Diabetic Foot Ulcer

A Diabetic Foot Ulcer (DFU) is a serious complication of diabetes and can lead to a lower limb amputation if not treated properly and in an early stage [10]. A DFU is often caused by poor blood circulation and neuropathy and therefore also heals poorly. For these long-term non-healing wounds, infection is a threat. If the wound does not heal or if an infection spreads, amputation is sometimes unavoidable [3].

DFU patients will become more common in the future. By 2045, the number of diabetic patients will have increased from 480 to 700 million, meaning more than 100 million people will get a DFU [8]. The World Health Organization (WHO) estimates that,

throughout the world, a lower limb is lost every 30 seconds due to diabetes [38]. If healthcare does not improve, amputation or even death will be inevitable for 12-15% of the patients. In this way, healthcare will come under a great deal of pressure in terms of capacity and financially [8].

Constant advances in technology means the use of Machine Learning (ML) algorithms in healthcare is becoming an increasingly popular approach [45]. Their ability to reduce human error, cost, number of personnel and time taken to complete tasks are useful features [45]. ML algorithms are characterized by their ability to learn and adapt over time without being explicitly programmed. ML can be classified into supervised learning, which trains a model on known input and output data so that it can predict future outputs and unsupervised learning, which finds hidden patterns or intrinsic structures in input data [45].

Numerous studies show that proper diagnosis and management of DFUs can greatly reduce or prevent serious complications [29,30,32,45,47]. Despite various national and international guidelines, the management of DFUs remains inconsistent. Due to the importance of reliable and quick management in diabetic patients, ML has great potential to improve healthcare systems.

In recent years, research on automation using computer vision and ML methods plays an important role in DFU treatment. Promising successes have already been achieved so far [8]. What makes this research stand out is because of all the findings within this research field, this is the first systematic review since 2020. In a research field that develops as fast as ML does, it is of high importance that an updated summery is made with regular interval. However, are the algorithm developed in the past two years accurate enough? Will it work with currently used and new perfusion imaging techniques? This work aims to investigate ways to improve treatment approaches for DFUs using ML.


Based on the findings in the founded articles, ML is now accurate enough to create predictions. These predictions can range from datamining in favor of finding out the likeliness for developing a DFU, to full-scale wound analyses combined with prediction of wound development. However, there is still a lot of development in this area that needs further investigation.
At the time of writing text input-based algorithms that wish to make a prediction on wound recovery are best suited to use a tree-based structure, while for image input-based algorithms it is best to use DL methods [36]. Based on these findings, this means that the use of both approaches in unison to have the highest results when evaluating wound recovery prediction in medical clinics treating patients with DFU wounds.


Goyal, M., Reeves, N. D., Davison, A. K., Rajbhandari, S., Spragg, J., & Yap, M. H. (2020). DFUNet: Convolutional Neural Networks for Diabetic Foot Ulcer Classification. IEEE Transactions on

Choke, E., Tang, T. Y., Cheng, S. C., & Tay, J. S. (2019). Treatment of lower limb ischaemia in patients with diabetes. Diabetes/Metabolism Research and Reviews. https://doi.org/10.1002/dmrr.3262

Al-Garaawi, N., Ebsim, R., Alharan, A. F., & Yap, M. H. (2022). Diabetic foot ulcer classification using mapped binary patterns and convolutional neural networks. Computers in Biology and Medicine.

Basu, S., Johnson, K. T., & Berkowitz, S. A. (2020). Use of Machine Learning Approaches in Clinical Epidemiological Research of Diabetes. Current Diabetes Reports. https://doi.org/10.1007/s11892- 020-01353-5

Lin, K. C., & Hsieh, Y. H. (2015). Classification of Medical Datasets Using SVMs with Hybrid Evolutionary Algorithms Based on Endocrine-Based Particle Swarm Optimization and Artificial Bee Colony Algorithms. Journal of Medical Systems. https://doi.org/10.1007/s10916- 015-0306-3

Dagliati, A., Marini, S., Sacchi, L., Cogni, G., Teliti, M., Tibollo, V., De Cata, P., Chiovato, L., & Bellazzi, R. (2017). Machine Learning Methods to Predict Diabetes Complications. Journal of Diabetes Science and Technology. https://doi.org/10.1177/193229681770637 5

Tulloch, J., Zamani, R., & Akrami, M. (2020). Machine Learning in the Prevention, Diagnosis and Management of Diabetic Foot Ulcers: A Systematic Review. IEEE Access. https://doi.org/10.1109/access.2020.30353 27

Dr. Ester de Jonge
I am an analytical, interested and down-to-earth Zeelander with a great sense of responsibility. I approach every project with a curious, open and flexible attitude. I like to translate theory and figures about nutrition and health into practical, understandable information. I have experience with health research within industry, academia and government.