Prediction of unsuccessful endometrial ablation: random forest vs logistic regression
Open Access
- 29 June 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in Gynecological Surgery
- Vol. 18 (1), 1-9
- https://doi.org/10.1186/s10397-021-01097-4
Abstract
Background Five percent of pre-menopausal women experience abnormal uterine bleeding. Endometrial ablation (EA) is one of the treatment options for this common problem. However, this technique shows a decrease in patient satisfaction and treatment efficacy on the long term. Study objective To develop a prediction model to predict surgical re-intervention (for example re-ablation or hysterectomy) within 2 years after endometrial ablation (EA) by using machine learning (ML). The performance of the developed prediction model was compared with a previously published multivariate logistic regression model (LR). Design This retrospective cohort study, with a minimal follow-up time of 2 years, included 446 pre-menopausal women (18+) that underwent an EA for complaints of heavy menstrual bleeding. The performance of the ML and the LR model was compared using the area under the receiving operating characteristic (ROC) curve. Results We found out that the ML model (AUC of 0.65 (95% CI 0.56–0.74)) is not superior compared to the LR model (AUC of 0.71 (95% CI 0.64–0.78)) in predicting the outcome of surgical re-intervention within 2 years after EA. Based on the ML model, dysmenorrhea and duration of menstruation have the highest impact on the surgical re-intervention rate. Conclusion Although machine learning techniques are gaining popularity in development of clinical prediction tools, this study shows that ML is not necessarily superior to the traditional statistical LR techniques. Both techniques should be considered when developing a clinical prediction model. Both models can identify the clinical predictors to surgical re-intervention and contribute to the shared decision-making process in the clinical practice.Keywords
This publication has 40 references indexed in Scilit:
- Endometrial Ablation: Is Tubal Ligation a Risk Factor for HysterectomyJournal of Minimally Invasive Gynecology, 2013
- Predicting Pelvic Pain After Endometrial Ablation: Which Preoperative Patient Characteristics Are Associated?Journal of Minimally Invasive Gynecology, 2013
- Hysterectomy Subsequent to Endometrial AblationJournal of Minimally Invasive Gynecology, 2012
- Five-Year Follow-Up After Comparing Bipolar Endometrial Ablation With Hydrothermablation for MenorrhagiaObstetrics & Gynecology, 2011
- A randomised comparison of microwave endometrial ablation with transcervical resection of the endometrium: follow up at a minimum of 10 yearsBJOG: An International Journal of Obstetrics and Gynaecology, 2009
- Probability of Hysterectomy After Endometrial AblationObstetrics & Gynecology, 2008
- Prediction of successful menorrhagia treatment after thermal balloon endometrial ablationJournal of Obstetrics and Gynaecology Research, 2004
- Internal validation of predictive models: Efficiency of some procedures for logistic regression analysisJournal of Clinical Epidemiology, 2001
- Prognostic modelling with logistic regression analysis: a comparison of selection and estimation methods in small data setsStatistics in Medicine, 2000
- Stepwise Selection in Small Data Sets A Simulation Study of Bias in Logistic Regression AnalysisJournal of Clinical Epidemiology, 1999