The Journal of hospital infection · 2026
Machine learning-based diagnostic model combined with Chinese natural language processing for surgical-site infections: development and validation.
СтатьяМногоцентровое исследованиеВалидационное исследованиеНазвание 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.
Shan J, Bao X Y, Jin M, Wang B, Wang Y B, Wang Y, Lv M, Huai W, Jin Y C, Jin Y X, Zhang Z X, Cao Y L
Аннотация
BACKGROUND: Surgical-site infections (SSIs) are a major healthcare-associated complication, yet early detection remains challenging.
OBJECTIVE: The aim of this study was to develop and validate a machine learning (ML)-based predictive model for the detection of SSI in Chinese surgical patients.
METHODS: A multi-centre cohort study was conducted at two tertiary hospitals in China. Data from 118,314 patients who underwent surgery between June 2023 and December 2024 were used for model development and validation. Clinical, microbiological, and demographic variables were considered as predictors. Multiple ML algorithms were applied, with hyperparameter tuning and cross-validation. Model performance was evaluated using area under the curve (AUC), sensitivity, specificity, and accuracy.
RESULTS: The decision tree model demonstrated robust predictive performance, achieving an AUC of 0.92 in the development cohort and 0.90 in the validation cohort. Sensitivity and specificity values confirmed its effectiveness in identifying patients at an elevated risk of SSIs. Performance remained stable across subgroups.
CONCLUSIONS: This study established and externally validated an ML-based model for SSI prediction in surgical patients. The model showed strong and consistent performance and may support clinical decision-making by enabling real-time, automated risk assessment.
OBJECTIVE: The aim of this study was to develop and validate a machine learning (ML)-based predictive model for the detection of SSI in Chinese surgical patients.
METHODS: A multi-centre cohort study was conducted at two tertiary hospitals in China. Data from 118,314 patients who underwent surgery between June 2023 and December 2024 were used for model development and validation. Clinical, microbiological, and demographic variables were considered as predictors. Multiple ML algorithms were applied, with hyperparameter tuning and cross-validation. Model performance was evaluated using area under the curve (AUC), sensitivity, specificity, and accuracy.
RESULTS: The decision tree model demonstrated robust predictive performance, achieving an AUC of 0.92 in the development cohort and 0.90 in the validation cohort. Sensitivity and specificity values confirmed its effectiveness in identifying patients at an elevated risk of SSIs. Performance remained stable across subgroups.
CONCLUSIONS: This study established and externally validated an ML-based model for SSI prediction in surgical patients. The model showed strong and consistent performance and may support clinical decision-making by enabling real-time, automated risk assessment.