Cerebrospinal Fluid Leakage Combined with Blood Biomarkers Predicts Poor Wound Healing After Posterior Lumbar Spinal Fusion: A Machine Learning Analysis

Zixiang Pang,* Yangqin Ou,* Jiawei Liang, Shengbin Huang, Jiayi Chen, Shengsheng Huang, Qian Wei, Yuzhen Liu, Hongyuan Qin, Yuanming Chen Department Orthopedics Ward 3 (Spine and Osteopathy Surgery), Second Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, People’s...

Full description

Saved in:
Bibliographic Details
Main Authors: Pang Z, Ou Y, Liang J, Huang S, Chen J, Wei Q, Liu Y, Qin H, Chen Y
Format: Article
Language:English
Published: Dove Medical Press 2024-11-01
Series:International Journal of General Medicine
Subjects:
Online Access:https://www.dovepress.com/cerebrospinal-fluid-leakage-combined-with-blood-biomarkers-predicts-po-peer-reviewed-fulltext-article-IJGM
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217428923973632
author Pang Z
Ou Y
Liang J
Huang S
Chen J
Huang S
Wei Q
Liu Y
Qin H
Chen Y
author_facet Pang Z
Ou Y
Liang J
Huang S
Chen J
Huang S
Wei Q
Liu Y
Qin H
Chen Y
author_sort Pang Z
collection DOAJ
description Zixiang Pang,* Yangqin Ou,* Jiawei Liang, Shengbin Huang, Jiayi Chen, Shengsheng Huang, Qian Wei, Yuzhen Liu, Hongyuan Qin, Yuanming Chen Department Orthopedics Ward 3 (Spine and Osteopathy Surgery), Second Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yuanming Chen, Department of Spinal Orthopedics, the Second Affiliated Hospital of Guangxi Medical University, No. 166, University East Road, Nanning, Guangxi, People’s Republic of China, Tel +86 13087712603, Email rkyygk@163.comObjective: The objective of this study aimed to investigate the risk factors for poor wound healing (PWH) after posterior lumbar spinal fusion. Currently, there is limited research on the application of machine learning in analyzing PWH after spinal surgery. Thus, our primary aim is to using machine learning identify these risk factors and construct a clinical risk prediction model.Methods: We retrospectively reviewed 2516 patients who underwent posterior lumbar spinal fusion at Guangxi Medical University’s Second Affiliated Hospital between August 2021 and August 2023. The data was divided into test and validation groups in a 7:3 ratio. In the test group, logistic regression analysis, support vector machine (SVM), random forest (RF), decision tree (DT), XGboost, Naïve Bayes (NB), k-Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) were used to identify specific variables. The top six models from the eight machine learning models with the highest area under curve (AUC) values were selected and used to construct a dynamic nomograms model. Model performance was evaluated using receiver operating characteristic (ROC) and calibration curves. The model’s internal performance was then verified in the validation group using ROC and calibration curves.Results: Data from 2516 patients were collected, with 411 eligible cases selected. By combining logistic regression analysis with six machine learning algorithms, this study identified six predictors associated with PWH: subcutaneous lumbar spine index(SLSI), albumin, postoperative glucose, cerebrospinal fluid leakage(CSFL), neutrophil (NEU), and C-reactive protein(CRP). These predictors were used to develop a prediction model, visually represented through a nomogram. The AUC value in the test group was 0.981, and the C-index of the model was 0.986 (95% CI 0.966– 0.995), indicating excellent predictive capability. Calibration curve analysis showed good consistency between nomogram-predicted values and actual measurements.Conclusion: SLSI, albumin, postoperative glucose, CSFL, NEU and CRP were identified as significant risk factors for PWH after posterior lumbar spinal fusion. The developed prediction model exhibited excellent predictive accuracy and usefulness.Keywords: poor wound healing, posterior lumbar spinal fusion, machine learning, dynamic prediction model
format Article
id doaj-art-d308e090ddc84d579306ac4bf2adb73e
institution OA Journals
issn 1178-7074
language English
publishDate 2024-11-01
publisher Dove Medical Press
record_format Article
series International Journal of General Medicine
spelling doaj-art-d308e090ddc84d579306ac4bf2adb73e2025-08-20T02:08:03ZengDove Medical PressInternational Journal of General Medicine1178-70742024-11-01Volume 175479549197654Cerebrospinal Fluid Leakage Combined with Blood Biomarkers Predicts Poor Wound Healing After Posterior Lumbar Spinal Fusion: A Machine Learning AnalysisPang ZOu YLiang JHuang SChen JHuang SWei QLiu YQin HChen YZixiang Pang,* Yangqin Ou,* Jiawei Liang, Shengbin Huang, Jiayi Chen, Shengsheng Huang, Qian Wei, Yuzhen Liu, Hongyuan Qin, Yuanming Chen Department Orthopedics Ward 3 (Spine and Osteopathy Surgery), Second Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yuanming Chen, Department of Spinal Orthopedics, the Second Affiliated Hospital of Guangxi Medical University, No. 166, University East Road, Nanning, Guangxi, People’s