Data-efficient deep learning of radiological image data for outcome prediction after endovascular treatment of patients with acute ischemic stroke

Hilbert, Adam; Ramos, Lucas A.; Os, Hendrikus J.A. van; Olabarriaga, Sílvia D.; Tolhuisen, Manon L.; Wermer, M.J.H.; Barros, Renan Sales; Schaaf, Irene van der; Dippel, Diederik W.J.; Roos, Yvo B.W.E.M.; Zwam, Wim H. van; Yoo, Albert J.; Emmer, Bart J.; Nijeholt, Geert J. Lycklama à; Zwinderman, Aeilko H.; Strijkers, Gustav J.; Majoie, Charles B. L. M.; Marquering, Henk A.

doi:10.1016/j.compbiomed.2019.103516

Cited by 88 publications

(91 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Besides, the more extensive follow-up NIHSS could be used to define poor functional outcome in future studies. Furthermore, for future research, ML models could be created using the raw imaging data (CT or CT angiography or both) and combined with the models created in this study (10,12,36,37). However, the large number of data points has to be taken into account when developing such approaches because imaging data is often of high dimensionality, and medical datasets have often a very limited number of samples.…”

Section: Strengths and Limitationsmentioning

confidence: 99%

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke

Ramos

Kappelhof

et al. 2020

Front. Neurol.

View full text Add to dashboard Cite

Background: Although endovascular treatment (EVT) has greatly improved outcomes in acute ischemic stroke, still one third of patients die or remain severely disabled after stroke. If we could select patients with poor clinical outcome despite EVT, we could prevent futile treatment, avoid treatment complications, and further improve stroke care. We aimed to determine the accuracy of poor functional outcome prediction, defined as 90-day modified Rankin Scale (mRS) score ≥5, despite EVT treatment. Methods: We included 1,526 patients from the MR CLEAN Registry, a prospective, observational, multicenter registry of ischemic stroke patients treated with EVT. We developed machine learning prediction models using all variables available at baseline before treatment. We optimized the models for both maximizing the area under the curve (AUC), reducing the number of false positives. Results: From 1,526 patients included, 480 (31%) of patients showed poor outcome. The highest AUC was 0.81 for random forest. The highest area under the precision recall curve was 0.69 for the support vector machine. The highest achieved specificity was 95% with a sensitivity of 34% for neural networks, indicating that all models contained false positives in their predictions. From 921 mRS 0-4 patients, 27-61 (3-6%) were incorrectly classified as poor outcome. From 480 poor outcome patients in the registry, 99-163 (21-34%) were correctly identified by the models. Conclusions: All prediction models showed a high AUC. The best-performing models correctly identified 34% of the poor outcome patients at a cost of misclassifying 4% of non-poor outcome patients. Further studies are necessary to determine whether these accuracies are reproducible before implementation in clinical practice.

show abstract

Section: Strengths and Limitationsmentioning

confidence: 99%

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke

Ramos

Kappelhof

et al. 2020

Front. Neurol.

View full text Add to dashboard Cite

show abstract

“…In the scope of this project imaging data was hypothesized as a means to improve the performance of clinical-based outcome prediction models, rather than providing reliable outcome prediction by itself. Nevertheless, the CNN framework trained only on imaging data for the outcome prediction task showed comparable results to the data-efficient method of Hilbert et al, 2019. At the same time, performance was relatively high on the training sets compared with the test sets, indicating that the model was suffering from overfitting.…”

Section: Discussionmentioning

confidence: 95%

“…A number of studies have presented models using Multilayer Perceptrons (MLPs) for outcome prediction based on clinical parameters (Asadi et al, 2014;Heo et al, 2019). Additionally, using Convolutional Neural Networks (CNNs) on imaging data has been proven to give promising results in tissue outcome prediction (Nielsen et al, 2018;Pinto et al, 2018), as well as predicting final stroke outcome (Hilbert et al, 2019). Hence, we propose two unimodal architectures based on deep learning methods: a 3D CNN to process neuroimaging data and an MLP for processing clinical metadata; both tailored to the requirements of the data and the final outcome prediction task.…”

Section: Introductionmentioning

confidence: 99%

Multimodal Fusion Strategies for Outcome Prediction in Stroke

Zihni

Madai

Khalil

et al. 2020

Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies

View full text Add to dashboard Cite

Data driven methods are increasingly being adopted in the medical domain for clinical predictive modeling. Prediction of stroke outcome using machine learning could provide a decision support system for physicians to assist them in patient-oriented diagnosis and treatment. While patient-specific clinical parameters play an important role in outcome prediction, a multimodal fusion approach that integrates neuroimaging with clinical data has the potential to improve accuracy. This paper addresses two research questions: (a) does multimodal fusion aid in the prediction of stroke outcome, and (b) what fusion strategy is more suitable for the task at hand. The baselines for our experimental work are two unimodal neural architectures: a 3D Convolutional Neural Network for processing neuroimaging data, and a Multilayer Perceptron for processing clinical data. Using these unimodal architectures as building blocks we propose two feature-level multimodal fusion strategies: 1) extracted features, where the unimodal architectures are trained separately and then fused, and 2) end-to-end, where the unimodal architectures are trained together. We show that integration of neuroimaging information with clinical metadata can potentially improve stroke outcome prediction. Additionally, experimental results indicate that the end-to-end fusion approach proves to be more robust.

show abstract

“…The first main reason was that the OCSP subtype was based on these neurological deficits. The second one was that the newly developed machine learning methods (such as deep learning) could process medical data better [27,28], even the features collected in 1990's were not very mature. In the study the dataset was firstly analyzed by Shapiro-Wilk algorithm and Pearson Correlation.…”

Section: Discussionmentioning

confidence: 99%

Automated Ischemic Stroke Subtyping Based on Machine Learning Approach

Fang

Liu

2020

IEEE Access

View full text Add to dashboard Cite

Ischemic stroke subtyping was not only highly valuable for effective intervention and treatment, but also important to the prognosis of ischemic stroke. The manual adjudication of disease classification was time-consuming, error-prone, and limits scaling to large datasets. In this study, an integrated machine learning approach was used to classify the subtype of ischemic stroke on The International Stroke Trial (IST) dataset. We considered the common problems of feature selection and prediction in medical datasets. Firstly, the importances of features were ranked by the Shapiro-Wilk algorithm and Pearson correlations between features were analyzed. Then, we used Recursive Feature Elimination with Cross-Validation (RFECV), which incorporated linear SVC, Random-Forest-Classifier, Extra-Trees-Classifier, AdaBoost-Classifier, and Multinomial-Naïve-Bayes-Classifier as estimator respectively, to select robust features important to ischemic stroke subtyping. Furthermore, the importances of selected features were determined by Extra-Trees-Classifier. Finally, the selected features were used by Extra-Trees-Classifier and a simple deep learning model to classify the ischemic stroke subtype on IST dataset. It was suggested that the described method could classify ischemic stroke subtype accurately. And the result showed that the machine learning approaches outperformed human professionals.

show abstract

Data-efficient deep learning of radiological image data for outcome prediction after endovascular treatment of patients with acute ischemic stroke

Cited by 88 publications

References 38 publications

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke

Multimodal Fusion Strategies for Outcome Prediction in Stroke

Automated Ischemic Stroke Subtyping Based on Machine Learning Approach

Contact Info

Product

Resources

About