AUTHOR=Cao Mingzhu , Liu Zhi , Lin Yanshan , Luo Yiqun , Li Sichen , Huang Qing , Liu Haiying , Liu Jianqiao TITLE=A Personalized Management Approach of OHSS: Development of a Multiphase Prediction Model and Smartphone-Based App JOURNAL=Frontiers in Endocrinology VOLUME=Volume 13 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2022.911225 DOI=10.3389/fendo.2022.911225 ISSN=1664-2392 ABSTRACT=Objective: This study aimed to develop multi-phase big-data-based prediction models of ovarian hyper-stimulation syndrome (OHSS), and a smartphone app for risk calculation and patients’ self-monitoring. Methods: Multi-phase prediction models were developed from a retrospective cohort database of 21566 women from January 2017 to December 2020 with controlled ovarian stimulation (COS). There were 17445 women included in the final data analysis. Women were randomly assigned to either training cohort (n=12211) or validation cohort (n=5234). Their baseline clinical characteristics, COS related characteristics and embryo information were evaluated. The prediction models were divided into 4 phase, 1) prior to COS, 2) on the day of ovulation trigger, 3) after oocytes retrieval, and 4) prior to embryo transfer. The multi-phase prediction models were built with stepwise regression, and confirmed with LASSO regression. Internal validations were performed using validation cohort and were assessed by discrimination and calibration, as well clinical decision curves. A smart-phone based app “OHSS monitor” was constructed as part of the build-in app of IVF-aid platform. The app had three modules, risk prediction module, symptom monitoring module and treatment monitoring module. Results: The multi-phase prediction models were developed with acceptable distinguishing ability to identify OHSS at-risk patients. C-statistics of the 1st, 2nd, 3rd and the 4th phase in the training cohort were 0.628 (95% CI 0.598-0.658), 0.715 (95% CI 0.688-0.742), 0.792 (95% CI 0.770-0.815), 0.814 (95% CI 0.793-0.834), respectively. Calibration plot showed the agreement of predictive and observed risk of OHSS, especially at the 3rd and 4th phase prediction models in both training and validation cohorts. The net clinical benefits of the multi-phase prediction models were also confirmed with clinical decision curve. A smartphone-based app was constructed as a risk calculator based on the multi-phase prediction models, and also as a self-monitoring tool for patients at risk. Conclusions: We have built multi-phase prediction models based on big-data, and constructed a user-friendly smartphone-based app for the personalized management of women at-risk of moderate/severe OHSS. The multi-phase prediction models and user-friendly app can be readily used in clinical practice for clinical decision-support and self-management of patients.