biomarkers. The model targets long-term functional outcomes, defined by the three-month modified Rankin Score (mRS), and mortality rates. A sample of 220 AIS patients in the anterior circulation who underwent endovascular thrombectomy (EVT) was included, with 81 (37%) demonstrating good outcomes (mRS ≤ 2). The performance of the different algorithms evaluated was comparable, with the maximum validation under the curve (AUC) reaching 0.87 using graph convolutional networks (GCN) for mRS prediction and 0.86 using fully connected networks (FCN) for mortality prediction. Moderate performance was obtained at admission (AUC of 0.76 using GCN), which improved to 0.84 post-thrombectomy and to 0.89 a day after stroke. Reliable uncertainty prediction of the model could be demonstrated.