Frontiers in public health · 2026
Prediction of depressive symptoms in middle-aged and older adult hospitalized patients with chronic diseases: a multicenter study in Anhui, China using machine learning methods.
СтатьяМногоцентровое 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.
Huang Shouqiang, Liu Huan, Liu Qingwei, Hu Xinyu, Qin Xu, Mei Guangliang, Wang Xiaoli, Gu Shijia, Hong Rui, Pan Lingling, Zhang Ming, Tao Mingfen
Аннотация
OBJECTIVE: This cross-sectional study has dual objectives: to investigate the predictive value of machine learning (ML) for the prevalence of depressive symptoms in middle-aged and older adult hospitalized patients with chronic diseases, and to identify significant factors influencing depressive symptoms in this population.
METHODS: A cross-sectional study was conducted among 618 hospitalized middle-aged and older adult patients with chronic diseases. Participants completed questionnaires assessing depression, chronic illness stigma, oral frailty, social isolation, family health, and demographic characteristics. The XG Boost model algorithm was employed for feature selection and variable importance ranking. A predictive model was constructed to assess the risk of depressive symptoms, and the feature importance honeycomb plot was utilized to illustrate the relationships between variables and prediction outcomes.
RESULTS: The study found multiple risk factors significantly associated with depression, including gender, place of residence, number of surgeries in the past year, hospitalization in the past 2 years, social isolation, level of education, comorbidity, age, malignant disease, oral frailty, stigma associated with illness, and family health. The XG Boost model demonstrated optimal predictive performance, achieving an AUC value of 0.931. Key predictive factors included stigma scale for chronic, family health, oral frailty, social isolation, malignant disease, and hospitalization in the past 2 years.
CONCLUSION: This study constructed a risk prediction model for depressive symptoms in middle-aged and older adult hospitalized patients with chronic diseases, providing an important reference basis for mental health interventions in this population.
METHODS: A cross-sectional study was conducted among 618 hospitalized middle-aged and older adult patients with chronic diseases. Participants completed questionnaires assessing depression, chronic illness stigma, oral frailty, social isolation, family health, and demographic characteristics. The XG Boost model algorithm was employed for feature selection and variable importance ranking. A predictive model was constructed to assess the risk of depressive symptoms, and the feature importance honeycomb plot was utilized to illustrate the relationships between variables and prediction outcomes.
RESULTS: The study found multiple risk factors significantly associated with depression, including gender, place of residence, number of surgeries in the past year, hospitalization in the past 2 years, social isolation, level of education, comorbidity, age, malignant disease, oral frailty, stigma associated with illness, and family health. The XG Boost model demonstrated optimal predictive performance, achieving an AUC value of 0.931. Key predictive factors included stigma scale for chronic, family health, oral frailty, social isolation, malignant disease, and hospitalization in the past 2 years.
CONCLUSION: This study constructed a risk prediction model for depressive symptoms in middle-aged and older adult hospitalized patients with chronic diseases, providing an important reference basis for mental health interventions in this population.