Development and validation of a machine learning-based model for post-sepsis frailty
| Autor: | Hye Ju Yeo, Dasom Noh, Tae Hwa Kim, Jin Ho Jang, Young Seok Lee, Sunghoon Park, Jae Young Moon, Kyeongman Jeon, Dong Kyu Oh, Su Yeon Lee, Mi Hyeon Park, Chae-Man Lim, Woo Hyun Cho, Sunyoung Kwon, on behalf of the Korean Sepsis Alliance investigators, Sang-Bum Hong, Gee Young Suh, Ryoung-Eun Ko, Young-Jae Cho, Yeon Joo Lee, Sung Yoon Lim, Jeongwon Heo, Jae-Myeong Lee, Kyung Chan Kim, Youjin Chang, Sang-Min Lee, Suk-Kyung Hong, Sang Hyun Kwak, Heung Bum Lee, Jong-Joon Ahn, Gil Myeong Seong, Song-I Lee, Tai Sun Park, Su Hwan Lee, Eun Young Choi, Hyung Koo Kang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2024 |
| Předmět: | |
| Zdroj: | ERJ Open Research, Vol 10, Iss 5 (2024) |
| Druh dokumentu: | article |
| ISSN: | 2312-0541 23120541 |
| DOI: | 10.1183/23120541.00166-2024 |
| Popis: | Background The development of post-sepsis frailty is a common and significant problem, but it is a challenge to predict. Methods Data for deep learning were extracted from a national multicentre prospective observational cohort of patients with sepsis in Korea between September 2019 and December 2021. The primary outcome was frailty at survival discharge, defined as a clinical frailty score on the Clinical Frailty Scale ≥5. We developed a deep learning model for predicting frailty after sepsis by 10 variables routinely collected at the recognition of sepsis. With cross-validation, we trained and tuned six machine learning models, including four conventional and two neural network models. Moreover, we computed the importance of each predictor variable in the model. We measured the performance of these models using a temporal validation data set. Results A total of 8518 patients were included in the analysis; 5463 (64.1%) were frail, and 3055 (35.9%) were non-frail at discharge. The Extreme Gradient Boosting (XGB) achieved the highest area under the receiver operating characteristic curve (AUC) (0.8175) and accuracy (0.7414). To confirm the generalisation performance of artificial intelligence in predicting frailty at discharge, we conducted external validation with the COVID-19 data set. The XGB still showed a good performance with an AUC of 0.7668. The machine learning model could predict frailty despite the disparity in data distribution. Conclusion The machine learning-based model developed for predicting frailty after sepsis achieved high performance with limited baseline clinical parameters. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|