Objective:To predict suicidal behaviors in patients with bipolar disorder by constructing a machine learning model based on random forest and backpropagation neural network, and provide clinical decision support for the prevention and intervention of patient suicide.Methods:From January 2020 to August 2023, 1 005 patients with bipolar disorder were enrolled.The general clinical data and social dysfunction, anxiety, depression scores of all patients were collected.The random forest algorithm was applied for feature selection, and backpropagation neural network model was constructed for evaluating the model's fitting effect and predictive performance.Results:There were statistically significant differences in sociodemographic characteristics and physiological and psychological factors among the suicide attempt group ( n=293), suicide ideation group ( n=332) and non-suicidal group ( n=380) of patients with bipolar disorder( P<0.05).Using the random forest algorithm identified six main predictive variables: educational level, age, free triiodothyronine (FT3), cognitive impairment, hopelessness and psychogenic anxiety.The developed backpropagation neural network model achieved a precision rate of 79.3%, a recall rate of 79.6%, an F1 score of 79.4%, and an AUC of 0.89 on the test set, indicating that the model predictive performance has high accuracy and discriminative power. Conclusion:This study developed a machine learning model for predicting suicide in patients with bipolar disorder, which possesses high accuracy and discriminative ability, providing a decision-making basis for the prevention and intervention of suicidal behaviors in patients with bipolar disorder.

Objective:To predict suicidal behaviors in patients with bipolar disorder by constructing a machine learning model based on random forest and backpropagation neural network, and provide clinical decision support for the prevention and intervention of patient suicide.Methods:From January 2020 to August 2023, 1 005 patients with bipolar disorder were enrolled.The general clinical data and social dysfunction, anxiety, depression scores of all patients were collected.The random forest algorithm was applied for feature selection, and backpropagation neural network model was constructed for evaluating the model's fitting effect and predictive performance.Results:There were statistically significant differences in sociodemographic characteristics and physiological and psychological factors among the suicide attempt group ( n=293), suicide ideation group ( n=332) and non-suicidal group ( n=380) of patients with bipolar disorder( P<0.05).Using the random forest algorithm identified six main predictive variables: educational level, age, free triiodothyronine (FT3), cognitive impairment, hopelessness and psychogenic anxiety.The developed backpropagation neural network model achieved a precision rate of 79.3%, a recall rate of 79.6%, an F1 score of 79.4%, and an AUC of 0.89 on the test set, indicating that the model predictive performance has high accuracy and discriminative power. Conclusion:This study developed a machine learning model for predicting suicide in patients with bipolar disorder, which possesses high accuracy and discriminative ability, providing a decision-making basis for the prevention and intervention of suicidal behaviors in patients with bipolar disorder.

Objective To survey the prevalence of Hyperuricemia (HUA) in elder population of Changchun city,and to detect the correlation between cardiovascular risk factors and the HUA.Methods 900 residents older than 55 years were selected randomly for this questionnaire survey.Physical and laboratory examinations were performed.Results The HUA prevalence rate elder people in Xixin District of Changchun was 16.0％(144/900),while the rates were 13.7％(50/365),15.2％(47/309) and 20.8％(47/226) (P＜0.05) in the elder group (55-65 years),the aged group (66-75 years),and the advanced aged group (older than 76 years) respectively;there was no statistical significant difference in the prevalences between male and female (x2=0.023 5,P＞0.05).The HUA prevalence rate was significantly different between people who had different level of blood pressure,cholesterol,hypersensitive C-reactive protein (hs-CRP),body mass index (BMI),waisthip ratio (WHR).The level of uric acid (UA),total cholesterol (TC) and hs-CRP was significantly different in people with high uric acid when compared with those of normal patients (P＜0.05).There was positive correlation between UA level and TC,triglyceride (TG) level (r=0.364,P＜0.05;r=0.479,P＜0.05).Conclusion The HUA prevalence rate increases significantly as people getting older.There is positive correlation between the increase of uric acid level and the major cardiovascular risk factor.People with hypertension,hyperlipidemia,overweight and obese have high risk for HUA,so change life style and dietary habits may prevent or reduce the occurrence of HUA.