Republic of China, Tel +86 13087712603, Email rkyygk@163.comObjective: The objective of this study aimed to investigate the risk factors for poor wound healing (PWH) after posterior lumbar spinal fusion. Currently, there is limited research on the application of machine learning in analyzing PWH after spinal surgery. Thus, our primary aim is to using machine learning identify these risk factors and construct a clinical risk prediction model.Methods: We retrospectively reviewed 2516 patients who underwent posterior lumbar spinal fusion at Guangxi Medical University’s Second Affiliated Hospital between August 2021 and August 2023. The data was divided into test and validation groups in a 7:3 ratio. In the test group, logistic regression analysis, support vector machine (SVM), random forest (RF), decision tree (DT), XGboost, Naïve Bayes (NB), k-Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) were used to identify specific variables. The top six models from the eight machine learning models with the highest area under curve (AUC) values were selected and used to construct a dynamic nomograms model. Model performance was evaluated using receiver operating characteristic (ROC) and calibration curves. The model’s internal performance was then verified in the validation group using ROC and calibration curves.Results: Data from 2516 patients were collected, with 411 eligible cases selected. By combining logistic regression analysis with six machine learning algorithms, this study identified six predictors associated with PWH: subcutaneous lumbar spine index(SLSI), albumin, postoperative glucose, cerebrospinal fluid leakage(CSFL), neutrophil (NEU), and C-reactive protein(CRP). These predictors were used to develop a prediction model, visually represented through a nomogram. The AUC value in the test group was 0.981, and the C-index of the model was 0.986 (95% CI 0.966– 0.995), indicating excellent predictive capability. Calibration curve analysis showed good consistency between nomogram-predicted values and actual measurements.Conclusion: SLSI, albumin, postoperative glucose, CSFL, NEU and CRP were identified as significant risk factors for PWH after posterior lumbar spinal fusion. The developed prediction model exhibited excellent predictive accuracy and usefulness.Keywords: poor wound healing, posterior lumbar spinal fusion, machine learning, dynamic prediction modelhttps://www.dovepress.com/cerebrospinal-fluid-leakage-combined-with-blood-biomarkers-predicts-po-peer-reviewed-fulltext-article-IJGMpoor wound healingposterior lumbar spinal fusionmachine learningdynamic prediction model
spellingShingle Pang Z
Ou Y
Liang J
Huang S
Chen J
Huang S
Wei Q
Liu Y
Qin H
Chen Y
Cerebrospinal Fluid Leakage Combined with Blood Biomarkers Predicts Poor Wound Healing After Posterior Lumbar Spinal Fusion: A Machine Learning Analysis
International Journal of General Medicine
poor wound healing
posterior lumbar spinal fusion
machine learning
dynamic prediction model
title Cerebrospinal Fluid Leakage Combined with Blood Biomarkers Predicts Poor Wound Healing After Posterior Lumbar Spinal Fusion: A Machine Learning Analysis
title_full Cerebrospinal Fluid Leakage Combined with Blood Biomarkers Predicts Poor Wound Healing After Posterior Lumbar Spinal Fusion: A Machine Learning Analysis
title_fullStr Cerebrospinal Fluid Leakage Combined with Blood Biomarkers Predicts Poor Wound Healing After Posterior Lumbar Spinal Fusion: A Machine Learning Analysis
title_full_unstemmed Cerebrospinal Fluid Leakage Combined with Blood Biomarkers Predicts Poor Wound Healing After Posterior Lumbar Spinal Fusion: A Machine Learning Analysis
title_short Cerebrospinal Fluid Leakage Combined with Blood Biomarkers Predicts Poor Wound Healing After Posterior Lumbar Spinal Fusion: A Machine Learning Analysis
title_sort cerebrospinal fluid leakage combined with blood biomarkers predicts poor wound healing after posterior lumbar spinal fusion a machine learning analysis
topic poor wound healing
posterior lumbar spinal fusion
machine learning
dynamic prediction model
url https://www.dovepress.com/cerebrospinal-fluid-leakage-combined-with-blood-biomarkers-predicts-po-peer-reviewed-fulltext-article-IJGM
work_keys_str_mv AT pangz cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis
AT ouy cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis
AT liangj cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis
AT huangs cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis
AT chenj cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis
AT huangs cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis
AT weiq cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis
AT liuy cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis
AT qinh cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis
AT cheny cerebrospinalfluidleakagecombinedwithbloodbiomarkerspredictspoorwoundhealingafterposteriorlumbarspinalfusionamachinelearninganalysis