Development of a clinical prediction model for recurrence and mortality outcomes after Clostridioides difficile infection using a machine learning approach.

Autor: Ruzicka D; Medical Affairs, MSD K.K., Tokyo, Japan, Kitanomaru Square, 1-13-12 Kudan-kita, Chiyoda-ku, Tokyo, 102-8667, Japan., Kondo T; Medical Affairs, MSD K.K., Tokyo, Japan, Kitanomaru Square, 1-13-12 Kudan-kita, Chiyoda-ku, Tokyo, 102-8667, Japan. Electronic address: takayuki.kondo@merck.com., Fujimoto G; Medical Affairs, MSD K.K., Tokyo, Japan, Kitanomaru Square, 1-13-12 Kudan-kita, Chiyoda-ku, Tokyo, 102-8667, Japan., Craig AP; Real World Evidence Solutions, IQVIA Solutions Japan K.K., Takanawa 4-10-18, Minato-ku, Tokyo, 108-0074, Japan., Kim SW; Real World Evidence Solutions, IQVIA Solutions Japan K.K., Takanawa 4-10-18, Minato-ku, Tokyo, 108-0074, Japan., Mikamo H; Department of Clinical Infectious Diseases, Aichi Medical University Graduate School of Medicine, 1-1, Yazakokarimata, Nagakute, Aichi, 480-1195, Japan.
Jazyk: angličtina
Zdroj: Anaerobe [Anaerobe] 2022 Oct; Vol. 77, pp. 102628. Date of Electronic Publication: 2022 Aug 17.
DOI: 10.1016/j.anaerobe.2022.102628
Abstrakt: Objectives: Clostridioides difficile infection (CDI) is associated with a large burden of morbidity and mortality worldwide. Previous studies have developed models for predicting recurrence and mortality following CDI, but no machine learning predictive models have been developed specifically using data from Japanese patients.
Methods: Using a database of records from acute care hospitals in Japan, we extracted records from January 2012 to September 2016 (plus a 60-day lookback window). A total of 19,159 patients were included. We used a machine learning approach, XGBoost, and compared it to a traditional unregularized logistic regression model. The first 80% of the dataset (by patient index date) was used to optimize model hyperparameters and train the final models, and evaluation was performed on the remaining 20%. We measured model performance by the area under the receiver operator curve and assessed feature importance using Shapley additive explanations.
Results: Performance was similar between the machine learning approach and the classical logistic regression model. Logistic regression performed slightly better than XGBoost for predicting mortality.
Conclusion: XGBoost performed slightly better than logistic regression for predicting recurrence, but it was not competitive with existing published models. Despite this, a future machine learning-based application provided in a bedside setting at low cost might be a clinically useful tool.
Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: D. Ruzicka, T. Kondo, G. Fujimoto, C. Andrew and SW. Kim have no potential conflicts of interest to declare. H. Mikamo received grant support from Asahi Kasei Pharma Corporation, Shionogi & Co. Ltd., Daiichi Sankyo Co., Ltd., Sumitomo Dainippon Pharma Co., Ltd.. and FUJIFILM Toyama Chemical Co., Ltd., payment for lectures from Astellas Pharma Inc., MSD K.K., Daiichi Sankyo Co., Ltd., Sumitomo Dainippon Pharma Co., Ltd., MIYARISAN Pharmaceutical Co., Ltd. Becton, Dickinson and Company Japan, and FUJIFILM Toyama Chemical Co. Ltd.
(Copyright © 2022 Merck Sharp & Dohme LLC., a subsidiary Merck & Co., Inc.,, The Author(s). Published by Elsevier Ltd.. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: