MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1016/j.crad.2024.05.009

Медицинская библиотека · Clinical radiology · 2024

Combined radiomics nomogram of different machine learning models for preoperative distinguishing intraspinal schwannomas and meningiomas: a multicenter and comparative study.

Xu Z, Wang Y-H, Cheng Z-Y, Feng Y-Z, Li X-C, Zhou Q, Cai X-R

СтатьяМногоцентровое исследованиеСравнительное исследованиеПоддержка исследования: вне правительства СШАПеревод пока не подготовлен

Аннотация

AIMS: The objective of our study was to establish and verify a novel combined model based on multiparameter magnetic resonance imaging (MRI) radiomics and clinical features to distinguish intraspinal schwannomas from meningiomas.

MATERIALS AND

METHODS

This research analyzed the preoperative magnetic resonance (MR) images and clinical characteristics of 209 patients with intraspinal tumors who received tumor resection at three institutions. 159 individuals from institutions 1 and 2 were randomly assigned into a training group (n=111) and a test group (n=48) in a 7-3 ratio. A nomogram was constructed using the training cohort and was internally and externally verified in the test cohort and an independent validation cohort (n=50). Model performance was assessed utilizing the area under the curve (AUC) of receiver operating characteristics (ROC), decision curve analysis (DCA), and calibration curves.

RESULTS

The nomogram exhibited superior predictive efficacy in distinguishing between spinal schwannomas and meningiomas when compared to both the radiomics model and the clinical model. The nomogram yielded AUCs of 0.994, 0.962, and 0.949 in the training, test, and external validation cohorts, respectively, indicating its exceptional differentiating ability. The DCAs demonstrated that the nomogram yielded the best net benefit. The calibration curves indicated that the nomogram got good agreement between the predicted and the actual observation.

CONCLUSION

This research suggests that the nomogram incorporating clinical and radiomic features may be an effective auxiliary tool for distinguishing between intraspinal schwannomas and meningiomas, and has important clinical significance for clinical decision-making and prognosis prediction.

Для цитирования: Xu Z, Wang Y-H, Cheng Z-Y, Feng Y-Z, Li X-C, Zhou Q, Cai X-R. Combined radiomics nomogram of different machine learning models for preoperative distinguishing intraspinal schwannomas and meningiomas: a multicenter and comparative study.. Clinical radiology. 2024. DOI: 10.1016/j.crad.2024.05.009.

Предметные рубрики MeSH

Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

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.