DOI 10.3389/fneur.2025.1674276
Predicting 90-day postoperative outcomes in spontaneous supratentorial intracerebral hemorrhage: a double-center study of clinical-radiomics integration using non-contrast CT.
Аннотация
OBJECTIVE
To evaluate the clinical utility of integrating baseline non-contrast computed tomography (NCCT) radiomics with clinical and surgical parameters for predicting 90-day postoperative functional outcomes in patients with spontaneous supratentorial intracerebral hemorrhage (sICH).
MATERIALS AND
METHODS
We retrospectively analyzed data from 220 patients with sICH who underwent surgical treatment from January 2022 to January 2025. Patients from Center 1 (n = 154) formed the training cohort, and those from Center 2 (n = 66) served as the validation cohort. Functional outcomes at 90 days were stratified using the modified Rankin Scale. Independent clinical risk factors were identified via univariate and multivariate analyses to construct a clinical model. Radiomics features extracted from baseline NCCT images were screened using elastic net regression with 10-fold cross-validation to generate a radiomics score (Radscore). A combined model was constructed by integrating Radscore into the clinical model, and its performance was evaluated using receiver operating characteristic curves, with visualization as a nomogram.
RESULTS
Six independent clinical risk factors (age, hydrocephalus, brain herniation, hematoma location, hematoma volume, surgical duration) and three optimal radiomics features (Flatness, Least axis length, VolumeCC) were identified. The combined model achieved the highest area under the receiver operating characteristic curve values: 0.882 in the training cohort and 0.865 in the validation cohort, outperforming the clinical model (0.844, 0.830) and Radscore (0.769, 0.743).
CONCLUSION
NCCT radiomics integrated with clinical parameters effectively predicts 90-day postoperative outcomes in sICH. The combined model, visualized as a nomogram, aids preoperative risk stratification and personalized treatment.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.