Prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings

Abstract Background An increase in the incidence of central venous catheter (CVC)-associated deep venous thrombosis (CADVT) has been reported in pediatric patients over the past decade. At the same time, current screening guidelines for venous thromboembolism risk have low sensitivity for CADVT in h...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Haomin Li, Yang Lu, Xian Zeng, Cangcang Fu, Huilong Duan, Qiang Shu, Jihua Zhu
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Central venous catheter Catheter-associated deep venous thrombosis Machine learning Prediction Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/c851a6d4aa6f4ec88e56154a7193dc32
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c851a6d4aa6f4ec88e56154a7193dc32
record_format	dspace
spelling	oai:doaj.org-article:c851a6d4aa6f4ec88e56154a7193dc322021-11-28T12:26:09ZPrediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings10.1186/s12911-021-01700-w1472-6947https://doaj.org/article/c851a6d4aa6f4ec88e56154a7193dc322021-11-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01700-whttps://doaj.org/toc/1472-6947Abstract Background An increase in the incidence of central venous catheter (CVC)-associated deep venous thrombosis (CADVT) has been reported in pediatric patients over the past decade. At the same time, current screening guidelines for venous thromboembolism risk have low sensitivity for CADVT in hospitalized children. This study utilized a multimodal deep learning model to predict CADVT before it occurs. Methods Children who were admitted to intensive care units (ICUs) between December 2015 and December 2018 and with CVC placement at least 3 days were included. The variables analyzed included demographic characteristics, clinical conditions, laboratory test results, vital signs and medications. A multimodal deep learning (MMDL) model that can handle temporal data using long short-term memory (LSTM) and gated recurrent units (GRUs) was proposed for this prediction task. Four benchmark machine learning models, logistic regression (LR), random forest (RF), gradient boosting decision tree (GBDT) and a published cutting edge MMDL, were used to compare and evaluate the models with a fivefold cross-validation approach. Accuracy, recall, area under the ROC curve (AUC), and average precision (AP) were used to evaluate the discrimination of each model at three time points (24 h, 48 h and 72 h) before CADVT occurred. Brier score and Spiegelhalter’s z test were used measure the calibration of these prediction models. Results A total of 1830 patients were included in this study, and approximately 15% developed CADVT. In the CADVT prediction task, the model proposed in this paper significantly outperforms both traditional machine learning models and existing multimodal deep learning models at all 3 time points. It achieved 77% accuracy and 90% recall at 24 h before CADVT was discovered. It can be used to accurately predict the occurrence of CADVT 72 h in advance with an accuracy of greater than 75%, a recall of more than 87%, and an AUC value of 0.82. Conclusion In this study, a machine learning method was successfully established to predict CADVT in advance. These findings demonstrate that artificial intelligence (AI) could provide measures for thromboprophylaxis in a pediatric intensive care setting.Haomin LiYang LuXian ZengCangcang FuHuilong DuanQiang ShuJihua ZhuBMCarticleCentral venous catheterCatheter-associated deep venous thrombosisMachine learningPredictionComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Central venous catheter Catheter-associated deep venous thrombosis Machine learning Prediction Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Central venous catheter Catheter-associated deep venous thrombosis Machine learning Prediction Computer applications to medicine. Medical informatics R858-859.7 Haomin Li Yang Lu Xian Zeng Cangcang Fu Huilong Duan Qiang Shu Jihua Zhu Prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings
description	Abstract Background An increase in the incidence of central venous catheter (CVC)-associated deep venous thrombosis (CADVT) has been reported in pediatric patients over the past decade. At the same time, current screening guidelines for venous thromboembolism risk have low sensitivity for CADVT in hospitalized children. This study utilized a multimodal deep learning model to predict CADVT before it occurs. Methods Children who were admitted to intensive care units (ICUs) between December 2015 and December 2018 and with CVC placement at least 3 days were included. The variables analyzed included demographic characteristics, clinical conditions, laboratory test results, vital signs and medications. A multimodal deep learning (MMDL) model that can handle temporal data using long short-term memory (LSTM) and gated recurrent units (GRUs) was proposed for this prediction task. Four benchmark machine learning models, logistic regression (LR), random forest (RF), gradient boosting decision tree (GBDT) and a published cutting edge MMDL, were used to compare and evaluate the models with a fivefold cross-validation approach. Accuracy, recall, area under the ROC curve (AUC), and average precision (AP) were used to evaluate the discrimination of each model at three time points (24 h, 48 h and 72 h) before CADVT occurred. Brier score and Spiegelhalter’s z test were used measure the calibration of these prediction models. Results A total of 1830 patients were included in this study, and approximately 15% developed CADVT. In the CADVT prediction task, the model proposed in this paper significantly outperforms both traditional machine learning models and existing multimodal deep learning models at all 3 time points. It achieved 77% accuracy and 90% recall at 24 h before CADVT was discovered. It can be used to accurately predict the occurrence of CADVT 72 h in advance with an accuracy of greater than 75%, a recall of more than 87%, and an AUC value of 0.82. Conclusion In this study, a machine learning method was successfully established to predict CADVT in advance. These findings demonstrate that artificial intelligence (AI) could provide measures for thromboprophylaxis in a pediatric intensive care setting.
format	article
author	Haomin Li Yang Lu Xian Zeng Cangcang Fu Huilong Duan Qiang Shu Jihua Zhu
author_facet	Haomin Li Yang Lu Xian Zeng Cangcang Fu Huilong Duan Qiang Shu Jihua Zhu
author_sort	Haomin Li
title	Prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings
title_short	Prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings
title_full	Prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings
title_fullStr	Prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings
title_full_unstemmed	Prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings
title_sort	prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings
publisher	BMC
publishDate	2021
url	https://doaj.org/article/c851a6d4aa6f4ec88e56154a7193dc32
work_keys_str_mv	AT haominli predictionofcentralvenouscatheterassociateddeepvenousthrombosisinpediatriccriticalcaresettings AT yanglu predictionofcentralvenouscatheterassociateddeepvenousthrombosisinpediatriccriticalcaresettings AT xianzeng predictionofcentralvenouscatheterassociateddeepvenousthrombosisinpediatriccriticalcaresettings AT cangcangfu predictionofcentralvenouscatheterassociateddeepvenousthrombosisinpediatriccriticalcaresettings AT huilongduan predictionofcentralvenouscatheterassociateddeepvenousthrombosisinpediatriccriticalcaresettings AT qiangshu predictionofcentralvenouscatheterassociateddeepvenousthrombosisinpediatriccriticalcaresettings AT jihuazhu predictionofcentralvenouscatheterassociateddeepvenousthrombosisinpediatriccriticalcaresettings
_version_	1718407982500282368

Prediction of central venous catheter-associated deep venous thrombosis in pediatric critical care settings

Ejemplares similares