1
|
López-Rueda A, Rodríguez-Sánchez MÁ, Serrano E, Moreno J, Rodríguez A, Llull L, Amaro S, Oleaga L. Enhancing mortality prediction in patients with spontaneous intracerebral hemorrhage: Radiomics and supervised machine learning on non-contrast computed tomography. Eur J Radiol Open 2024; 13:100618. [PMID: 39687913 PMCID: PMC11648778 DOI: 10.1016/j.ejro.2024.100618] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2024] [Revised: 11/17/2024] [Accepted: 11/28/2024] [Indexed: 12/18/2024] Open
Abstract
Purpose This study aims to develop a Radiomics-based Supervised Machine-Learning model to predict mortality in patients with spontaneous intracerebral hemorrhage (sICH). Methods Retrospective analysis of a prospectively collected clinical registry of patients with sICH consecutively admitted at a single academic comprehensive stroke center between January-2016 and April-2018. We conducted an in-depth analysis of 105 radiomic features extracted from 105 patients. Following the identification and handling of missing values, radiomics values were scaled to 0-1 to train different classifiers. The sample was split into 80-20 % training-test and validation cohort in a stratified fashion. Random Forest(RF), K-Nearest Neighbor(KNN), and Support Vector Machine(SVM) classifiers were evaluated, along with several feature selection methods and hyperparameter optimization strategies, to classify the binary outcome of mortality or survival during hospital admission. A tenfold stratified cross-validation method was used to train the models, and average metrics were calculated. Results RF, KNN, and SVM, with the "DropOut+SelectKBest" feature selection strategy and no hyperparameter optimization, demonstrated the best performances with the least number of radiomic features and the most simplified models, achieving a sensitivity range between 0.90 and 0.95 and AUC range from 0.97 to 1 on the validation dataset. Regarding the confusion matrix, the SVM model did not predict any false negative test (negative predicted value 1). Conclusion Radiomics-based Supervised Machine Learning models can predict mortality during admission in patients with sICH. SVM with the "DropOut+SelectKBest" feature selection strategy and no hyperparameter optimization was the best simplified model to detect mortality during admission in patients with sICH.
Collapse
Affiliation(s)
- Antonio López-Rueda
- Clinical Informatics Department, Hospital Clínic de Barcelona, Barcelona, Spain
- Radiology Department, Hospital Clínic de Barcelona, Barcelona, Spain
| | | | - Elena Serrano
- Radiology Department, Hospital Universitario de Bellvitge, Barcelona, Spain
| | - Javier Moreno
- Radiology Department, Hospital Clínic de Barcelona, Barcelona, Spain
| | | | - Laura Llull
- Neurology Department, Hospital Clínic de Barcelona, Barcelona, Spain
| | - Sergi Amaro
- Neurology Department, Hospital Clínic de Barcelona, Barcelona, Spain
| | - Laura Oleaga
- Radiology Department, Hospital Clínic de Barcelona, Barcelona, Spain
| |
Collapse
|
2
|
Serrano E, Moreno J, Llull L, Rodríguez A, Zwanzger C, Amaro S, Oleaga L, López-Rueda A. Radiomic-based nonlinear supervised learning classifiers on non-contrast CT to predict functional prognosis in patients with spontaneous intracerebral hematoma. RADIOLOGIA 2023; 65:519-530. [PMID: 38049251 DOI: 10.1016/j.rxeng.2023.08.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2023] [Accepted: 08/03/2023] [Indexed: 12/06/2023]
Abstract
PURPOSE To evaluate if nonlinear supervised learning classifiers based on non-contrast CT can predict functional prognosis at discharge in patients with spontaneous intracerebral hematoma. METHODS Retrospective, single-center, observational analysis of patients with a diagnosis of spontaneous intracerebral hematoma confirmed by non-contrast CT between January 2016 and April 2018. Patients with HIE > 18 years and with TCCSC performed within the first 24 h of symptom onset were included. Patients with secondary spontaneous intracerebral hematoma and in whom radiomic variables were not available were excluded. Clinical, demographic and admission variables were collected. Patients were classified according to the Modified Rankin Scale (mRS) at discharge into good (mRS 0-2) and poor prognosis (mRS 3-6). After manual segmentation of each spontaneous intracerebral hematoma, the radiomics variables were obtained. The sample was divided into a training and testing cohort and a validation cohort (70-30% respectively). Different methods of variable selection and dimensionality reduction were used, and different algorithms were used for model construction. Stratified 10-fold cross-validation were performed on the training and testing cohort and the mean area under the curve (AUC) were calculated. Once the models were trained, the sensitivity of each was calculated to predict functional prognosis at discharge in the validation cohort. RESULTS 105 patients with spontaneous intracerebral hematoma were analyzed. 105 radiomic variables were evaluated for each patient. P-SVM, KNN-E and RF-10 algorithms, in combination with the ANOVA variable selection method, were the best performing classifiers in the training and testing cohort (AUC 0.798, 0.752 and 0.742 respectively). The predictions of these models, in the validation cohort, had a sensitivity of 0.897 (0.778-1;95%CI), with a false-negative rate of 0% for predicting poor functional prognosis at discharge. CONCLUSION The use of radiomics-based nonlinear supervised learning classifiers are a promising diagnostic tool for predicting functional outcome at discharge in HIE patients, with a low false negative rate, although larger and balanced samples are still needed to develop and improve their performance.
