EUVIMEDScopri EUVIMED
Systematische ÜbersichtOpen access

Diabetic Foot Ulcer Classification Models Using Artificial Intelligence and Machine Learning Techniques: Systematic Review

Klassifikationsmodelle für diabetische Fußulzera mit künstlicher Intelligenz und Machine-Learning-Techniken: systematische Übersicht

Manuel Alberto Silva iD, Emma J Hamilton iD, David A Russell iD, Fran Game iD, Sheila C Wang iD, Sofia Baptista iD, Matilde Monteiro-Soares iD

Journal of Medical Internet Research · 2025-09-24 · 27 · e69408

DOI: 10.2196/69408 ↗

Auf einen Blick

Die Übersicht fand 11 Studien zu ML-basierten Prognosemodellen bei diabetischen Fußulzera. Die Modelle zeigten insgesamt eine gute Diskriminierung, waren aber wegen hohem Bias-Risiko und fehlender externer Validierung nur eingeschränkt nutzbar.

Fragestellung

Welche Evidenz gibt es zur Fähigkeit von ML-basierten Modellen, klinische Endpunkte bei Menschen mit diabetischem Fußulkus vorherzusagen?

Methode

Systematische Übersicht; Suche in MEDLINE (PubMed), Scopus, Web of Science und IEEE Xplore bis Juli 2023; narrative Synthese; Biasbewertung mit QUIPS und PROBAST.

Ergebnisse

11 Studien mit 13 Publikationen; 55 Vorhersagemodelle zu Wundheilung, Amputation der unteren Extremität und Mortalität. AUROC 0,56 bis 0,94; die meisten Modelle lagen bei ≥0,8, meist ohne 95 %-KI.

Einschränkungen

Alle Studien hatten ein hohes Bias-Risiko, u. a. wegen uneinheitlicher Variablen- und Endpunktdefinitionen, kleinen Stichproben und unzureichender Missing-Data-Behandlung.

Schlussfolgerung der Autor:innen

Die Autor:innen fanden mehrere ML-Modelle mit guter Diskrimination, sehen die Nutzung aber durch Entwicklung/Interne Validierung, mehrere Modelle ohne Auswahl des besten und nicht erklärbare Techniken klar eingeschränkt.

Kernaussagen

  • 11 Studien, 13 Publikationen; 55 Modelle
  • AUROC 0,56 bis 0,94
  • Hohe Verzerrungsgefahr und fehlende externe Validierung

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in Journal of Medical Internet Research, published online on 2025-09-24. Written by Manuel Alberto Silva and 6 co-authors. Institution: USF Sanus Carandá, ULS Braga, Braga, Portugal. Major MEDLINE topics: Machine Learning, Diabetic Foot, Artificial Intelligence. Cited 23 times so far (Crossref); 53 references. The full text is freely available in PubMed Central.

Auf einen BlickAbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

Diabetes-related foot ulceration (DFU) is a common complication of diabetes, with a significant impact on survival, health care costs, and health-related quality of life. The prognosis of DFU varies widely among individuals. The International Working Group on the Diabetic Foot recently updated their guidelines on how to classify ulcers using “classical” classification and scoring systems. No system was recommended for individual prognostication, and the group considered that more detail in ulcer characterization was needed and that machine learning (ML)–based models may be the solution. Despite advances in the field, no assessment of available evidence was done.

Objective

This study aimed to identify and collect available evidence assessing the ability of ML-based models to predict clinical outcomes in people with DFU.

Methods

We searched the MEDLINE database (PubMed), Scopus, Web of Science, and IEEE Xplore for papers published up to July 2023. Studies were eligible if they were anterograde analytical studies that examined the prognostic abilities of ML models in predicting clinical outcomes in a population that included at least 80% of adults with DFU. The literature was screened independently by 2 investigators (MMS and DAR or EH in the first phase, and MMS and MAS in the second phase) for eligibility criteria and data extracted. The risk of bias was evaluated using the Quality In Prognosis Studies tool and the Prediction model Risk Of Bias Assessment Tool by 2 investigators (MMS and MAS) independently. A narrative synthesis was conducted.

Results

We retrieved a total of 2412 references after removing duplicates, of which 167 were subjected to full-text screening. Two references were added from searching relevant studies’ lists of references. A total of 11 studies, comprising 13 papers, were included focusing on 3 outcomes: wound healing, lower extremity amputation, and mortality. Overall, 55 predictive models were created using mostly clinical characteristics, random forest as the developing method, and area under the receiver operating characteristic curve (AUROC) as a discrimination accuracy measure. AUROC varied from 0.56 to 0.94, with the majority of the models reporting an AUROC equal or superior to 0.8 but lacking 95% CIs. All studies were found to have a high risk of bias, mainly due to a lack of uniform variable definitions, outcome definitions and follow-up periods, insufficient sample sizes, and inadequate handling of missing data.

Conclusions

We identified several ML-based models predicting clinical outcomes with good discriminatory ability in people with DFU. Due to the focus on development and internal validation of the models, the proposal of several models in each study without selecting the “best one,” and the use of nonexplainable techniques, the use of this type of model is clearly impaired. Future studies externally validating explainable models are needed so that ML models can become a reality in DFU care. Trial Registration PROSPERO CRD42022308248; https://www.crd.york.ac.uk/PROSPERO/view/CRD42022308248

Subjects

MeSH terms (MEDLINE)

Machine LearningDiabetic FootArtificial IntelligenceHumansPrognosis

Author keywords

artificial intelligenceclassificationdiabetic footmachine learningprognosis.

Authors and institutions

  • USF Sanus Carandá, ULS Braga, Braga, Portugal.
  • Faculty of Medicine, University of Porto, Porto, Portugal.
  • Department of Endocrinology and Diabetes, Fiona Stanley Hospital, Murdoch, Australia.
  • University of Western Australia School of Medicine, Fiona Stanley Hospital, Murdoch, Australia.
  • Leeds Institute of Clinical Trials Research, University of Leeds, Leeds, United Kingdom.
  • Leeds Vascular Institute, Leeds Teaching Hospitals NHS Trust, Leeds, United Kingdom.

ORCID profiles: Manuel Alberto Silva, Emma J Hamilton, David A Russell, Fran Game, Sheila C Wang, Sofia Baptista, Matilde Monteiro-Soares

Cite

APA

Silva, M. A., Hamilton, E. J., Russell, D. A., Game, F., Wang, S. C., Baptista, S., & Monteiro-Soares, M. (2025). Diabetic Foot Ulcer Classification Models Using Artificial Intelligence and Machine Learning Techniques: Systematic Review. Journal of Medical Internet Research, 27, e69408. https://doi.org/10.2196/69408

Vancouver

Silva MA, Hamilton EJ, Russell DA, Game F, Wang SC, Baptista S, et al. Diabetic Foot Ulcer Classification Models Using Artificial Intelligence and Machine Learning Techniques: Systematic Review. Journal of Medical Internet Research. 2025;27:e69408. doi:10.2196/69408

BibTeX
@article{Silva2025,
  author = {Silva, Manuel Alberto and Hamilton, Emma J and Russell, David A and Game, Fran and Wang, Sheila C and Baptista, Sofia and Monteiro-Soares, Matilde},
  title = {Diabetic Foot Ulcer Classification Models Using Artificial Intelligence and Machine Learning Techniques: Systematic Review},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e69408},
  doi = {10.2196/69408}
}
Start for free →