The coronavirus disease 2019 (COVID-19) epidemic went down in history as a pandemic caused by corona-viruses that emerged in 2019 and spread rapidly around the world. The different symptoms of COVID-19 made it difficult to understand which variables were more influential on the diagnosis, course and mortality of the disease. Machine learning models can accurately assess hidden patterns among risk factors by analyzing large-datasets to quickly predict diagnosis, prognosis and mortality of diseases. Because of this advantage, the use of machine learning models as decision support systems in health services is increasing. The aim of this study is to determine the diagnosis and prognosis of COVID-19 disease with blood-gas data using the Chi-squared Automatic Interaction Detector (CHAID) decision-tree-model, one of the machine learning methods, which is a subfield of artificial intelligence. This study was carried out on a total of 686 patients with COVID-19 (n = 343) and non-COVID-19 (n = 343) treated at Erzincan-Mengücek-Gazi-Training and Research-Hospital between April 1, 2020 and March 1, 2021. Arterial blood gas values of all patients were obtained from the hospital registry system. While the total-accuracyratio of the decision-tree-model was 65.0% in predicting the prognosis of the disease, it was 68.2% in the diagnosis of the disease. According to the results obtained, the low ionized-calcium value (< 1.10 mM) significantly predicted the need for intensive care of COVID-19 patients. At admission, low-carboxyhemoglobin (< 1.00%), high-pH (> 7.43), low-sodium (< 135.0 mM), hematocrit (< 40.0%), and methemoglobin (< 1.30%) values are important biomarkers in the diagnosis of COVID-19 and the results were promising. The findings in the study may aid in the early-diagnosis of the disease and the intensive-care treatment of patients who are severe. The study was approved by the Ministry of Health and Erzincan University Faculty of Medicine Clinical Research Ethics Committee.

How the routine laboratory tests change in terms of coronavirus disease 2019 (COVID-19) was retrospectively analyzed in a large group of patients. Biochemical, hematological and inflammatory variables of a totaly 555 (n = 532 in non-intensive care unit (non-ICU), n = 23 in ICU) patients diagnosed with COVID-19 were analyzed accessing them through the laboratory information system. White blood cell (WBC), neutrophil (NEU), platelet large cell ratio, neutrophil to lymphocyte ratio (NLR), derived NLR (d-NLR), aspartate aminotransferase, urea, creatine kinase (CK) myocardial band (CK-MB), procalcitonin (PCT) values were high whereas lymphocyte (LYM), eosinophil, red blood cells (RBC), hemoglobin, lymphocyte to monocyte ratio, estimated glomerular filtration rate values were low in the ICU group when compared with non-ICU. WBC, NEU, red cell distribution width, alanine transaminase, creatinine, urea, CK-MB, CK, direct bilirubin, lactate dehydrogenase, glucose, C-reactive protein, erythrocyte sedimentation rate, ferritin, D-dimer, PCT and international normalized ratio values increased while RBC, hemoglobin, hematocrit, mean corpuscular volume and total bilirubin values decreased in a significant proportion of patients in both groups based on the normal reference ranges. LYM count was found to be low in a significant number of patients (57.5%) especially in the ICU group and as an important risk factor and diagnostic parameter on admission to ICU (OR: 125, AUC: 0.74). Routine laboratory tests provide important information in terms of both diagnosis and severity of COVID-19. Lymphopenia is a condition that should be monitored which indicates the severity of the disease.

Healthcare digitalization requires effective applications of human sensors, when various parameters of the human body are instantly monitored in everyday life due to the Internet of Things (IoT). In particular, machine learning (ML) sensors for the prompt diagnosis of COVID-19 are an important option for IoT application in healthcare and ambient assisted living (AAL). Determining a COVID-19 infected status with various diagnostic tests and imaging results is costly and time-consuming. This study provides a fast, reliable and cost-effective alternative tool for the diagnosis of COVID-19 based on the routine blood values (RBVs) measured at admission. The dataset of the study consists of a total of 5296 patients with the same number of negative and positive COVID-19 test results and 51 routine blood values. In this study, 13 popular classifier machine learning models and the LogNNet neural network model were exanimated. The most successful classifier model in terms of time and accuracy in the detection of the disease was the histogram-based gradient boosting (HGB) (accuracy: 100%, time: 6.39 sec). The HGB classifier identified the 11 most important features (LDL, cholesterol, HDL-C, MCHC, triglyceride, amylase, UA, LDH, CK-MB, ALP and MCH) to detect the disease with 100% accuracy. In addition, the importance of single, double and triple combinations of these features in the diagnosis of the disease was discussed. We propose to use these 11 features and their binary combinations as important biomarkers for ML sensors in the diagnosis of the disease, supporting edge computing on Arduino and cloud IoT service.