Collapse
Affiliation(s)
- E Serrano
- Departamento Radiología, Hospital Universitario Bellvitge, Hospitalet de Llobregat, Barcelona, Spain
| | - J Moreno
- Clínica Iribas-IRM, Asunción, Paraguay
| | - L Llull
- Departamento de Neurología, Hospital Clínic, Barcelona, Spain
| | - A Rodríguez
- Departamento de Neurología, Hospital Clínic, Barcelona, Spain
| | - C Zwanzger
- Departamento Radiología, Hospital del Mar, Barcelona, Spain
| | - S Amaro
- Departamento de Neurología, Hospital Clínic, Barcelona, Spain
| | - L Oleaga
- Departamento Radiología, Hospital Clínic, Barcelona, Spain
| | - A López-Rueda
- Departamento Radiología, Hospital Clínic, Barcelona, Spain; Servicio de Informática Clínica, Hospital Clínic, Barcelona, Spain.
| |
Collapse
|
3
|
Hillal A, Ullberg T, Ramgren B, Wassélius J. Computed tomography in acute intracerebral hemorrhage: neuroimaging predictors of hematoma expansion and outcome. Insights Imaging 2022; 13:180. [DOI: 10.1186/s13244-022-01309-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2022] [Accepted: 09/24/2022] [Indexed: 11/24/2022] Open
Abstract
AbstractIntracerebral hemorrhage (ICH) accounts for 10–20% of all strokes worldwide and is associated with serious outcomes, including a 30-day mortality rate of up to 40%. Neuroimaging is pivotal in diagnosing ICH as early detection and determination of underlying cause, and risk for expansion/rebleeding is essential in providing the correct treatment. Non-contrast computed tomography (NCCT) is the most used modality for detection of ICH, identification of prognostic markers and measurements of hematoma volume, all of which are of major importance to predict outcome. The strongest predictors of 30-day mortality and functional outcome for ICH patients are baseline hematoma volume and hematoma expansion. Even so, exact hematoma measurement is rare in clinical routine practice, primarily due to a lack of tools available for fast, effective, and reliable volumetric tools. In this educational review, we discuss neuroimaging findings for ICH from NCCT images, and their prognostic value, as well as the use of semi-automatic and fully automated hematoma volumetric methods and assessment of hematoma expansion in prognostic studies.
Collapse
|
4
|
Huang X, Wang D, Zhang Q, Ma Y, Zhao H, Li S, Deng J, Ren J, Yang J, Zhao Z, Xu M, Zhou Q, Zhou J. Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study. Neuroimage Clin 2022; 36:103242. [PMID: 36279754 PMCID: PMC9668657 DOI: 10.1016/j.nicl.2022.103242] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2022] [Revised: 10/15/2022] [Accepted: 10/18/2022] [Indexed: 11/11/2022]
Abstract
BACKGROUND Accurate risk stratification of patients with intracerebral hemorrhage (ICH) could help refine adjuvant therapy selection and better understand the clinical course. We aimed to evaluate the value of radiomics features from hematomal and perihematomal edema areas for prognosis prediction and to develop a model combining clinical and radiomic features for accurate outcome prediction of patients with ICH. METHODS This multicenter study enrolled patients with ICH from January 2016 to November 2021. Their outcomes at 3 months were recorded based on the modified Rankin Scale (good, 0-3; poor, 4-6). Independent clinical and radiomic risk factors for poor outcome were identified through multivariate logistic regression analysis, and predictive models were developed. Model performance and clinical utility were evaluated in both internal and external cohorts. RESULTS Among the 1098 ICH patients evaluated (mean age, 60 ± 13 years), 703 (64 %) had poor outcomes. Age, hemorrhage volume and location, and Glasgow Coma Scale (GCS) were independently associated with outcomes. The area under the receiver operating characteristic curve (AUC) of the clinical model was 0.881 in the external validation cohort. Addition of the Rad-score (combined hematoma and perihematomal edema area) improved predictive accuracy and model performance (AUC, 0.893), net reclassification improvement, 0.140 (P < 0.001), and integrated discrimination improvement, 0.050 (P < 0.001). CONCLUSIONS The radiomics features of hematomal and perihematomal edema area have additional value in prognostic prediction; moreover, addition of radiomic features significantly improves model accuracy.
Collapse
Affiliation(s)
- Xiaoyu Huang
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China
| | - Dan Wang
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China
| | - Qiaoying Zhang
- Department of Radiology, Xi'an Central Hospital, Xi An 710000, China
| | - Yaqiong Ma
- Second Clinical School, Lanzhou University, Lanzhou 730030, China; Department of Radiology, Gansu Provincial Hospital, Lanzhou 730030, China
| | - Hui Zhao
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China
| | - Shenglin Li
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China
| | - Juan Deng
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China
| | | | - Jingjing Yang
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China
| | - Zhiyong Zhao
- Department of Radiology, Gansu Provincial Hospital, Lanzhou 730030, China
| | - Min Xu
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China
| | - Qing Zhou
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China
| | - Junlin Zhou
- Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China; Department of Neurosurgery, Lanzhou University Second Hospital Lanzhou 730030, China.
| |
Collapse
|