A two-stage modeling approach for predicting occurrence risk of non-time-varying outcome based on repeated measurement data_Chinese Journal of Evidence-Based Medicine

Authors：

JIA Yulong ^1,2,3 , REN Yan ^1,2,3 , WEI Wanqiang ^1,2,3 , XU Ye ^1,2,3 , LIU Chunrong ^1,2,3 , ZHAO Peng ^1,2,3 , LIU Xinghui ⁴ ,  SUN Xin ^1,2,3 ,  TAN Jing ^1,2,3

1. Chinese Evidence-based Medicine Center, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
2. NMPA Key Laboratory for Real World Data Research and Evaluation in Hainan, Chengdu 610041, P. R. China;
3. Sichuan Center of Technology Innovation for Real World Data, Chengdu 610041, P. R. China;
4. Department of Gynecology and Obstetrics, Key Laboratory of Obstetrics and Gynecologic and Pediatric Diseases and Birth Defects of Ministry of Education, West China Second University Hospital of Sichuan University, Chengdu 610041, P. R. China;

Corresponding author：

SUN Xin, Email: sunxin@wchscu.cn; TAN Jing, Email: tanjing84@outlook.com

Keywords：

Two-stage models; Repeated measurement data; Non-time-varying outcome; Severe postpartum hemorrhage

DOI：

10.7507/1672-2531.202406045

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

The use of repeated measurement data from patients to improve the classification ability of prediction models is a key methodological issue in the current development of clinical prediction models. This study aims to investigate the statistical modeling approach of the two-stage model in developing prediction models for non-time-varying outcomes using repeated measurement data. Using the prediction of the risk of severe postpartum hemorrhage as a case study, this study presents the implementation process of the two-stage model from various perspectives, including data structure, basic principles, software utilization, and model evaluation, to provide methodological support for clinical investigators.

Citation： JIA Yulong, REN Yan, WEI Wanqiang, XU Ye, LIU Chunrong, ZHAO Peng, LIU Xinghui, SUN Xin, TAN Jing. A two-stage modeling approach for predicting occurrence risk of non-time-varying outcome based on repeated measurement data. Chinese Journal of Evidence-Based Medicine, 2024, 24(11): 1360-1364. doi: 10.7507/1672-2531.202406045 Copy

1.	Tan J, Xiong Y, Qi Y, et al. Data resource profile: Xiamen registry of pregnant women and offspring (REPRESENT): a population-based, long-term follow-up database linking four major healthcare data platforms. Int J Epidemiol, 2021, 50(1): 27-28.
2.	张沂洁, 朱燕, 陈超. 早产儿发生率及变化趋势. 中华新生儿科杂志, 2021, 36(4): 74-77.
3.	中华医学会妇产科学分会产科学组, 中华医学会围产医学分会. 产后出血预防与处理指南(2023). 中华妇产科杂志, 2023, 58(6): 401-409.
4.	沈忠周, 王雅文, 马帅, 等. 新生儿早产、低出生体重及小于胎龄的危险因素. 中华流行病学杂志, 2019, 40(9): 1125-1129.
5.	Welten M, de Kroon MLA, Renders CM, et al. Repeatedly measured predictors: a comparison of methods for prediction modeling. Diagn Progn Res, 2018, 2: 5.
6.	Maruyama N, Takahashi F, Takeuchi M. Prediction of an outcome using trajectories estimated from a linear mixed model. J Biopharm Stat, 2009, 19(5): 779-790.
7.	Chen YH, Ferguson KK, Meeker JD, et al. Statistical methods for modeling repeated measures of maternal environmental exposure biomarkers during pregnancy in association with preterm birth. Environ Health, 2015, 14: 9.
8.	Bull LM, Lunt M, Martin GP, et al. Harnessing repeated measurements of predictor variables for clinical risk prediction: a review of existing methods. Diagn Progn Res, 2020, 4: 9.
9.	冯国双. 观察性研究中的logistic回归分析思路. 中华流行病学杂志, 2019, 40(8): 1006-1009.
10.	Galwey NW. Introduction to mixed modelling: beyond regression and analysis of variance. New York: John Wiley & Sons, 2014.
11.	杨珉, 张菊英. 多水平统计模型及其在预防和临床医学中的应用. 北京: 中国统计出版社, 2023.
12.	Tu YK, Tilling K, Sterne JA, et al. A critical evaluation of statistical approaches to examining the role of growth trajectories in the developmental origins of health and disease. Int J Epidemiol, 2013, 42(5): 1327-1339.
13.	Albert PS. A linear mixed model for predicting a binary event from longitudinal data under random effects misspecification. Stat Med, 2012, 31(2): 143-154.
14.	石慧峰, 陈练, 王晓霞, 等. 2016-2019年中国严重产后出血的流行病学现状和变化趋势. 中华妇产科杂志, 2021, 56(7): 451-457.
15.	Pettersen S, Falk RS, Vangen S, et al. Exploring trends of severe postpartum haemorrhage: a hospital-based study. BMC Pregnancy Childbirth, 2023, 23(1): 363.
16.	Wang S, Dai Y, Shen J, et al. Research on expansion and classification of imbalanced data based on SMOTE algorithm. Sci Rep, 2021, 11(1): 24039.
17.	Khalilia M, Chakraborty S, Popescu M. Predicting disease risks from highly imbalanced data using random forest. BMC Med Inform Decis Mak, 2011, 11: 51.
18.	Chen X, Chen H, Nan S, et al. Dealing with missing, imbalanced, and sparse features during the development of a prediction model for sudden death using emergency medicine data: machine learning approach. JMIR Med Inform, 2023, 11: e38590.
19.	van den Goorbergh R, van Smeden M, Timmerman D, et al. The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression. J Am Med Inform Assoc, 2022, 29(9): 1525-1534.

