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

Abstract

Background: Diabetes-related foot ulceration (DFU) is a common complication of diabetes, with a significant impact on survival, healthcare costs and health-related quality of life. We aimed to systematically identify and collect the available evidence assessing the ability of machine learning (ML) based models in predicting clinical outcomes in people with DFU. Methods: We searched PubMed, Scopus, Web of Science and IEEExplore for articles published up to July 2023. The literature was screened independently by two investigators for eligibility criteria and extracted data. Risk of bias was evaluated using Quality In Prognosis Studies (QUIPS) tool and Prediction Model Risk Of Bias Assessment Tool (PROBAST) by two investigators independently. Results: A total of 11 studies, comprising 13 articles, were included in our systematic review, focusing on four outcomes: wound healing, lower extremity amputation (LEA), mortality and reintervention. Overall, 57 predictive models were created using mostly clinical characteristics, random forest as developing method and area under the curve (AUC) as discrimination accuracy measure. AUC varied from 0.56 to 0.94, with the majority of the models achieving a good discrimination ability (defined as AUC >= 0.8). All studies were found to have a high risk of bias, mainly due to lack of uniform variable definitions, outcome definitions and follow-up periods, insufficient sample sizes, and inadequate handling of missing data. Conclusion: The ML-based models found in this study achieved good discrimination ability in people with DFU. However, models presented a high risk of bias meaning further studies with a stricter methodology are needed.