Noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow MRI radiomics based on interpretable machine learning: a multicenter cohort study

Abstract Objectives To develop and validate an interpretable machine learning model based on clinicoradiological features and radiomic features based on magnetic resonance imaging (MRI) to predict the failure of conservative treatment in lateral epicondylitis (LE). Methods This retrospective study i...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianing Cui, Ping Wang, Xiaodong Zhang, Ping Zhang, Yuming Yin, Rongjie Bai
Format: Article
Language:English
Published: BMC 2025-05-01
Series:Journal of Orthopaedic Surgery and Research
Subjects:
Online Access:https://doi.org/10.1186/s13018-025-05901-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730898965037056
author Jianing Cui
Ping Wang
Xiaodong Zhang
Ping Zhang
Yuming Yin
Rongjie Bai
author_facet Jianing Cui
Ping Wang
Xiaodong Zhang
Ping Zhang
Yuming Yin
Rongjie Bai
author_sort Jianing Cui
collection DOAJ
description Abstract Objectives To develop and validate an interpretable machine learning model based on clinicoradiological features and radiomic features based on magnetic resonance imaging (MRI) to predict the failure of conservative treatment in lateral epicondylitis (LE). Methods This retrospective study included 420 patients with LE from three hospitals, divided into a training cohort (n = 245), an internal validation cohort (n = 115), and an external validation cohort (n = 60). Patients were categorized into conservative treatment failure (n = 133) and conservative treatment success (n = 287) groups based on the outcome of conservative treatment. We developed two predictive models: one utilizing clinicoradiological features, and another integrating clinicoradiological and radiomic features. Seven machine learning algorithms were evaluated to determine the optimal model for predicting the failure of conservative treatment. Model performance was assessed using ROC, and model interpretability was examined using SHapley Additive exPlanations (SHAP). Results The LightGBM algorithm was selected as the optimal model because of its superior performance. The combined model demonstrated enhanced predictive accuracy with an area under the ROC curve (AUC) of 0.96 (95% CI: 0.91, 0.99) in the external validation cohort. SHAP analysis identified the radiological feature “CET coronal tear size” and the radiomic feature “AX_log-sigma-1-0-mm-3D_glszm_SmallAreaEmphasis” as key predictors of conservative treatment failure. Conclusions We developed and validated an interpretable LightGBM machine learning model that integrates clinicoradiological and radiomic features to predict the failure of conservative treatment in LE. The model demonstrates high predictive accuracy and offers valuable insights into key prognostic factors.
format Article
id doaj-art-a3595fa4f44c443681f8d8c1f51b09d8
institution DOAJ
issn 1749-799X
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series Journal of Orthopaedic Surgery and Research
spelling doaj-art-a3595fa4f44c443681f8d8c1f51b09d82025-08-20T03:08:43ZengBMCJournal of Orthopaedic Surgery and Research1749-799X2025-05-0120111210.1186/s13018-025-05901-1Noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow MRI radiomics based on interpretable machine learning: a multicenter cohort studyJianing Cui0Ping Wang1Xiaodong Zhang2Ping Zhang3Yuming Yin4Rongjie Bai5Department of Radiology, Beijing Jishuitan Hospital, Capital Medical UniversityDepartment of Radiology, Beijing Jishuitan Hospital, Capital Medical UniversityDepartment of Radiology, The Third Affiliated Hospital, Southern Medical UniversityDepartment of Radiology, Beijing Geriatric HospitalDepartment of Radiology, Pomona Valley Hospital Medical CenterDepartment of Radiology, Beijing Jishuitan Hospital, Capital Medical UniversityAbstract Objectives To develop and validate an interpretable machine learning model based on clinicoradiological features and radiomic features based on magnetic resonance imaging (MRI) to predict the failure of conservative treatment in lateral epicondylitis (LE). Methods This retrospective study included 420 patients with LE from three hospitals, divided into a training cohort (n = 245), an internal validation cohort (n = 115), and an external validation cohort (n = 60). Patients were categorized into conservative treatment failure (n = 133) and conservative treatment success (n = 287) groups based on the outcome of conservative treatment. We developed two predictive models: one utilizing clinicoradiological features, and another integrating clinicoradiological and radiomic features. Seven machine learning algorithms were evaluated to determine the optimal model for predicting the failure of conservative treatment. Model performance was assessed using ROC, and model interpretability was examined using SHapley Additive exPlanations (SHAP). Results The LightGBM algorithm was selected as the optimal model because of its superior performance. The combined model demonstrated enhanced predictive accuracy with an area under the ROC curve (AUC) of 0.96 (95% CI: 0.91, 0.99) in the external validation cohort. SHAP analysis identified the radiological feature “CET coronal tear size” and the radiomic feature “AX_log-sigma-1-0-mm-3D_glszm_SmallAreaEmphasis” as key predictors of conservative treatment failure. Conclusions We developed and validated an interpretable LightGBM machine learning model that integrates clinicoradiological and radiomic features to predict the failure of conservative treatment in LE. The model demonstrates high predictive accuracy and offers valuable insights into key prognostic factors.https://doi.org/10.1186/s13018-025-05901-1Lateral epicondylitisMachine learningMagnetic resonance imagingRadiomicsSHapley additive explanation
spellingShingle Jianing Cui
Ping Wang
Xiaodong Zhang
Ping Zhang
Yuming Yin
Rongjie Bai
Noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow MRI radiomics based on interpretable machine learning: a multicenter cohort study
Journal of Orthopaedic Surgery and Research
Lateral epicondylitis
Machine learning
Magnetic resonance imaging
Radiomics
SHapley additive explanation
title Noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow MRI radiomics based on interpretable machine learning: a multicenter cohort study
title_full Noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow MRI radiomics based on interpretable machine learning: a multicenter cohort study
title_fullStr Noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow MRI radiomics based on interpretable machine learning: a multicenter cohort study
title_full_unstemmed Noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow MRI radiomics based on interpretable machine learning: a multicenter cohort study
title_short Noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow MRI radiomics based on interpretable machine learning: a multicenter cohort study
title_sort noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow mri radiomics based on interpretable machine learning a multicenter cohort study
topic Lateral epicondylitis
Machine learning
Magnetic resonance imaging
Radiomics
SHapley additive explanation
url https://doi.org/10.1186/s13018-025-05901-1
work_keys_str_mv AT jianingcui noninvasivepredictionoffailureoftheconservativetreatmentinlateralepicondylitisbyclinicoradiologicalfeaturesandelbowmriradiomicsbasedoninterpretablemachinelearningamulticentercohortstudy
AT pingwang noninvasivepredictionoffailureoftheconservativetreatmentinlateralepicondylitisbyclinicoradiologicalfeaturesandelbowmriradiomicsbasedoninterpretablemachinelearningamulticentercohortstudy
AT xiaodongzhang noninvasivepredictionoffailureoftheconservativetreatmentinlateralepicondylitisbyclinicoradiologicalfeaturesandelbowmriradiomicsbasedoninterpretablemachinelearningamulticentercohortstudy
AT pingzhang noninvasivepredictionoffailureoftheconservativetreatmentinlateralepicondylitisbyclinicoradiologicalfeaturesandelbowmriradiomicsbasedoninterpretablemachinelearningamulticentercohortstudy
AT yumingyin noninvasivepredictionoffailureoftheconservativetreatmentinlateralepicondylitisbyclinicoradiologicalfeaturesandelbowmriradiomicsbasedoninterpretablemachinelearningamulticentercohortstudy
AT rongjiebai noninvasivepredictionoffailureoftheconservativetreatmentinlateralepicondylitisbyclinicoradiologicalfeaturesandelbowmriradiomicsbasedoninterpretablemachinelearningamulticentercohortstudy