Performance evaluation of selected decision tree algorithms for COVID-19 diagnosis using routine clinical data

Abstract

Background: The novel 2019 Coronavirus disease (COVID-19) poses a great threat to global public health and the economy. The earlier detection of COVID-19 is the key to its treatment and mitigating the transmission of the virus. Given that Machine Learning (ML) could be potentially useful in COVID-19 identification, we compared 7 decision tree (DT) algorithms to select the best clinical diagnostic model. Methods: A hospital-based retrospective dataset was used to train the selected DT algorithms. The performance of DT models was measured using performance criteria, such as accuracy, sensitivity, specificity, receiver operating characteristic (ROC), and precision-recall curves (PRC). Finally, the best decision model was obtained based on comparing the mentioned performance criteria. Results: Based on the Gini Index (GI) scoring model, 13 diagnostic criteria, including the lung lesion existence (GI= 0217), fever (GI= 0.205), history of contact with suspected people (GI= 0.188), O 2 saturation rate in the blood (GI= 0.181), rhinorrhea (GI= 0.177), dyspnea (GI = 0.177), cough (GI = 0.159), history of taking the immunosuppressive drug (GI= 0.145), history of respiratory failure (ARDS) (GI= 0.141), lung lesion situation (GI= 0.133) and appearance (GI= 0.126), diarrhea (GI= 0.112), and nausea and vomiting (GI = 0.092) have been obtained as the most important criteria in diagnosing COVID-19. The results indicated that the J-48, with the accuracy= 0.85, F-Score= 0.85, ROC= 0.926, and PRC= 0.93, had the best performance for diagnosing COVID-19. Conclusion: According to the empirical results, it is promising to implement J-48 in health care settings to increase the accuracy and speed of COVID-19 diagnosis.

Supervised Machine Learning Approach to COVID-19 Detection Based on Clinical Data

“…According to the C4.5 decision tree, "contact with a person who has COVID-19" was determined as the first divider in identifying the infected person. Among the research that have been done with the aim of diagnosing COVID-19 based on ML algorithms in Iran, we can mention the research of Shanbehzadeh M et al ( 37 ). In order to select the best detection model, they compared 7 decision tree algorithms.…”

“…But in Shanbehzadeh M's research, "the lung lesion existence" is the most important factor identified. One of the strengths of our research compared to( 37 )is high volume dataset. Also, since our dataset is related to a province (Fars province), our results have more integrity than Shanbehzadeh M's research, which used only the data from one hospital.…”

Machine learning to analyse omic-data for COVID-19 diagnosis and prognosis

“…Brinati et al [9] proposed ML model to detect the infection of COVID-19 based on routine blood, with accuracies ranging from 82 to 86%. Some studies have explored robust ML models based on patients' conventional clinical data, disease history, epidemiological factors and other physiological characteristics to diagnose covid-19 [10,11]. A study investigated the value of Chest-tomography (CT) images for covid-19 severity assessment and clinical outcome prediction [12].…”

Hemogram‐based decision tree models for discriminating COVID‐19 from RSV in infants

“…Decision trees are efficient and reliable decision‐making algorithms, because they are characterized by high classification accuracy and simple visualization of collected data. 10 , 11 …”

“…The input variables can be continuous and categorical, and based on them, the final classification is made. Decision trees are efficient and reliable decision‐making algorithms, because they are characterized by high classification accuracy and simple visualization of collected data 10,11 …”