Machine Learning to Predict Delayed Cerebral Ischemia and Outcomes in Subarachnoid Hemorrhage
| العنوان: | Machine Learning to Predict Delayed Cerebral Ischemia and Outcomes in Subarachnoid Hemorrhage |
|---|---|
| المؤلفون: | Liang Zhu, Jude P.J. Savarraj, Zhongming Zhao, Farhaan S Vahidy, Ryan S. Kitagawa, Murad Megjhani, H. Alex Choi, Georgene W. Hergenroeder, Tiffany R. Chang, Soojin Park |
| المصدر: | Neurology |
| بيانات النشر: | Ovid Technologies (Wolters Kluwer Health), 2020. |
| سنة النشر: | 2020 |
| مصطلحات موضوعية: | Adult, Male, Time Factors, Subarachnoid hemorrhage, Ischemia, 030204 cardiovascular system & hematology, Machine learning, computer.software_genre, Article, Brain Ischemia, Machine Learning, 03 medical and health sciences, 0302 clinical medicine, Predictive Value of Tests, Modified Rankin Scale, Humans, Medicine, Prospective Studies, Prospective cohort study, Aged, Retrospective Studies, Receiver operating characteristic, business.industry, Retrospective cohort study, Middle Aged, Subarachnoid Hemorrhage, medicine.disease, Confidence interval, Treatment Outcome, Predictive value of tests, Female, Neurology (clinical), Artificial intelligence, business, computer, 030217 neurology & neurosurgery |
| الوصف: | ObjectiveTo determine whether machine learning (ML) algorithms can improve the prediction of delayed cerebral ischemia (DCI) and functional outcomes after subarachnoid hemorrhage (SAH).MethodsML models and standard models (SMs) were trained to predict DCI and functional outcomes with data collected within 3 days of admission. Functional outcomes at discharge and at 3 months were quantified using the modified Rankin Scale (mRS) for neurologic disability (dichotomized as good [mRS ≤ 3] vs poor [mRS ≥ 4] outcomes). Concurrently, clinicians prospectively prognosticated 3-month outcomes of patients. The performance of ML, SMs, and clinicians were retrospectively compared.ResultsDCI status, discharge, and 3-month outcomes were available for 399, 393, and 240 participants, respectively. Prospective clinician (an attending, a fellow, and a nurse) prognostication of 3-month outcomes was available for 90 participants. ML models yielded predictions with the following area under the receiver operating characteristic curve (AUC) scores: 0.75 ± 0.07 (95% confidence interval [CI] 0.64–0.84) for DCI, 0.85 ± 0.05 (95% CI 0.75–0.92) for discharge outcome, and 0.89 ± 0.03 (95% CI 0.81–0.94) for 3-month outcome. ML outperformed SMs, improving AUC by 0.20 (95% CI −0.02 to 0.4) for DCI, by 0.07 ± 0.03 (95% CI −0.0018 to 0.14) for discharge outcomes, and by 0.14 (95% CI 0.03–0.24) for 3-month outcomes and matched physician's performance in predicting 3-month outcomes.ConclusionML models significantly outperform SMs in predicting DCI and functional outcomes and has the potential to improve SAH management. |
| تدمد: | 1526-632X 0028-3878 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5afcb95bdefcc4945cf24578510a22cbTest https://doi.org/10.1212/wnl.0000000000011211Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....5afcb95bdefcc4945cf24578510a22cb |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 1526632X 00283878 |
|---|