Prediction of Endometrial Carcinoma Using the Combination of Electronic Health Records and an Ensemble Machine Learning Method

Wenwen Wang; Yang Xu; Suzhen Yuan; Zhiying Li; Xin Zhu; Qin Zhou; Wenfeng Shen; Shixuan Wang

doi:10.3389/fmed.2022.851890

Prediction of Endometrial Carcinoma Using the Combination of Electronic Health Records and an Ensemble Machine Learning Method

Front Med (Lausanne). 2022 Mar 4:9:851890. doi: 10.3389/fmed.2022.851890. eCollection 2022.

Authors

Wenwen Wang¹, Yang Xu², Suzhen Yuan¹, Zhiying Li³, Xin Zhu⁴, Qin Zhou¹, Wenfeng Shen², Shixuan Wang¹

Affiliations

¹ Department of Obstetrics and Gynecology, Tongji Medical College, Tongji Hospital, Huazhong University of Science and Technology, Wuhan, China.
² School of Computer Engineering and Science, Shanghai University, Shanghai, China.
³ Department of Obstetrics and Gynecology, Affiliated Renhe Hospital of China Three Gorges University, Yichang, China.
⁴ Biomedical Information Engineering Lab, The University of Aizu, Fukushima, Japan.

Abstract

Endometrial carcinoma (EC) is a common cause of cancer death in women, and having an early accurate prediction model to identify this disease is crucial. The aim of this study was to develop a new machine learning (ML) model-based diagnostic prediction model for EC. We collected data from consecutive patients between November 2012 and January 2021 at tertiary hospitals in central China. Inclusion criteria included women undergoing endometrial biopsy, dilation and curettage, or hysterectomy. A total of 9 features, including patient demographics, vital signs, and laboratory and ultrasound results, were selected in the final analysis. This new model was combined with three top optimal ML methods, namely, logistic regression, gradient-boosted decision tree, and random forest. A total of 1,922 patients were eligible for final analysis and modeling. The ensemble model, called TJHPEC, was validated in an internal validation cohort and two external validation cohorts. The results showed that the AUC values were 0.9346, 0.8341, and 0.8649 for the prediction of total EC and 0.9347, 0.8073, and 0.871 for prediction of stage I EC. Nine clinical features were confirmed to be highly related to the prediction of EC in TJHPEC. In conclusion, our new model may be accurate for identifying EC, especially in the early stage, in the general population of central China.

Keywords: endometrial carcinoma (EC); ensemble method; machine learning; model; prediction.