FRID-PI: a machine learning model for diagnosing fracture-related infections based on 18F-FDG PET/CT and inflammatory markers

PurposeThe diagnosis of fracture-related infection (FRI) especially patients presenting without clinical confirmatory criteria in clinical settings poses challenges with potentially serious consequences if misdiagnosed. This study aimed to construct and evaluate a novel diagnostic nomogram based on...

Full description

Saved in:
Bibliographic Details
Main Authors: Mei Yang, Quanhui Tan, Tingting Li, Jie Chen, Weiwei Hu, Yi Zhang, Xiaohua Chen, Jiangfeng Wang, Chentian Shen, Zhenghao Tang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1534988/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849391901201924096
author Mei Yang
Quanhui Tan
Tingting Li
Jie Chen
Weiwei Hu
Yi Zhang
Xiaohua Chen
Jiangfeng Wang
Chentian Shen
Zhenghao Tang
author_facet Mei Yang
Quanhui Tan
Tingting Li
Jie Chen
Weiwei Hu
Yi Zhang
Xiaohua Chen
Jiangfeng Wang
Chentian Shen
Zhenghao Tang
author_sort Mei Yang
collection DOAJ
description PurposeThe diagnosis of fracture-related infection (FRI) especially patients presenting without clinical confirmatory criteria in clinical settings poses challenges with potentially serious consequences if misdiagnosed. This study aimed to construct and evaluate a novel diagnostic nomogram based on 18F-fluorodeoxyglucose positron emission tomography /computed tomography (18F-FDG PET/CT) and laboratory biomarkers for FRI by machine learning.MethodsA total of 552 eligible patients recruited from a single institution between January 2021 and December 2022 were randomly divided into a training (60%) and a validation (40%) cohort. In the training cohort, the Least Absolute Shrinkage and Selection Operator (LASSO) regression model analysis and multivariate Cox regression analysis were utilized to identify predictive factors for FRI. The performance of the model was assessed using the area under the Receiver Operating Characteristic (ROC) curve (AUC), calibration curves, and decision curve analysis in both training and validation cohorts.ResultsA nomogram model (named FRID-PE) based on the maximum standardized uptake value (SUVmax) from 18F-FDG PET/CT imaging, Systemic Immune-Inflammation Index (SII), Interleukin - 6 and erythrocyte sedimentation rate (ESR) were generated, yielding an AUC of 0.823 [95% confidence interval (CI), 0.778–0.868] in the training test and 0.811 (95% CI, 0.753–0.869) in the validation cohort for the diagnosis of FRI. Furthermore, the calibration curves and decision curve analysis proved the potential clinical utility of this model. An online webserver was built based on the proposed nomogram for convenient clinical use.ConclusionThis study introduces a novel model (FRID - PI) based on SUVmax and inflammatory markers, such as SII, IL - 6, and ESR, for diagnosing FRI. Our model, which exhibits good diagnostic performance, holds promise for future clinical applications.Clinical relevance statementThe study aims to construct and evaluate a novel diagnostic model based on 18F-fluorodeoxyglucose positron emission tomography /computed tomography (18F-FDG PET/CT) and laboratory biomarkers for fracture-related infection (FRI).
format Article
id doaj-art-4c540cb43bdf4131998abf56dc858878
institution Kabale University
issn 2296-858X
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-4c540cb43bdf4131998abf56dc8588782025-08-20T03:40:54ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-03-011210.3389/fmed.2025.15349881534988FRID-PI: a machine learning model for diagnosing fracture-related infections based on 18F-FDG PET/CT and inflammatory markersMei Yang0Quanhui Tan1Tingting Li2Jie Chen3Weiwei Hu4Yi Zhang5Xiaohua Chen6Jiangfeng Wang7Chentian Shen8Zhenghao Tang9Department of Infectious Diseases, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Infectious Diseases, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Infectious Diseases, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Infectious Diseases, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Infectious Diseases, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Infectious Diseases, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Infectious Diseases, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Infectious Diseases, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaPurposeThe diagnosis of