Using Artificial Intelligence for Detecting Diabetic Foot Osteomyelitis: Validation of Deep Learning Model for Plain Radiograph Interpretation

Objective: To develop and validate a ResNet-50-based deep learning model for automatic detection of osteomyelitis (DFO) in plain radiographs of patients with diabetic foot ulcers (DFUs). Research Design and Methods: This retrospective study included 168 patients with type one or type two diabetes an...

Full description

Saved in:
Bibliographic Details
Main Authors: Francisco Javier Álvaro-Afonso, Aroa Tardáguila-García, Mateo López-Moral, Irene Sanz-Corbalán, Esther García-Morales, José Luis Lázaro-Martínez
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/15/8583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406091735072768
author Francisco Javier Álvaro-Afonso
Aroa Tardáguila-García
Mateo López-Moral
Irene Sanz-Corbalán
Esther García-Morales
José Luis Lázaro-Martínez
author_facet Francisco Javier Álvaro-Afonso
Aroa Tardáguila-García
Mateo López-Moral
Irene Sanz-Corbalán
Esther García-Morales
José Luis Lázaro-Martínez
author_sort Francisco Javier Álvaro-Afonso
collection DOAJ
description Objective: To develop and validate a ResNet-50-based deep learning model for automatic detection of osteomyelitis (DFO) in plain radiographs of patients with diabetic foot ulcers (DFUs). Research Design and Methods: This retrospective study included 168 patients with type one or type two diabetes and clinical suspicion of DFO confirmed via a surgical bone biopsy. An experienced clinician and a pretrained ResNet-50 model independently interpreted the radiographs. The model was developed using Python-based frameworks with ChatGPT assistance for coding. The diagnostic performance was assessed against the histopathological findings, calculating sensitivity, specificity, the positive predictive value (PPV), the negative predictive value (NPV), and the likelihood ratios. Agreement between the AI model and the clinician was evaluated using Cohen’s kappa coefficient. Results: The AI model demonstrated high sensitivity (92.8%) and PPV (0.97), but low-level specificity (4.4%). The clinician showed 90.2% sensitivity and 37.8% specificity. The Cohen’s kappa coefficient between the AI model and the clinician was −0.105 (<i>p</i> = 0.117), indicating weak agreement. Both the methods tended to classify many cases as DFO-positive, with 81.5% agreement in the positive cases. Conclusions: This study demonstrates the potential of IA to support the radiographic diagnosis of DFO using a ResNet-50-based deep learning model. AI-assisted radiographic interpretation could enhance early DFO detection, particularly in high-prevalence settings. However, further validation is necessary to improve its specificity and assess its utility in primary care.
format Article
id doaj-art-15ac10d6b69d4b05a78a30d5b46d23e5
institution Kabale University
issn 2076-3417
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-15ac10d6b69d4b05a78a30d5b46d23e52025-08-20T03:36:31ZengMDPI AGApplied Sciences2076-34172025-08-011515858310.3390/app15158583Using Artificial Intelligence for Detecting Diabetic Foot Osteomyelitis: Validation of Deep Learning Model for Plain Radiograph InterpretationFrancisco Javier Álvaro-Afonso0Aroa Tardáguila-García1Mateo López-Moral2Irene Sanz-Corbalán3Esther García-Morales4José Luis Lázaro-Martínez5Diabetic Foot Unit, University Podiatric Clinic, Faculty of Nursing, Physiotherapy and Podiatry, Complutense University of Madrid, 28040 Madrid, SpainDiabetic Foot Unit, University Podiatric Clinic, Faculty of Nursing, Physiotherapy and Podiatry, Complutense University of Madrid, 28040 Madrid, SpainDiabetic Foot Unit, University Podiatric Clinic, Faculty of Nursing, Physiotherapy and Podiatry, Complutense University of Madrid, 28040 Madrid, SpainDiabetic Foot Unit, University Podiatric Clinic, Faculty of Nursing, Physiotherapy and Podiatry, Complutense University of Madrid, 28040 Madrid, SpainDiabetic Foot Unit, University Podiatric Clinic, Faculty of Nursing, Physiotherapy and Podiatry, Complutense University of Madrid, 28040 Madrid, SpainDiabetic Foot Unit, University Podiatric Clinic, Faculty of