BMC nursing · 2026
Which machine learning algorithms are best at predicting eating disorder tendencies among nursing students in China?
СтатьяНазвание и аннотация: Перевод в очереди
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.
Wang Zenghui, Chen Chen, Sun Xiangjie, Deng Tiantian, Yang Deyan, Feng Danjun
Аннотация
BACKGROUND: Nursing students are at high risk for developing eating disorders (ED). However, methods for identifying ED tendencies within this group remain underexplored.
PURPOSE: This study aims to develop and validate machine learning-based models for predicting ED tendencies among nursing students.
METHODS: A cross-sectional study was conducted with a sample of nursing students in mainland China (N = 1709). Machine learning models were developed using a training set (N = 1196), and internally validated using a test set (N = 513). Model performance was evaluated based on widely used metrics, including the area under the receiver operating characteristic curve (AUC).
RESULTS: The random forest performed best in test set, achieving a Bootstrapped_AUC of 0.804 (95% CI, 0.787, 0.818), a Bootstrapped_AP of 0.711 (95% CI, 0.682, 0.739), and a brier score of 0.170. The non-black box models showed that rumination related to ED, low body satisfaction, and depression were significant risk factors of eating disorders tendencies among nursing students.
CONCLUSION: Machine learning-based models can help nursing educators to identify nursing students at risk of ED. Additionally, addressing cognitive biases regarding body shape and weight, as well as alleviating depressive symptoms, may help reduce ED risk among nursing students.
CLINICAL TRIAL NUMBER: Not applicable.
PURPOSE: This study aims to develop and validate machine learning-based models for predicting ED tendencies among nursing students.
METHODS: A cross-sectional study was conducted with a sample of nursing students in mainland China (N = 1709). Machine learning models were developed using a training set (N = 1196), and internally validated using a test set (N = 513). Model performance was evaluated based on widely used metrics, including the area under the receiver operating characteristic curve (AUC).
RESULTS: The random forest performed best in test set, achieving a Bootstrapped_AUC of 0.804 (95% CI, 0.787, 0.818), a Bootstrapped_AP of 0.711 (95% CI, 0.682, 0.739), and a brier score of 0.170. The non-black box models showed that rumination related to ED, low body satisfaction, and depression were significant risk factors of eating disorders tendencies among nursing students.
CONCLUSION: Machine learning-based models can help nursing educators to identify nursing students at risk of ED. Additionally, addressing cognitive biases regarding body shape and weight, as well as alleviating depressive symptoms, may help reduce ED risk among nursing students.
CLINICAL TRIAL NUMBER: Not applicable.