COVID-19 Risk Prediction for Diabetic Patients Using Fuzzy Inference System and Machine Learning Approaches

Abstract

Individuals with pre-existing diabetes seem to be vulnerable to the COVID-19 due to changes in blood sugar levels and diabetes complications. As observed globally, around 20–50% of individuals affected by coronavirus had diabetes. However, there is no recent finding that diabetic patients are more prone to contract COVID-19 than nondiabetic patients. However, a few recent findings have observed that it could be at least twice as likely to die from complications of diabetes. Considering the multifold mortality rate of COVID-19 in diabetic patients, this study proposes a COVID-19 risk prediction model for diabetic patients using a fuzzy inference system and machine learning approaches. This study aimed to estimate the risk level of COVID-19 in diabetic patients without a medical practitioner’s advice for timely action and overcoming the multifold mortality rate of COVID-19 in diabetic patients. The proposed model takes eight input parameters, which were found as the most influential symptoms in diabetic patients. With the help of the various state-of-the-art machine learning techniques, fifteen models were built over the rule base. CatBoost classifier gives the best accuracy, recall, precision, F1 score, and kappa score. After hyper-parameter optimization, CatBoost classifier showed 76% accuracy and improvements in the recall, precision, F1 score, and kappa score, followed by logistic regression and XGBoost with 75.1% and 74.7% accuracy. Stratified k-fold cross-validation is used for validation purposes.

A novel multimodal fusion framework for early diagnosis and accurate classification of COVID-19 patients using X-ray images and speech signal processing techniques

“…Although these models can forecast the initial outbreak and growth trajectories, they are restricted in their ability to capture many temporally dynamic and geographically variable aspects driving disease spread [1] . Therefore, governments are looking for disruptive technologies to promptly diagnose individuals and control the widespread COVID-19 pandemic [29] [4] [26] [27] [30] . Several clinical diagnosis-based frameworks and strategies have been deployed for testing, tracing, and treatment, helping to crush the pandemic curve across the world (e.g., in Singapore, South Korea, and China) in its early stages.…”

Human-Machine Interaction Methods for Minimally Invasive Surgical Robotic Arms

“…For the same moving distance, the variable conductance control model based on fuzzy Sarsa (λ) learning is more energy-efficient than the high-damped-conductance model, with the maximum torque reduced from 2.72 Nm to 1.9 Nm, and the required energy decreased by 38.58%, while the positioning accuracy is very close to that of the highdamped-conductance model, with a significant improvement over the larger positioning overshoot of the lowdamped-conductance model. Comparing with the variable guide parameter adjustment method, the damping parameter adjustment strategy optimized by the fuzzy Sarsa (λ) learning algorithm has a significant improvement in the control of acceleration fluctuations, which makes the active swing operation of the minimally invasive surgical arm more supple and natural [27][28][29][30][31][32][33][34][35].…”

Compliance level toward COVID-19 preventive measures and associated factors among the Ambo University community, 2021

“…These strategies are critical for lowering mortality and alleviating the burden on healthcare systems ( 4 , 7 ). Such safeguards are thought to reduce COVID-19 transmissions in general and in particular to protect those at higher risk of severe illness, such as the elderly and those with underlying medical conditions like diabetes mellitus ( 8 ), and in frontline health workers ( 9 , 10 ).…”