Content area
Full Text
Abstract
During the COVID-19 pandemic, one of the main problems healthcare providers have faced is the shortage of medical resources and a proper plan to distribute them efficiently. An influx of ill-equipped healthcare infrastructure and an inadequate pool of healthcare professionals caused an influx of mortalities. People with underlying medical problems, such as diabetes, cardiovascular problems, hypertension, and asthma, could not receive adequate medical care due to the lack of planning and allocation of healthcare resources to high-risk patients. In tough times like these, being able to predict what kind of care level an individual might require at the time of being tested positive or even before that will be of immense help to the authorities as they would be able to procure and arrange for the resources necessary to save the life of that patient. This retrospective study evaluated the comorbidity profile in COVID patients with Type 2 Diabetes Mellitus (DM). Accurate prediction and early recognition of blood coagulation in COVID Type-2 DM patients will lead to timely and meaningful interventions while preventing associated complications. The main goal of this paper is to build a machine learning model that, given a Covid-19 patient's current symptom, status, and medical history, will predict whether the patient is at high risk. This study compares multiple ML techniques for predictive modeling based on different coagulation-associated variables. Our results show that these models can be used to predict high-risk patients with Covid infection, and healthcare providers can plan the resource allocation based on the severity level of a patient's complications.
Keywords
Healthcare Resource Management, COVID-19, Machine Learning, Prediction, Type-2 Diabetes Mellitus
Introduction
Post Covid-19 pandemic, many studies reported the gap in the utilization of healthcare resources because of such
measures as lockdowns and healthcare facility access restrictions. These restrictions significantly reduced services, especially for people with underlying conditions such as Type-2 Diabetes and other comorbidities missed out on much- needed care such as life-extending interventions. Due to this situation, people misused the medications in terms of dosage. They used medicines in their violation, especially in low-income countries where pharmacies have fewer restrictions than in high-income countries. Disentangling the population who have missed the necessary care from
those who do not have comorbidities requires sensitive and nuanced analysis with...