Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage
Abstract To examine whether machine learning (ML) approach can be used to predict hematoma expansion in acute intracerebral hemorrhage (ICH) with accuracy and widespread applicability, we applied ML algorithms to multicenter clinical data and CT findings on admission. Patients with acute ICH from th...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-15400-6 |
| _version_ | 1818192850555240448 |
|---|---|
| author | Satoru Tanioka Tetsushi Yago Katsuhiro Tanaka Fujimaro Ishida Tomoyuki Kishimoto Kazuhiko Tsuda Munenari Ikezawa Tomohiro Araki Yoichi Miura Hidenori Suzuki |
| author_facet | Satoru Tanioka Tetsushi Yago Katsuhiro Tanaka Fujimaro Ishida Tomoyuki Kishimoto Kazuhiko Tsuda Munenari Ikezawa Tomohiro Araki Yoichi Miura Hidenori Suzuki |
| author_sort | Satoru Tanioka |
| collection | DOAJ |
| description | Abstract To examine whether machine learning (ML) approach can be used to predict hematoma expansion in acute intracerebral hemorrhage (ICH) with accuracy and widespread applicability, we applied ML algorithms to multicenter clinical data and CT findings on admission. Patients with acute ICH from three hospitals (n = 351) and those from another hospital (n = 71) were retrospectively assigned to the development and validation cohorts, respectively. To develop ML predictive models, the k-nearest neighbors (k-NN) algorithm, logistic regression, support vector machines (SVMs), random forests, and XGBoost were applied to the patient data in the development cohort. The models were evaluated for their performance on the patient data in the validation cohort, which was compared with previous scoring methods, the BAT, BRAIN, and 9-point scores. The k-NN algorithm achieved the highest area under the receiver operating characteristic curve (AUC) of 0.790 among all ML models, and the sensitivity, specificity, and accuracy were 0.846, 0.733, and 0.775, respectively. The BRAIN score achieved the highest AUC of 0.676 among all previous scoring methods, which was lower than the k-NN algorithm (p = 0.016). We developed and validated ML predictive models of hematoma expansion in acute ICH. The models demonstrated good predictive ability, showing better performance than the previous scoring methods. |
| first_indexed | 2024-12-12T00:37:03Z |
| format | Article |
| id | doaj.art-dad2cf8658464cd997ee34190763f431 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-12T00:37:03Z |
| publishDate | 2022-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-dad2cf8658464cd997ee34190763f4312022-12-22T00:44:20ZengNature PortfolioScientific Reports2045-23222022-07-011211810.1038/s41598-022-15400-6Machine learning prediction of hematoma expansion in acute intracerebral hemorrhageSatoru Tanioka0Tetsushi Yago1Katsuhiro Tanaka2Fujimaro Ishida3Tomoyuki Kishimoto4Kazuhiko Tsuda5Munenari Ikezawa6Tomohiro Araki7Yoichi Miura8Hidenori Suzuki9Department of Neurosurgery, Mie Chuo Medical CenterDepartment of Neurosurgery, Mie Chuo Medical CenterDepartment of Neurosurgery, Mie Chuo Medical CenterDepartment of Neurosurgery, Mie Chuo Medical CenterDepartment of Neurosurgery, Matsusaka Chuo General HospitalDepartment of Neurosurgery, Matsusaka Chuo General HospitalDepartment of Neurosurgery, Suzuka Kaisei HospitalDepartment of Neurosurgery, Suzuka Kaisei HospitalDepartment of Neurosurgery, Mie University Graduate School of MedicineDepartment of Neurosurgery, Mie University Graduate School of MedicineAbstract To examine whether machine learning (ML) approach can be used to predict hematoma expansion in acute intracerebral hemorrhage (ICH) with accuracy and widespread applicability, we applied ML algorithms to multicenter clinical data and CT findings on admission. Patients with acute ICH from three hospitals (n = 351) and those from another hospital (n = 71) were retrospectively assigned to the development and validation cohorts, respectively. To develop ML predictive models, the k-nearest neighbors (k-NN) algorithm, logistic regression, support vector machines (SVMs), random forests, and XGBoost were applied to the patient data in the development cohort. The models were evaluated for their performance on the patient data in the validation cohort, which was compared with previous scoring methods, the BAT, BRAIN, and 9-point scores. The k-NN algorithm achieved the highest area under the receiver operating characteristic curve (AUC) of 0.790 among all ML models, and the sensitivity, specificity, and accuracy were 0.846, 0.733, and 0.775, respectively. The BRAIN score achieved the highest AUC of 0.676 among all previous scoring methods, which was lower than the k-NN algorithm (p = 0.016). We developed and validated ML predictive models of hematoma expansion in acute ICH. The models demonstrated good predictive ability, showing better performance than the previous scoring methods.https://doi.org/10.1038/s41598-022-15400-6 |
| spellingShingle | Satoru Tanioka Tetsushi Yago Katsuhiro Tanaka Fujimaro Ishida Tomoyuki Kishimoto Kazuhiko Tsuda Munenari Ikezawa Tomohiro Araki Yoichi Miura Hidenori Suzuki Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage Scientific Reports |
| title | Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage |
| title_full | Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage |
| title_fullStr | Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage |
| title_full_unstemmed | Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage |
| title_short | Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage |
| title_sort | machine learning prediction of hematoma expansion in acute intracerebral hemorrhage |
| url | https://doi.org/10.1038/s41598-022-15400-6 |
| work_keys_str_mv | AT satorutanioka machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage AT tetsushiyago machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage AT katsuhirotanaka machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage AT fujimaroishida machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage AT tomoyukikishimoto machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage AT kazuhikotsuda machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage AT munenariikezawa machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage AT tomohiroaraki machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage AT yoichimiura machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage AT hidenorisuzuki machinelearningpredictionofhematomaexpansioninacuteintracerebralhemorrhage |