BMC neurology · 2025
Machine learning-based models in prediction of the radiological outcomes of vestibular schwannoma following stereotactic radiosurgery: a systematic review and meta-analysis.
СтатьяСистематический обзорМетаанализНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
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.
Hajikarimloo Bardia, Nazari Mohammad Ali, Habibi Mohammad Amin, Taghipour Pourya, Alaei Seyyed-Ali, Khalaji Amirreza, Hashemi Rana, Mohammadzadeh Ibrahim, Tos Salem M
Аннотация
BACKGROUND: Prediction of the radiological outcomes of the vestibular schwannomas (VSs) following stereotactic radiosurgery (SRS) is critical in the management of these lesions. Predictions of tumor control can optimize therapeutic strategies and enhance treatment outcomes. Significant advancements in machine learning (ML) have led to the development of models to predict the radiological outcomes after SRS in VS individuals. This study evaluated the role of ML-based models in predicting the radiological outcomes of SRS in the setting of VS.
METHODS: On December 12, 2024, the four electronic databases, Pubmed, Embase, Scopus, and Web of Science, were systematically searched. Studies that evaluated the performance outcomes of the ML-based predictive models were included. The pooled sensitivity, specificity, area under the curve (AUC), and diagnostic odds ratio (DOR) were calculated through the R program. The hierarchical summary receiver operating characteristic (HSROC) model was utilized to form a summary ROC (SROC) curve.
RESULTS: Nine studies with 1095 patients were included. Most of the best performance models were ML-based (88.9 8/9). The most frequent algorithm was the support vector machine (SVM) (44.4%, 4/9). The meta-analysis revealed a pooled sensitivity rate of 86% (95%CI: 83-89%), a specificity rate of 78% (95%CI: 62-89%), and a DOR of 19.8 (95%CI: 9.12-42.9). The SROC curve exhibited an AUC of 0.845 for tumor response prediction.
CONCLUSION: Clinical application of ML-based predictive models can optimize the therapeutic strategy and enhance the outcomes for patients with VS.
METHODS: On December 12, 2024, the four electronic databases, Pubmed, Embase, Scopus, and Web of Science, were systematically searched. Studies that evaluated the performance outcomes of the ML-based predictive models were included. The pooled sensitivity, specificity, area under the curve (AUC), and diagnostic odds ratio (DOR) were calculated through the R program. The hierarchical summary receiver operating characteristic (HSROC) model was utilized to form a summary ROC (SROC) curve.
RESULTS: Nine studies with 1095 patients were included. Most of the best performance models were ML-based (88.9 8/9). The most frequent algorithm was the support vector machine (SVM) (44.4%, 4/9). The meta-analysis revealed a pooled sensitivity rate of 86% (95%CI: 83-89%), a specificity rate of 78% (95%CI: 62-89%), and a DOR of 19.8 (95%CI: 9.12-42.9). The SROC curve exhibited an AUC of 0.845 for tumor response prediction.
CONCLUSION: Clinical application of ML-based predictive models can optimize the therapeutic strategy and enhance the outcomes for patients with VS.