Related Experiment Video
Updated: Jul 8, 2025
Optimized Management of Endovascular Treatment for Acute Ischemic Stroke
Published on: January 18, 2018
Explaining predictors of discharge destination assessed along the patients' acute stroke journey
Artem Lensky1, Christian Lueck2, Hanna Suominen3
1School of Engineering and Technology, The University of New South Wales, Canberra ACT 2600, Australia; School of Biomedical Engineering, The University of Sydney, NSW, Australia.
Insights
Machine learning models accurately predict stroke patient discharge destinations early. Adaptive Boosting excels at predicting death, with key factors including stroke scales, dyslipidemia, and hypertension.
Area of Science:
- Neurology
- Medical Informatics
- Machine Learning
Background:
- Early prediction of stroke patient outcomes is crucial for effective management.
- This study evaluates machine learning (ML) algorithms for predicting discharge destinations at various stroke progression stages.
Purpose of the Study:
- To assess the predictive accuracy of three ML algorithms (k-Nearest Neighbour, Adaptive Boosting, Bootstrap Aggregation) for stroke patient outcomes.
- To compare the predictive power of ML models against traditional stroke scores.
Main Methods:
- Retrospective analysis of acute stroke patients (2015-2019).
- Utilized 16 predictors and discharge destination as the target variable.
- Employed k-Nearest Neighbour, Adaptive Boosting, and Bootstrap Aggregation for outcome prediction.
- Assessed accuracy at four stages and evaluated feature importance using Relief algorithm.
Main Results:
- Adaptive Boosting achieved 90% accuracy in predicting death at Stage 4.
- kNN (k=2) showed the highest overall accuracy (81.7%).
- Key predictors included 24-hour Scandinavian Stroke Scale (SSS) and National Institutes of Health Stroke Scale (NIHSS) scores, dyslipidemia, hypertension, and premorbid mRS score.
- Combining initial SSS and 24-hour NIHSS scores improved death prediction accuracy to 95% (Adaptive Boosting) and overall accuracy to 85.4% (kNN).
Conclusions:
- Clinically useful predictions of discharge destination are possible even in early stroke management stages.
- Adaptive Boosting appears to be the most effective ML model, particularly for predicting mortality.
- Hypertension and dyslipidemia were identified as significant predictors of discharge outcome.
- Utilizing mixed stroke score systems can enhance prediction accuracy.
Introduction:
Accurate prediction of outcome destination at an early stage would help manage patients presenting with stroke. This study assessed the predictive ability of three machine learning (ML) algorithms to predict outcomes at four different stages as well as compared the predictive power of stroke scores.
Methods:
Patients presenting with acute stroke to the Canberra Hospital between 2015 and 2019 were selected retrospectively. 16 potential predictors and one target variable (discharge destination) were obtained from the notes. k-Nearest Neighbour (kNN) and two ensemble-based classification algorithms (Adaptive Boosting and Bootstrap Aggregation) were employed to predict outcomes. Predictive accuracy was assessed at each of the four stages using both overall and per-class accuracy. The contribution of each variable to the prediction outcome was evaluated by the ensemble-based algorithm and using the Relief feature selection algorithm. Various combinations of stroke scores were tested using the aforementioned models.
Results:
Of the three ML models, Adaptive Boosting demonstrated the highest accuracy (90%) at Stage 4 in predicting death while the highest overall accuracy (81.7%) was achieved by kNN (k=2/City-block distance). Feature importance analysis has shown that the most important features are the 24-hour Scandinavian Stroke Scale (SSS) and 24-hour National Institutes of Health Stroke Scale (NIHSS) scores, dyslipidaemia, hypertension and premorbid mRS score. For the initial and 24-hour scores, there was a higher correlation (0.93) between SSS scores than for NIHSS scores (0.81). Reducing the overall four scores to InitSSS/24hrNIHSS increased accuracy to 95% in predicting death (Adaptive Boosting) and overall accuracy to 85.4% (kNN). Accuracies at Stage 2 (pre-treatment, 11 predictors) were not far behind those at Stage 4.
Conclusion:
Our findings suggest that even in the early stages of management, a clinically useful prediction regarding discharge destination can be made. Adaptive Boosting might be the best ML model, especially when it comes to predicting death. The predictors' importance analysis also showed that dyslipidemia and hypertension contributed to the discharge outcome even more than expected. Further, surprisingly using mixed score systems might also lead to higher prediction accuracies.
More Related Videos
06:52Assessment of Dependence in Activities of Daily Living Among Older Patients in an Acute Care Unit
Published on: September 30, 2020
09:52Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide
Published on: January 15, 2017
Related Concept Videos
01:31Discharge Summary Forms
Here's a detailed look at the key components and guidelines for preparing a discharge summary:
01:21Planning Nursing Care I
01:19Restorative Care
01:27Regulation of Stroke Volume
Preload refers to the degree of stretch on the heart before it contracts. It's analogous to the stretching of a rubber band; the more it's stretched, the more forcefully it snaps back. This concept is encapsulated in the Frank-Starling law of the...