A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields

Abstract Background The misestimation of surgical risk is a serious threat to the lives of patients when implementing surgical risk calculator. Improving the accuracy of postoperative risk prediction has received much attention and many methods have been proposed to cope with this problem in the pas...

Full description

Bibliographic Details
Main Authors: Ruoyu Liu, Xin Lai, Jiayin Wang, Xuanping Zhang, Xiaoyan Zhu, Paul B. S. Lai, Ci-ren Guo
Format: Article
Language:English
Published: BMC 2021-07-01
Series:BMC Medical Informatics and Decision Making
Subjects:
Online Access:https://doi.org/10.1186/s12911-021-01450-9
id doaj-4065772053c448d2ad35ec3d471bf4ae
record_format Article
spelling doaj-4065772053c448d2ad35ec3d471bf4ae2021-08-01T11:32:12ZengBMCBMC Medical Informatics and Decision Making1472-69472021-07-0121S211910.1186/s12911-021-01450-9A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fieldsRuoyu Liu0Xin Lai1Jiayin Wang2Xuanping Zhang3Xiaoyan Zhu4Paul B. S. Lai5Ci-ren Guo6School of Computer Science and Technology, Xi’an Jiaotong UniversitySchool of Computer Science and Technology, Xi’an Jiaotong UniversitySchool of Computer Science and Technology, Xi’an Jiaotong UniversitySchool of Computer Science and Technology, Xi’an Jiaotong UniversitySchool of Computer Science and Technology, Xi’an Jiaotong UniversityDepartment of Surgery, The Chinese University of Hong KongDepartment of Tumor Gynecology, Fujian Medical University Cancer Hospital and Fujian Cancer HospitalAbstract Background The misestimation of surgical risk is a serious threat to the lives of patients when implementing surgical risk calculator. Improving the accuracy of postoperative risk prediction has received much attention and many methods have been proposed to cope with this problem in the past decades. However, those linear approaches are inable to capture the non-linear interactions between risk factors, which have been proved to play an important role in the complex physiology of the human body, and thus may attenuate the performance of surgical risk calculators. Methods In this paper, we presented a new surgical risk calculator based on a non-linear ensemble algorithm named Gradient Boosting Decision Tree (GBDT) model, and explored the corresponding pipeline to support it. In order to improve the practicability of our approach, we designed three different modes to deal with different data situations. Meanwhile, considering that one of the obstacles to clinical acceptance of surgical risk calculators was that the model was too complex to be used in practice, we reduced the number of input risk factors according to the importance of them in GBDT. In addition, we also built some baseline models and similar models to compare with our approach. Results The data we used was three-year clinical data from Surgical Outcome Monitoring and Improvement Program (SOMIP) launched by the Hospital Authority of Hong Kong. In all experiments our approach shows excellent performance, among which the best result of area under curve (AUC), Hosmer–Lemeshow test ( $${{\mathrm{HL}}}_{\hat{c}}$$ HL c ^ ) and brier score (BS) can reach 0.902, 7.398 and 0.047 respectively. After feature reduction, the best result of AUC, $${\mathrm{HL}}_{\hat{c}}$$ HL c ^ and BS of our approach can still be maintained at 0.894, 7.638 and 0.060, respectively. In addition, we also performed multiple groups of comparative experiments. The results show that our approach has a stable advantage in each evaluation indicator. Conclusions The experimental results demonstrate that NL-SRC can not only improve the accuracy of predicting the surgical risk of patients, but also effectively capture important risk factors and their interactions. Meanwhile, it also has excellent performance on the mixed data from multiple surgical fields.https://doi.org/10.1186/s12911-021-01450-9Surgical risk calculatorGradient boosting decision treeMachine learningClinical decision support system
collection DOAJ
language English
format Article
sources DOAJ
author Ruoyu Liu
Xin Lai
Jiayin Wang
Xuanping Zhang
Xiaoyan Zhu
Paul B. S. Lai
Ci-ren Guo
spellingShingle Ruoyu Liu
Xin Lai
Jiayin Wang
Xuanping Zhang
Xiaoyan Zhu
Paul B. S. Lai
Ci-ren Guo
A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields
BMC Medical Informatics and Decision Making
Surgical risk calculator
Gradient boosting decision tree
Machine learning
Clinical decision support system
author_facet Ruoyu Liu
Xin Lai
Jiayin Wang
Xuanping Zhang
Xiaoyan Zhu
Paul B. S. Lai
Ci-ren Guo
author_sort Ruoyu Liu
title A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields
title_short A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields
title_full A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields
title_fullStr A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields
title_full_unstemmed A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields
title_sort non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields
publisher BMC
series BMC Medical Informatics and Decision Making
issn 1472-6947
publishDate 2021-07-01
description Abstract Background The misestimation of surgical risk is a serious threat to the lives of patients when implementing surgical risk calculator. Improving the accuracy of postoperative risk prediction has received much attention and many methods have been proposed to cope with this problem in the past decades. However, those linear approaches are inable to capture the non-linear interactions between risk factors, which have been proved to play an important role in the complex physiology of the human body, and thus may attenuate the performance of surgical risk calculators. Methods In this paper, we presented a new surgical risk calculator based on a non-linear ensemble algorithm named Gradient Boosting Decision Tree (GBDT) model, and explored the corresponding pipeline to support it. In order to improve the practicability of our approach, we designed three different modes to deal with different data situations. Meanwhile, considering that one of the obstacles to clinical acceptance of surgical risk calculators was that the model was too complex to be used in practice, we reduced the number of input risk factors according to the importance of them in GBDT. In addition, we also built some baseline models and similar models to compare with our approach. Results The data we used was three-year clinical data from Surgical Outcome Monitoring and Improvement Program (SOMIP) launched by the Hospital Authority of Hong Kong. In all experiments our approach shows excellent performance, among which the best result of area under curve (AUC), Hosmer–Lemeshow test ( $${{\mathrm{HL}}}_{\hat{c}}$$ HL c ^ ) and brier score (BS) can reach 0.902, 7.398 and 0.047 respectively. After feature reduction, the best result of AUC, $${\mathrm{HL}}_{\hat{c}}$$ HL c ^ and BS of our approach can still be maintained at 0.894, 7.638 and 0.060, respectively. In addition, we also performed multiple groups of comparative experiments. The results show that our approach has a stable advantage in each evaluation indicator. Conclusions The experimental results demonstrate that NL-SRC can not only improve the accuracy of predicting the surgical risk of patients, but also effectively capture important risk factors and their interactions. Meanwhile, it also has excellent performance on the mixed data from multiple surgical fields.
topic Surgical risk calculator
Gradient boosting decision tree
Machine learning
Clinical decision support system
url https://doi.org/10.1186/s12911-021-01450-9
work_keys_str_mv AT ruoyuliu anonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT xinlai anonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT jiayinwang anonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT xuanpingzhang anonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT xiaoyanzhu anonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT paulbslai anonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT cirenguo anonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT ruoyuliu nonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT xinlai nonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT jiayinwang nonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT xuanpingzhang nonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT xiaoyanzhu nonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT paulbslai nonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
AT cirenguo nonlinearensemblemodelbasedsurgicalriskcalculatorformixeddatafrommultiplesurgicalfields
_version_ 1721245761238204416