Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus

Machine learning predictive modeling of the persistence of post-Covid19 disorders: Loss of smell and taste as case studies

The worldwide health crisis triggered by the novel coronavirus (COVID-19) epidemic has resulted in an extensive variety of symptoms in people who have been infected, the most prevalent disorders of which are loss of smell and taste senses. In some patients, these disorders might occasionally last for several months and can strongly affect patients' quality of life. The COVID-19-related loss of taste and smell does not presently have a particular therapy. However, with the help of an early prediction of these disorders, healthcare providers can direct the patients to control these symptoms and prevent complications by following special procedures. The purpose of this research is to develop a machine learning (ML) model that can predict the occurrence and persistence of post-COVID-19-related loss of smell and taste abnormalities. In this study, we used our dataset to describe the symptoms, functioning, and disability of 413 verified COVID-19 patients. In order to prepare accurate classification models, we combined several ML algorithms, including logistic regression, k-nearest neighbors, support vector machine, random forest, extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM). The accuracy of the loss of taste model was 91.5 % with an area-under-cure (AUC) of 0.94, and the accuracy of the loss of smell model was 95 % with an AUC of 0.97. Our proposed modelling framework can be utilized by hospitals experts to assess these post-COVID-19 disorders in the early stages, which supports the development of treatment strategies.

Olfactory function in diabetes mellitus

Diabetes mellitus (DM) is an increasingly common disease in both children and adults. In addition to neuronal and/or vascular disorders, it can cause chemosensory abnormalities including olfactory deterioration. The purpose of this article is to summarize current knowledge on olfactory function in DM, highlighting the impact of co-morbidities, especially obesity, thyroid dysfunction, chronic kidney disease and COVID-19 on olfactory outcomes. Research to date mostly shows that olfactory impairment is more common in people with diabetes than in the general population. In addition, the presence of concomitant diseases is a factor increasing olfactory impairment. Such a correlation was shown for type 1 diabetes, type 2 diabetes and gestational diabetes. At the same time, not only chronic diseases, but also DM in acute conditions such as COVID-19 leads to a higher prevalence of olfactory disorders during infection. Analyzing the existing literature, it is important to be aware of the limitations of published studies. These include the small number of patients studied, the lack of uniformity in the methods used to assess the sense of smell, frequently relying on rated olfactory function only, and the simultaneous analysis of patients with different types of diabetes, often without a clear indication of diabetes type. In addition, the number of available publications is small. Certainly, further research in this area is needed. From a practical point of view decreased olfactory performance may be an indicator for central neuropathy and an indication for assessing the patient's nutritional status, examining cognitive function, especially in older patients and performing additional diagnostic tests, such as checking thyroid function, because all those changes were correlated with smell deterioration.