Infectious diseases and therapy · 2026
Clinical Research on Microecological Landscape for Infection Risk Stratification in Newly Diagnosed Patients with Hematological Conditions.
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.
Peng Miaoxin, Xu Yueyi, Cao Xuefang, Xue Yizhe, Pang Jie, Zhou Shiyuan, Xu Peipei, Yang Yonggong, Zhang Xiaoping, Qian Jun, Wang Yang, Lu Xuzhang, Wan Yan, Sun Yu, Hua Xiaoying, Xu Yan, Chen Bing, Ouyang Jian
Аннотация
INTRODUCTION: Infection is a common and potentially fatal complication during the treatment of hematological diseases, particularly in the context of chemotherapy-induced immunosuppression. The nonselective use of antibiotic prophylaxis in patients with neutropenia in China has persistently accelerated antimicrobial resistance. Early identification of patients at high risk for infection before clinical symptom onset could enable targeted preventive strategies; however, reliable and biologically informed screening approaches remain limited.
METHODS: We developed a prediction model for infection risk stratification in newly diagnosed patients with hematological conditions. Plasma metagenomic next-generation sequencing was performed in a prospective cohort of 230 patients. Among them, 116 patients provided prechemotherapy, non-neutropenic plasma samples (cohort A), and 114 patients provided postchemotherapy, neutropenic samples (cohort B). Microbial community profiles were analyzed, and machine learning approaches were applied to construct classifiers for neutropenia status and subsequent infection risk.
RESULTS: Plasma metagenomic profiling revealed a complex microecological landscape in patients with hematological conditions and identified distinct microbial features associated with neutropenia. A trained random forest classifier successfully distinguished patients without neutropenia from patients with neutropenia, achieving an area under the receiver operating characteristic curve of 0.8324. Importantly, a microorganism-based random forest model was established to predict patients at high risk of infection, yielding an area under the curve of 0.942. Nested cross-validation demonstrated high classification accuracy, correctly identifying 99.1% of patients who subsequently developed infections and 72.7% of patients who remained infection-free. Furthermore, integration of microbial features with clinical metrics improved predictive performance, resulting in an area under the curve of 0.953.
CONCLUSIONS: This microorganism-based prediction model provides an effective tool for infection risk stratification in patients with hematological conditions. By enabling early identification of high-risk individuals, the model has potential clinical utility for guiding precise preventive interventions and optimizing infection management strategies, which can significantly reduce the use of prophylactic antibiotics, thereby mitigating the development of resistance.
REGISTRATION NUMBER: ChiCTR2100042992.
METHODS: We developed a prediction model for infection risk stratification in newly diagnosed patients with hematological conditions. Plasma metagenomic next-generation sequencing was performed in a prospective cohort of 230 patients. Among them, 116 patients provided prechemotherapy, non-neutropenic plasma samples (cohort A), and 114 patients provided postchemotherapy, neutropenic samples (cohort B). Microbial community profiles were analyzed, and machine learning approaches were applied to construct classifiers for neutropenia status and subsequent infection risk.
RESULTS: Plasma metagenomic profiling revealed a complex microecological landscape in patients with hematological conditions and identified distinct microbial features associated with neutropenia. A trained random forest classifier successfully distinguished patients without neutropenia from patients with neutropenia, achieving an area under the receiver operating characteristic curve of 0.8324. Importantly, a microorganism-based random forest model was established to predict patients at high risk of infection, yielding an area under the curve of 0.942. Nested cross-validation demonstrated high classification accuracy, correctly identifying 99.1% of patients who subsequently developed infections and 72.7% of patients who remained infection-free. Furthermore, integration of microbial features with clinical metrics improved predictive performance, resulting in an area under the curve of 0.953.
CONCLUSIONS: This microorganism-based prediction model provides an effective tool for infection risk stratification in patients with hematological conditions. By enabling early identification of high-risk individuals, the model has potential clinical utility for guiding precise preventive interventions and optimizing infection management strategies, which can significantly reduce the use of prophylactic antibiotics, thereby mitigating the development of resistance.
REGISTRATION NUMBER: ChiCTR2100042992.