1. Tan J, Xiong Y, Qi Y, et al. Data resource profile: Xiamen registry of pregnant women and offspring (REPRESENT): a population-based, long-term follow-up database linking four major healthcare data platforms. Int J Epidemiol, 2021, 50(1): 27-28.
2. 张沂洁, 朱燕, 陈超. 早产儿发生率及变化趋势. 中华新生儿科杂志, 2021, 36(4): 74-77.
3. 中华医学会妇产科学分会产科学组, 中华医学会围产医学分会. 产后出血预防与处理指南(2023). 中华妇产科杂志, 2023, 58(6): 401-409.
4. 沈忠周, 王雅文, 马帅, 等. 新生儿早产、低出生体重及小于胎龄的危险因素. 中华流行病学杂志, 2019, 40(9): 1125-1129.
5. Welten M, de Kroon MLA, Renders CM, et al. Repeatedly measured predictors: a comparison of methods for prediction modeling. Diagn Progn Res, 2018, 2: 5.
6. Maruyama N, Takahashi F, Takeuchi M. Prediction of an outcome using trajectories estimated from a linear mixed model. J Biopharm Stat, 2009, 19(5): 779-790.
7. Chen YH, Ferguson KK, Meeker JD, et al. Statistical methods for modeling repeated measures of maternal environmental exposure biomarkers during pregnancy in association with preterm birth. Environ Health, 2015, 14: 9.
8. Bull LM, Lunt M, Martin GP, et al. Harnessing repeated measurements of predictor variables for clinical risk prediction: a review of existing methods. Diagn Progn Res, 2020, 4: 9.
9. 冯国双. 观察性研究中的logistic回归分析思路. 中华流行病学杂志, 2019, 40(8): 1006-1009.
10. Galwey NW. Introduction to mixed modelling: beyond regression and analysis of variance. New York: John Wiley & Sons, 2014.
11. 杨珉, 张菊英. 多水平统计模型及其在预防和临床医学中的应用. 北京: 中国统计出版社, 2023.
12. Tu YK, Tilling K, Sterne JA, et al. A critical evaluation of statistical approaches to examining the role of growth trajectories in the developmental origins of health and disease. Int J Epidemiol, 2013, 42(5): 1327-1339.
13. Albert PS. A linear mixed model for predicting a binary event from longitudinal data under random effects misspecification. Stat Med, 2012, 31(2): 143-154.
14. 石慧峰, 陈练, 王晓霞, 等. 2016-2019年中国严重产后出血的流行病学现状和变化趋势. 中华妇产科杂志, 2021, 56(7): 451-457.
15. Pettersen S, Falk RS, Vangen S, et al. Exploring trends of severe postpartum haemorrhage: a hospital-based study. BMC Pregnancy Childbirth, 2023, 23(1): 363.
16. Wang S, Dai Y, Shen J, et al. Research on expansion and classification of imbalanced data based on SMOTE algorithm. Sci Rep, 2021, 11(1): 24039.
17. Khalilia M, Chakraborty S, Popescu M. Predicting disease risks from highly imbalanced data using random forest. BMC Med Inform Decis Mak, 2011, 11: 51.
18. Chen X, Chen H, Nan S, et al. Dealing with missing, imbalanced, and sparse features during the development of a prediction model for sudden death using emergency medicine data: machine learning approach. JMIR Med Inform, 2023, 11: e38590.
19. van den Goorbergh R, van Smeden M, Timmerman D, et al. The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression. J Am Med Inform Assoc, 2022, 29(9): 1525-1534.

Previous Article
Application of Mendelian randomization analysis in cancer prevention and treatment research

Chinese Journal of Evidence-Based Medicine

A two-stage modeling approach for predicting occurrence risk of non-time-varying outcome based on repeated measurement data

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Format

Content