Abstract 1122‐000047: Machine Learning to Predict Stroke Outcomes after Mechanical Thrombectomy
Introduction: Prognostication is an integral part of clinical decision‐making in stroke care. Machine learning (ML) methods have gained increasing popularity in the medical field due to their flexibility and high performance. Using a large comprehensive stroke center registry, we sought to apply var...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-11-01
|
| Series: | Stroke: Vascular and Interventional Neurology |
| Subjects: | |
| Online Access: | https://www.ahajournals.org/doi/10.1161/SVIN.01.suppl_1.000047 |
| _version_ | 1797948343560699904 |
|---|---|
| author | Mehdi Bouslama Leonardo Pisani Diogo Haussen Raul Nogueira |
| author_facet | Mehdi Bouslama Leonardo Pisani Diogo Haussen Raul Nogueira |
| author_sort | Mehdi Bouslama |
| collection | DOAJ |
| description | Introduction: Prognostication is an integral part of clinical decision‐making in stroke care. Machine learning (ML) methods have gained increasing popularity in the medical field due to their flexibility and high performance. Using a large comprehensive stroke center registry, we sought to apply various ML techniques for 90‐day stroke outcome predictions after thrombectomy. Methods: We used individual patient data from our prospectively collected thrombectomy database between 09/2010 and 03/2020. Patients with anterior circulation strokes (Internal Carotid Artery, Middle Cerebral Artery M1, M2, or M3 segments and Anterior Cerebral Artery) and complete records were included. Our primary outcome was 90‐day functional independence (defined as modified Rankin Scale score 0–2). Pre‐ and post‐procedure models were developed. Four known ML algorithms (support vector machine, random forest, gradient boosting, and artificial neural network) were implemented using a 70/30 training‐test data split and 10‐fold cross‐validation on the training data for model calibration. Discriminative performance was evaluated using the area under the receiver operator characteristics curve (AUC) metric. Results: Among 1248 patients with anterior circulation large vessel occlusion stroke undergoing thrombectomy during the study period, 1020 had complete records and were included in the analysis. In the training data (n = 714), 49.3% of the patients achieved independence at 90‐days. Fifteen baseline clinical, laboratory and neuroimaging features were used to develop the pre‐procedural models, with four additional parameters included in the post‐procedure models. For the preprocedural models, the highest AUC was 0.797 (95%CI [0.75‐ 0.85]) for the gradient boosting model. Similarly, the same ML technique performed best on post‐procedural data and had an improved discriminative performance compared to the pre‐procedure model with an AUC of 0.82 (95%CI [0.77‐ 0.87]). Conclusions: Our pre‐and post‐procedural models reliably estimated outcomes in stroke patients undergoing thrombectomy. They represent a step forward in creating simple and efficient prognostication tools to aid treatment decision‐making. A web‐based platform and related mobile app are underway. |
| first_indexed | 2024-04-10T21:42:57Z |
| format | Article |
| id | doaj.art-c28947aba4f5418894e12b65602db817 |
| institution | Directory Open Access Journal |
| issn | 2694-5746 |
| language | English |
| last_indexed | 2024-04-10T21:42:57Z |
| publishDate | 2021-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Stroke: Vascular and Interventional Neurology |
