Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network

Abstract

Since February 2020, the world has been engaged in an intense struggle with the COVID-19 disease, and health systems have come under tragic pressure as the disease turned into a pandemic. The aim of this study is to obtain the most effective routine blood values (RBV) in the diagnosis and prognosis of COVID-19 using a backward feature elimination algorithm for the LogNNet reservoir neural network. The first dataset in the study consists of a total of 5296 patients with the same number of negative and positive COVID-19 tests. The LogNNet-model achieved the accuracy rate of 99.5% in the diagnosis of the disease with 46 features and the accuracy of 99.17% with only mean corpuscular hemoglobin concentration, mean corpuscular hemoglobin, and activated partial prothrombin time. The second dataset consists of a total of 3899 patients with a diagnosis of COVID-19 who were treated in hospital, of which 203 were severe patients and 3696 were mild patients. The model reached the accuracy rate of 94.4% in determining the prognosis of the disease with 48 features and the accuracy of 82.7% with only erythrocyte sedimentation rate, neutrophil count, and C reactive protein features. Our method will reduce the negative pressures on the health sector and help doctors to understand the pathogenesis of COVID-19 using the key features. The method is promising to create mobile health monitoring systems in the Internet of Things.

Differences Between Omicron Infections and Fever Outpatients: Comparison of Clinical Manifestations and Initial Routine Hematology Indicators

“…But, the analysis of clinical symptoms and routine blood parameters for Omicron is limited. [15][16][17] Here, we investigated the initial manifestations and hematological parameters of 65 patients with Omicron infections and matched 69 age-and sex-matched Fever outpatients, aiming to identify the differences between these two diseases and provide data support for the early identification of Omicron infections. We also included 1595 patients with fever who visited the Fever Clinic Department of Enze Medical Center from April 6, 2022, to April 30, 2022, as Fever group.…”

Machine Learning Sensors for Diagnosis of COVID-19 Disease Using Routine Blood Values for Internet of Things Application

“…However, imaging-based solutions are costly and require specialized equipment. Machine learning (ML) and AI studies based on RBVs features are a more economical and rapid alternative method for the early detection, diagnosis and prognosis of COVID-19 [ 7 , 11 , 12 ]. Previous studies have indicated that this disease can accompany multi-organ dysfunction and cause a variety of symptoms [ 3 , 13 , 14 , 15 ].…”

“…The early detection of patients in pandemics is an important but clinically difficult process in terms of morbidity and mortality [ 14 , 24 ]. The diagnosis and prognosis of COVID-19 with the use of advanced devices can provide support in improving patient comfort, health system and tackling economic inadequacies [ 6 , 11 , 12 ]. In this context, studies are carried out to diagnose and determine the severity of the disease in the early period by using ML and AI-based methods as well as RBVs data [ 7 , 11 , 12 ].…”

“…The diagnosis and prognosis of COVID-19 with the use of advanced devices can provide support in improving patient comfort, health system and tackling economic inadequacies [ 6 , 11 , 12 ]. In this context, studies are carried out to diagnose and determine the severity of the disease in the early period by using ML and AI-based methods as well as RBVs data [ 7 , 11 , 12 ]. The basic element in ML approaches is to determine the feature vector with a linear classifier [ 30 ].…”

“…We examined the SARS-CoV-2-RBV1 database using the LogNNet neural network [ 12 ]. LogNNet can be defined as a feed forward network that increases the classification accuracy by chaotic mapping that fills a reservoir matrix.…”