Toward Machine-Learning-Based Decision Support in Diabetes Care: A Risk Stratification Study on Diabetic Foot Ulcer and Amputation

Frontiers in Medicine

Trine Rolighed Thomsen¹  Zeinab Schäfer²  Andreas Mathisen²  Katrine Svendsen³  Susanne Engberg⁴  Klaus Kirketerp-Møller⁵ 

[1] Department of Chemistry and Biosciences, Center for Microbial Communities, Aalborg University, Aalborg, Denmark;Life Science, Danish Technological Institute, Taastrup, Denmark;Department of Computer Science, Aarhus University, Aarhus, Denmark;Research Unit for Mental Public Health, Department of Public Health, Aarhus University, Aarhus, Denmark;Steno Diabetes Center, Copenhagen, Denmark;Steno Diabetes Center, Copenhagen, Denmark;Department of Dermatology, Venereology and Wounds, Copenhagen Wound Healing Center, Bispebjerg Hospital, Copenhagen, Denmark;

关键词: risk assessment;    amputation;    prediction models;    cohort analyses;    diabetic foot ulcer;   

DOI  :  10.3389/fmed.2020.601602

来源: Frontiers

【 摘 要 】

Diabetes mellitus is associated with serious complications, with foot ulcers and amputation of limbs among the most debilitating consequences of late diagnosis and treatment of foot ulcers. Thus, prediction and on-time treatment of diabetic foot ulcers (DFU) are of great importance for improving and maintaining patients' quality of life and avoiding the consequent socio-economical burden of amputation. In this study, we use Danish national registry data to understand the risk factors of developing diabetic foot ulcers and amputation among patients with diabetes. We analyze the data of 246,705 patients with diabetes to assess some of the main risk factors for developing DFU/amputation. We study the socioeconomic information and past medical history of the patients. Factors, such as low family disposable income, cardiovascular disorders, peripheral artery, neuropathy, and chronic renal complications are among the important risk factors. Mental disorders and depression, albeit not as pronounced, still pose higher risks in comparison to the group of people without these complications. We further use machine learning techniques to assess the practical usefulness of such risk factors for predicting foot ulcers and amputation. Finally, we outline the limitations of working with registry data sources and explain potentials for combining additional public and private data sources in future applications of artificial intelligence (AI) to improve the prediction of diabetic foot ulcers and amputation.

【 授权许可】

CC BY