Nursing, Physiotherapy and Podiatry, Complutense University of Madrid, 28040 Madrid, SpainObjective: To develop and validate a ResNet-50-based deep learning model for automatic detection of osteomyelitis (DFO) in plain radiographs of patients with diabetic foot ulcers (DFUs). Research Design and Methods: This retrospective study included 168 patients with type one or type two diabetes and clinical suspicion of DFO confirmed via a surgical bone biopsy. An experienced clinician and a pretrained ResNet-50 model independently interpreted the radiographs. The model was developed using Python-based frameworks with ChatGPT assistance for coding. The diagnostic performance was assessed against the histopathological findings, calculating sensitivity, specificity, the positive predictive value (PPV), the negative predictive value (NPV), and the likelihood ratios. Agreement between the AI model and the clinician was evaluated using Cohen’s kappa coefficient. Results: The AI model demonstrated high sensitivity (92.8%) and PPV (0.97), but low-level specificity (4.4%). The clinician showed 90.2% sensitivity and 37.8% specificity. The Cohen’s kappa coefficient between the AI model and the clinician was −0.105 (<i>p</i> = 0.117), indicating weak agreement. Both the methods tended to classify many cases as DFO-positive, with 81.5% agreement in the positive cases. Conclusions: This study demonstrates the potential of IA to support the radiographic diagnosis of DFO using a ResNet-50-based deep learning model. AI-assisted radiographic interpretation could enhance early DFO detection, particularly in high-prevalence settings. However, further validation is necessary to improve its specificity and assess its utility in primary care.https://www.mdpi.com/2076-3417/15/15/8583artificial intelligencediabetic footdiabetic foot osteomyelitis
spellingShingle Francisco Javier Álvaro-Afonso
Aroa Tardáguila-García
Mateo López-Moral
Irene Sanz-Corbalán
Esther García-Morales
José Luis Lázaro-Martínez
Using Artificial Intelligence for Detecting Diabetic Foot Osteomyelitis: Validation of Deep Learning Model for Plain Radiograph Interpretation
Applied Sciences
artificial intelligence
diabetic foot
diabetic foot osteomyelitis
title Using Artificial Intelligence for Detecting Diabetic Foot Osteomyelitis: Validation of Deep Learning Model for Plain Radiograph Interpretation
title_full Using Artificial Intelligence for Detecting Diabetic Foot Osteomyelitis: Validation of Deep Learning Model for Plain Radiograph Interpretation
title_fullStr Using Artificial Intelligence for Detecting Diabetic Foot Osteomyelitis: Validation of Deep Learning Model for Plain Radiograph Interpretation
title_full_unstemmed Using Artificial Intelligence for Detecting Diabetic Foot Osteomyelitis: Validation of Deep Learning Model for Plain Radiograph Interpretation
title_short Using Artificial Intelligence for Detecting Diabetic Foot Osteomyelitis: Validation of Deep Learning Model for Plain Radiograph Interpretation
title_sort using artificial intelligence for detecting diabetic foot osteomyelitis validation of deep learning model for plain radiograph interpretation
topic artificial intelligence
diabetic foot
diabetic foot osteomyelitis
url https://www.mdpi.com/2076-3417/15/15/8583
work_keys_str_mv AT franciscojavieralvaroafonso usingartificialintelligencefordetectingdiabeticfootosteomyelitisvalidationofdeeplearningmodelforplainradiographinterpretation
AT aroatardaguilagarcia usingartificialintelligencefordetectingdiabeticfootosteomyelitisvalidationofdeeplearningmodelforplainradiographinterpretation
AT mateolopezmoral usingartificialintelligencefordetectingdiabeticfootosteomyelitisvalidationofdeeplearningmodelforplainradiographinterpretation
AT irenesanzcorbalan usingartificialintelligencefordetectingdiabeticfootosteomyelitisvalidationofdeeplearningmodelforplainradiographinterpretation
AT esthergarciamorales usingartificialintelligencefordetectingdiabeticfootosteomyelitisvalidationofdeeplearningmodelforplainradiographinterpretation
AT joseluislazaromartinez usingartificialintelligencefordetectingdiabeticfootosteomyelitisvalidationofdeeplearningmodelforplainradiographinterpretation