Cargando…

Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study

Hospital acquired thrombocytopenia (HAT) is a common hematological complication after surgery. This research aimed to develop and compare the performance of seven machine learning (ML) algorithms for predicting patients that are at risk of HAT after surgery. We conducted a retrospective cohort study...

Descripción completa

Detalles Bibliográficos
Autores principales: Cheng, Yisong, Chen, Chaoyue, Yang, Jie, Yang, Hao, Fu, Min, Zhong, Xi, Wang, Bo, He, Min, Hu, Zhi, Zhang, Zhongwei, Jin, Xiaodong, Kang, Yan, Wu, Qin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8466367/
https://www.ncbi.nlm.nih.gov/pubmed/34573956
http://dx.doi.org/10.3390/diagnostics11091614
_version_ 1784573119185289216
author Cheng, Yisong
Chen, Chaoyue
Yang, Jie
Yang, Hao
Fu, Min
Zhong, Xi
Wang, Bo
He, Min
Hu, Zhi
Zhang, Zhongwei
Jin, Xiaodong
Kang, Yan
Wu, Qin
author_facet Cheng, Yisong
Chen, Chaoyue
Yang, Jie
Yang, Hao
Fu, Min
Zhong, Xi
Wang, Bo
He, Min
Hu, Zhi
Zhang, Zhongwei
Jin, Xiaodong
Kang, Yan
Wu, Qin
author_sort Cheng, Yisong
collection PubMed
description Hospital acquired thrombocytopenia (HAT) is a common hematological complication after surgery. This research aimed to develop and compare the performance of seven machine learning (ML) algorithms for predicting patients that are at risk of HAT after surgery. We conducted a retrospective cohort study which enrolled adult patients transferred to the intensive care unit (ICU) after surgery in West China Hospital of Sichuan University from January 2016 to December 2018. All subjects were randomly divided into a derivation set (70%) and test set (30%). ten-fold cross-validation was used to estimate the hyperparameters of ML algorithms during the training process in the derivation set. After ML models were developed, the sensitivity, specificity, area under the curve (AUC), and net benefit (decision analysis curve, DCA) were calculated to evaluate the performances of ML models in the test set. A total of 10,369 patients were included and in 1354 (13.1%) HAT occurred. The AUC of all seven ML models exceeded 0.7, the two highest were Gradient Boosting (GB) (0.834, 0.814–0.853, p < 0.001) and Random Forest (RF) (0.828, 0.807–0.848, p < 0.001). There was no difference between GB and RF (0.834 vs. 0.828, p = 0.293); however, these two were better than the remaining five models (p < 0.001). The DCA revealed that all ML models had high net benefits with a threshold probability approximately less than 0.6. In conclusion, we found that ML models constructed by multiple preoperative variables can predict HAT in patients transferred to ICU after surgery, which can improve risk stratification and guide management in clinical practice.
format Online
Article
Text
id pubmed-8466367
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-84663672021-09-27 Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study Cheng, Yisong Chen, Chaoyue Yang, Jie Yang, Hao Fu, Min Zhong, Xi Wang, Bo He, Min Hu, Zhi Zhang, Zhongwei Jin, Xiaodong Kang, Yan Wu, Qin Diagnostics (Basel) Article Hospital acquired thrombocytopenia (HAT) is a common hematological complication after surgery. This research aimed to develop and compare the performance of seven machine learning (ML) algorithms for predicting patients that are at risk of HAT after surgery. We conducted a retrospective cohort study which enrolled adult patients transferred to the intensive care unit (ICU) after surgery in West China Hospital of Sichuan University from January 2016 to December 2018. All subjects were randomly divided into a derivation set (70%) and test set (30%). ten-fold cross-validation was used to estimate the hyperparameters of ML algorithms during the training process in the derivation set. After ML models were developed, the sensitivity, specificity, area under the curve (AUC), and net benefit (decision analysis curve, DCA) were calculated to evaluate the performances of ML models in the test set. A total of 10,369 patients were included and in 1354 (13.1%) HAT occurred. The AUC of all seven ML models exceeded 0.7, the two highest were Gradient Boosting (GB) (0.834, 0.814–0.853, p < 0.001) and Random Forest (RF) (0.828, 0.807–0.848, p < 0.001). There was no difference between GB and RF (0.834 vs. 0.828, p = 0.293); however, these two were better than the remaining five models (p < 0.001). The DCA revealed that all ML models had high net benefits with a threshold probability approximately less than 0.6. In conclusion, we found that ML models constructed by multiple preoperative variables can predict HAT in patients transferred to ICU after surgery, which can improve risk stratification and guide management in clinical practice. MDPI 2021-09-03 /pmc/articles/PMC8466367/ /pubmed/34573956 http://dx.doi.org/10.3390/diagnostics11091614 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Cheng, Yisong
Chen, Chaoyue
Yang, Jie
Yang, Hao
Fu, Min
Zhong, Xi
Wang, Bo
He, Min
Hu, Zhi
Zhang, Zhongwei
Jin, Xiaodong
Kang, Yan
Wu, Qin
Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study
title Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study
title_full Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study
title_fullStr Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study
title_full_unstemmed Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study
title_short Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study
title_sort using machine learning algorithms to predict hospital acquired thrombocytopenia after operation in the intensive care unit: a retrospective cohort study
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8466367/
https://www.ncbi.nlm.nih.gov/pubmed/34573956
http://dx.doi.org/10.3390/diagnostics11091614
work_keys_str_mv AT chengyisong usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT chenchaoyue usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT yangjie usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT yanghao usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT fumin usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT zhongxi usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT wangbo usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT hemin usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT huzhi usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT zhangzhongwei usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT jinxiaodong usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT kangyan usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy
AT wuqin usingmachinelearningalgorithmstopredicthospitalacquiredthrombocytopeniaafteroperationintheintensivecareunitaretrospectivecohortstudy