Construction and validation of a hyperuricemia risk prediction model for the helicopter pilots stationed in plateau
10.3760/cma.j.cn113854-20231124-00121
- VernacularTitle:高海拔地区直升机飞行员高尿酸血症风险预测模型的构建与验证
- Author:
He ZHANG
1
;
Jun LIU
;
Chenjie ZHOU
;
Weifang WANG
;
Zhiying LUO
Author Information
1. 空军杭州特勤疗养中心疗养三区疗养一科，杭州 310000
- Publication Type:Journal Article
- Keywords:
Altitude;
Hyperuricemia;
Prediction model;
Helicopter;
Pilots
- From:
Chinese Journal of Aerospace Medicine
2024;35(3):198-204
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To establish a model for predicting the risk of hyperuricemia in helicopter pilots stationed in plateau and to verify the application effect of the model.Methods:By using a convenience sampling method, 409 pilots who recuperated in Air Force Healthcare Center for Special Services Hangzhou from August of 2017 to March of 2023 were selected as the subjects, and a retrospective analysis was conducted on the relevant data. They were randomly divided into modeling group (286 cases) and validation group (123 cases) with the ratio of 7∶3. Lasso regression and Logistic regression analysis were used in screening out the influencing factors of hyperuricemia for the helicopter pilots stationed in plateau. R software was used to construct risk prediction model and column chart model. The prediction effect of the model was tested using the area under the operating characteristic curve of the subjects.Results:TG, ALT, exercise intensity were the influencing factors of hyperuricemia in altitude helicopter pilots ( Z=2.62, 2.68, -3.02, P=0.009, 0.007, 0.003). Based on the above 3 influencing factors, a risk prediction model and a column chart model were constructed, and the receiver operating characteristic curve was drawn. The results showed that the area under the curve (AUC) of the modeling group was 0.758,95% CI was 0.696-0.820. The Yoden index was 0.331, the sensitivity was 76.5%, and the specificity was 56.6%. The AUC of the validation group was 0.747, 95% CI was 0.655-0.840. The Yoden index was 0.642, the sensitivity was 68.6%, and the specificity was 85.2%,respectively, those suggested good predictive result. The calibration curve showed that the model performed well in predicting compliance, and the clinical decision curve analysis showed that the model performed well in clinical efficacy. Conclusions:The prediction model constructed in this study has good discrimination and calibration, and can help medical staff to screen out high-risk populations of the helicopter pilots with hyperuricemia, and take targeted intervention measures.
