Artificial Intelligence Methodologies Applied to Technologies for Screening, Diagnosis and Care of the Diabetic Foot: A Narrative Review.

Diabetic foot syndrome is a multifactorial pathology with at least three main etiological factors, i.e., peripheral neuropathy, peripheral arterial disease, and infection. In addition to complexity, another distinctive trait of diabetic foot syndrome is its insidiousness, due to a frequent lack of early symptoms. In recent years, it has become clear that the prevalence of diabetic foot syndrome is increasing, and it is among the diabetes complications with a stronger impact on patient's quality of life. Considering the complex nature of this syndrome, artificial intelligence (AI) methodologies appear adequate to address aspects such as timely screening for the identification of the risk for foot ulcers (or, even worse, for amputation), based on appropriate sensor technologies. In this review, we summarize the main findings of the pertinent studies in the field, paying attention to both the AI-based methodological aspects and the main physiological/clinical study outcomes. The analyzed studies show that AI application to data derived by different technologies provides promising results, but in our opinion future studies may benefit from inclusion of quantitative measures based on simple sensors, which are still scarcely exploited.

Prediction of clamp-derived insulin sensitivity from the oral glucose insulin sensitivity index.

AIMS/HYPOTHESIS: The euglycaemic-hyperinsulinaemic clamp is the gold-standard method for measuring insulin sensitivity, but is less suitable for large clinical trials. Thus, several indices have been developed for evaluating insulin sensitivity from the oral glucose tolerance test (OGTT). However, most of them yield values different from those obtained by the clamp method. The aim of this study was to develop a new index to predict clamp-derived insulin sensitivity (M value) from the OGTT-derived oral glucose insulin sensitivity index (OGIS). METHODS: We analysed datasets of people that underwent both a clamp and an OGTT or meal test, thereby allowing calculation of both the M value and OGIS. The population was divided into a training and a validation cohort (n = 359 and n = 154, respectively). After a stepwise selection approach, the best model for M value prediction was applied to the validation cohort. This cohort was also divided into subgroups according to glucose tolerance, obesity category and age. RESULTS: The new index, called PREDIcted M (PREDIM), was based on OGIS, BMI, 2 h glucose during OGTT and fasting insulin. Bland-Altman analysis revealed a good relationship between the M value and PREDIM in the validation dataset (only 9 of 154 observations outside limits of agreement). Also, no significant differences were found between the M value and PREDIM (equivalence test: p < 0.0063). Subgroup stratification showed that measured M value and PREDIM have a similar ability to detect intergroup differences (p < 0.02, both M value and PREDIM). CONCLUSIONS/INTERPRETATION: The new index PREDIM provides excellent prediction of M values from OGTT or meal data, thereby allowing comparison of insulin sensitivity between studies using different tests.