Tele-homecare Service for Diabetic Foot Patients (Risk 0, Risk 1 and Risk 2 Level): Testing and Validation of Dedicated APPs and Artificial Intelligence Solutions

Without effective self-care, people with diabetic foot ulcers (DFUs) are at risk of prolonged healing times, hospitalization, amputation, and reduced quality of life. Despite these consequences, adherence to DFU self-care remains low.

As already pointed out in the preceding paragraphs, patient education in the prevention of diabetic foot ulcers found has been recognised as providing positive short-term effects on knowledge about care of the foot, delaying foot ulceration and amputation, especially in high-risk patients. New strategies are needed to engage people in the self-care of their DFUs.

Modern information technology may assist in attracting patients' interest if any direct benefit is promptly perceived by the patient who uses it . It is also of utmost importance that health professionals, especially those who work with diabetic patients on a daily basis, are aware of such practices and then be able to convince patients they merit the best care possible to avoid any further degradation of the pathology.

Mobile health apps hold great promise for people with diabetes, but few apps seek to engage people in their DFU self-care , , .

Schäfer et al. examined the risk factors of developing diabetic foot ulcers and amputation among patients with diabetes. They concluded that 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-economic burden of amputation.

Machine learning is a part of the field of artificial intelligence, which can automatically learn models from data and better inform clinical decision-making. Xie et al. developed an accurate and explainable prediction model to estimate the risk of in-hospital amputation in 618 hospitalized patients with DFU. They concluded that machine learning model provided accurate estimates of the amputation rate in patients with DFU during hospitalisation. Besides, the model could inform individualised analyses of the patients' risk factors.

The severe complications associated with diabetes include diabetic ketoacidosis, nonketotic hypersmolar coma, cardiovascular disease, stroke, chronic renal failure, retinal damage and foot ulcers. There is a huge increase in the number of patients with diabetes globally and it is considered a major health problem worldwide. Early diagnosis of diabetes is helpful for treatment and reduces the chance of severe complications associated with it. Machine learning algorithms (such as ANN, SVM, Naive Bayes, PLS-DA and deep learning) and data mining techniques are used for detecting interesting patterns for diagnosing and treatment of disease. Current computational methods for diabetes diagnosis have some limitations and are not tested on different datasets or people from different countries which limits the practical use of prediction methods .

A system deploying artificial intelligence and machine learning, developed by a startup based in Vrnjacka banja (Serbia), can help predict the development of complications in the feet of diabetic patients.

MY FOOT project aims at filling the gap in mobile applications by providing evidence to both involved stakeholders, that is the remote assistance from the hospital and the patient, who is directly involved in their own care strategy.

In particular, the application has to motivate patients and engage them in their self-care. Interaction with the mobile phone application is in the following terms:

APP elaborates data input from the patient in terms of own feeling of health status, symptoms revealed along the day, events eventually occurred, photos of the foot, including ulcer zoom (if any), APP reports back about increase / decrease in the Risk Level graph through time, maps the ulcer evolution or healing based on photos elaboration, using adequate graphs reporting time in the main axis, whilst reminds personal goals to enact care on a regular basis on the basis of the current conditions, eventually alerts the patient to contact clinicians for a visual inspection at a hospital.

• Analysing of potential risk factors contributed into Risk 0 and 1 [Срок оценки: 12 months]
• Analysing of potential precipitating factors for DFU [Срок оценки: 12 months]