Assessment and prediction of restless leg syndrome (RLS) in patients with diabetes mellitus type II through artificial intelligence (AI)

Abstract

This study aimed to diagnose the incidence of restless leg syndrome (RLS) in patients with diabetes mellitus (DM) type-2, thorough artificial intelligence based multilayer perceptron (MLP). 300 cases of diabetes mellitus type-2, of age between 18-80 years were included. Point-biserial correlation/Pearson Chi-Square correlations were conducted between RLS and risk factors. We trained a backpropagation MLP via. supervised learning algorithm to predict clinical outcome for RLS. Majority of the patients were having hypertension (63%) and with peripheral neuropathy (69%). Two mostly reported scaled parameters were: 18% ‘tiredness’ and 14%, ‘impact on mood’. A significant correlation was found in RLS with smoking, hypertension and chronic renal failure (CRF). MLP model achieved more than 95% accuracy in predicting the outcome with cross entropy error 0.5%. Following scaled symptomatic variables: ‘need/urge to move’ (100%) achieved the highest normalized importance, followed by ‘relief by moving’ (85.7%), ‘sleep disturbance’ (62%) and ‘impact on mood’ (51.3%). Artificial intelligence based models can help physicians to identify the pre diagnose RLS, so that active measures can be taken in time to avoid further complications.