fracture-related infection (FRI) especially patients presenting without clinical confirmatory criteria in clinical settings poses challenges with potentially serious consequences if misdiagnosed. This study aimed to construct and evaluate a novel diagnostic nomogram based on 18F-fluorodeoxyglucose positron emission tomography /computed tomography (18F-FDG PET/CT) and laboratory biomarkers for FRI by machine learning.MethodsA total of 552 eligible patients recruited from a single institution between January 2021 and December 2022 were randomly divided into a training (60%) and a validation (40%) cohort. In the training cohort, the Least Absolute Shrinkage and Selection Operator (LASSO) regression model analysis and multivariate Cox regression analysis were utilized to identify predictive factors for FRI. The performance of the model was assessed using the area under the Receiver Operating Characteristic (ROC) curve (AUC), calibration curves, and decision curve analysis in both training and validation cohorts.ResultsA nomogram model (named FRID-PE) based on the maximum standardized uptake value (SUVmax) from 18F-FDG PET/CT imaging, Systemic Immune-Inflammation Index (SII), Interleukin - 6 and erythrocyte sedimentation rate (ESR) were generated, yielding an AUC of 0.823 [95% confidence interval (CI), 0.778–0.868] in the training test and 0.811 (95% CI, 0.753–0.869) in the validation cohort for the diagnosis of FRI. Furthermore, the calibration curves and decision curve analysis proved the potential clinical utility of this model. An online webserver was built based on the proposed nomogram for convenient clinical use.ConclusionThis study introduces a novel model (FRID - PI) based on SUVmax and inflammatory markers, such as SII, IL - 6, and ESR, for diagnosing FRI. Our model, which exhibits good diagnostic performance, holds promise for future clinical applications.Clinical relevance statementThe study aims to construct and evaluate a novel diagnostic model based on 18F-fluorodeoxyglucose positron emission tomography /computed tomography (18F-FDG PET/CT) and laboratory biomarkers for fracture-related infection (FRI).https://www.frontiersin.org/articles/10.3389/fmed.2025.1534988/full18F-FDG PET/CTlaboratory biomarkersfracture-related infectionnomogrammodel
spellingShingle Mei Yang
Quanhui Tan
Tingting Li
Jie Chen
Weiwei Hu
Yi Zhang
Xiaohua Chen
Jiangfeng Wang
Chentian Shen
Zhenghao Tang
FRID-PI: a machine learning model for diagnosing fracture-related infections based on 18F-FDG PET/CT and inflammatory markers
Frontiers in Medicine
18F-FDG PET/CT
laboratory biomarkers
fracture-related infection
nomogram
model
title FRID-PI: a machine learning model for diagnosing fracture-related infections based on 18F-FDG PET/CT and inflammatory markers
title_full FRID-PI: a machine learning model for diagnosing fracture-related infections based on 18F-FDG PET/CT and inflammatory markers
title_fullStr FRID-PI: a machine learning model for diagnosing fracture-related infections based on 18F-FDG PET/CT and inflammatory markers
title_full_unstemmed FRID-PI: a machine learning model for diagnosing fracture-related infections based on 18F-FDG PET/CT and inflammatory markers
title_short FRID-PI: a machine learning model for diagnosing fracture-related infections based on 18F-FDG PET/CT and inflammatory markers
title_sort frid pi a machine learning model for diagnosing fracture related infections based on 18f fdg pet ct and inflammatory markers
topic 18F-FDG PET/CT
laboratory biomarkers
fracture-related infection
nomogram
model
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1534988/full
work_keys_str_mv AT meiyang fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers
AT quanhuitan fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers
AT tingtingli fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers
AT jiechen fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers
AT weiweihu fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers
AT yizhang fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers
AT xiaohuachen fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers
AT jiangfengwang fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers
AT chentianshen fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers
AT zhenghaotang fridpiamachinelearningmodelfordiagnosingfracturerelatedinfectionsbasedon18ffdgpetctandinflammatorymarkers