| spelling | doaj.art-c28947aba4f5418894e12b65602db8172023-01-18T21:39:24ZengWileyStroke: Vascular and Interventional Neurology2694-57462021-11-011S110.1161/SVIN.01.suppl_1.000047Abstract 1122‐000047: Machine Learning to Predict Stroke Outcomes after Mechanical ThrombectomyMehdi Bouslama0Leonardo Pisani1Diogo Haussen2Raul Nogueira3New‐York Presbyterian | Weill Cornell Medicine, New York New York United States of AmericaSt Vincent Hospital, Worcester Massachusetts United States of AmericaEmory University SOM, Atlanta Georgia United States of AmericaEmory University SOM, Atlanta Georgia United States of AmericaIntroduction: Prognostication is an integral part of clinical decision‐making in stroke care. Machine learning (ML) methods have gained increasing popularity in the medical field due to their flexibility and high performance. Using a large comprehensive stroke center registry, we sought to apply various ML techniques for 90‐day stroke outcome predictions after thrombectomy. Methods: We used individual patient data from our prospectively collected thrombectomy database between 09/2010 and 03/2020. Patients with anterior circulation strokes (Internal Carotid Artery, Middle Cerebral Artery M1, M2, or M3 segments and Anterior Cerebral Artery) and complete records were included. Our primary outcome was 90‐day functional independence (defined as modified Rankin Scale score 0–2). Pre‐ and post‐procedure models were developed. Four known ML algorithms (support vector machine, random forest, gradient boosting, and artificial neural network) were implemented using a 70/30 training‐test data split and 10‐fold cross‐validation on the training data for model calibration. Discriminative performance was evaluated using the area under the receiver operator characteristics curve (AUC) metric. Results: Among 1248 patients with anterior circulation large vessel occlusion stroke undergoing thrombectomy during the study period, 1020 had complete records and were included in the analysis. In the training data (n = 714), 49.3% of the patients achieved independence at 90‐days. Fifteen baseline clinical, laboratory and neuroimaging features were used to develop the pre‐procedural models, with four additional parameters included in the post‐procedure models. For the preprocedural models, the highest AUC was 0.797 (95%CI [0.75‐ 0.85]) for the gradient boosting model. Similarly, the same ML technique performed best on post‐procedural data and had an improved discriminative performance compared to the pre‐procedure model with an AUC of 0.82 (95%CI [0.77‐ 0.87]). Conclusions: Our pre‐and post‐procedural models reliably estimated outcomes in stroke patients undergoing thrombectomy. They represent a step forward in creating simple and efficient prognostication tools to aid treatment decision‐making. A web‐based platform and related mobile app are underway.https://www.ahajournals.org/doi/10.1161/SVIN.01.suppl_1.000047Acute StrokeMechanical Thrombectomy |
| spellingShingle | Mehdi Bouslama Leonardo Pisani Diogo Haussen Raul Nogueira Abstract 1122‐000047: Machine Learning to Predict Stroke Outcomes after Mechanical Thrombectomy Stroke: Vascular and Interventional Neurology Acute Stroke Mechanical Thrombectomy |
| title | Abstract 1122‐000047: Machine Learning to Predict Stroke Outcomes after Mechanical Thrombectomy |
| title_full | Abstract 1122‐000047: Machine Learning to Predict Stroke Outcomes after Mechanical Thrombectomy |
| title_fullStr | Abstract 1122‐000047: Machine Learning to Predict Stroke Outcomes after Mechanical Thrombectomy |
| title_full_unstemmed | Abstract 1122‐000047: Machine Learning to Predict Stroke Outcomes after Mechanical Thrombectomy |
| title_short | Abstract 1122‐000047: Machine Learning to Predict Stroke Outcomes after Mechanical Thrombectomy |
| title_sort | abstract 1122 000047 machine learning to predict stroke outcomes after mechanical thrombectomy |
| topic | Acute Stroke Mechanical Thrombectomy |
| url | https://www.ahajournals.org/doi/10.1161/SVIN.01.suppl_1.000047 |
| work_keys_str_mv | AT mehdibouslama abstract1122000047machinelearningtopredictstrokeoutcomesaftermechanicalthrombectomy AT leonardopisani abstract1122000047machinelearningtopredictstrokeoutcomesaftermechanicalthrombectomy AT diogohaussen abstract1122000047machinelearningtopredictstrokeoutcomesaftermechanicalthrombectomy AT raulnogueira abstract1122000047machinelearningtopredictstrokeoutcomesaftermechanicalthrombectomy |