Abstract
COVID‐19 threatens millions of lives, especially elderly population and people with chronic diseases including diabetes, hypertension, cancer, and cardiovascular diseases. Rapid and effective diagnoses are vital for the isolation of infected people and starting treatment immediately to stop the spread of COVID‐19 virus. Bioinformatics techniques such as artificial intelligence should be used for collecting the hemogram and serum biochemistry data of all COVID‐19‐ infected people worldwide, even they do not show severe symptoms. These data may help find a biomarker that can be used in combination with the CT results for rapid and accurate diagnosis of COVID‐19.
Keywords: artificial intelligence, bioinformatics, COVID‐19, hemogram, pandemic, serum biochemical parameters
COVID‐19 pandemic affects millions of lives all over the world as a major public health concern. Elderly patients and people with chronic diseases including hypertension, cardiovascular diseases, cancer, and diabetes have been categorized as risk groups during pandemic [1]. There are no treatments including drugs, vaccines, or targeted therapy approaches have been found until now, therefore after diagnosis quarantine has been applied for infected individuals. Since false negative test results have been encountered and COVID‐19 symptoms can be confused with pneumonia, rapid diagnosis and patient isolation are vital to stop the spread of the disease and to cure patients, especially the ones belonging to the risk groups [2]. Diagnostic characteristics and algorithms are required for the rapid clinical diagnosis instead of suspected cases, thus isolation and treatment of patients can start immediately after diagnosis. Additionally, another risk during COVID‐19 pandemic is described as the collapsing health systems because of limited capacities worldwide [3].
Bioinformatics techniques such as machine learning have been used for infectious agents including viruses, thus collecting patient data and analyzing them via software programs may help us to find biomarkers to evaluate disease prognosis and progression. These biomarkers should be used with PCR results and computed tomography (CT) images of people infected by COVID‐19 for rapid and effective diagnosis [4]. Serum biochemical parameters and hemogram analysis are commonly used, easy to measure, routine and cheaper techniques helping diagnosis and progression of diseases [5]. Lymphopenia (lymphocyte count <1,000), increased lactate dehydrogenase levels, the alanine aminotransferase (ALT)/aspartate aminotransferase (AST) ratio, prothrombin time, creatinine, D‐dimer, creatine phosphokinase (CPK), peripheral absolute monocyte count, and absolute neutrophil count levels are tightly associated with COVID‐19 progression [6, 7]. Moreover, leukocyte and granulocyte levels are associated with disease progression as well [8].
Artificial intelligence has been used to find biomarkers for the prognosis and evaluation of progression of diseases. Besides, laboratory test ordering, data mining, interpretations of test results, early diagnosis, disease monitoring, personalized treatments, and clinical trials can be achieved by artificial learning. Therefore, we should use machine learning techniques for collecting all biochemistry and hemogram data of COVID‐19‐infected people worldwide to find biomarkers that can be used in the combination with PCR and CT results. Moreover, people infected by COVID‐19 can be tested for hemogram and serum biochemistry parameters daily basis even they do not show severe symptoms, thus progression of the COVID‐19 infection can be evaluated easily [9, 10, 11].
2. Conflict of Interest
The authors declare that they have no conflict of interest.
1. Acknowledgements
The authors gratefully acknowledge use of the services and facilities of the Koç University Research Center for Translational Medicine (KUTTAM), funded by the Presidency of Turkey, Presidency of Strategy and Budget. The content is solely the responsibility of the authors and does not necessarily represent the official views of the Presidency of Strategy and Budget.
References
- 1. Aydemir, D. , and Ulusu, N. N. (2020) Pathog. Glob. Health 114, 109–110. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 2. Aydemir, D. , and Ulusu, N. N. (2020) Travel Med. Infect. Dis. 10.1016/j.tmaid.2020.101697. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 3. Evelyne, B. , Guoting, C. , and Teresad, F. M. (2020) Swiss Med. Wkly. 150, w20216.32134111 [Google Scholar]
- 4. Belmont, J. W. , and Shaw, C. A. (2016) Expert Rev. Mol. Diagn 16, 1139–1141. [DOI] [PubMed] [Google Scholar]
- 5. Chełstowska, B. , and Kuźma‐Kozakiewicz, M. (2020) Neurol. Sci. 41, 1115–1124. [DOI] [PubMed] [Google Scholar]
- 6. Singhal, T. (2020) Indian J. Pediatr. 87, 281–286. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 7. Fan, B. E. , Chong, V. C. L. , Chan, S. S. W. , Lim, G. H. , Lim, K. G. E. , Tan, G. B. , Mucheli, S. S. , Kuperan, P. , and Ong, K. H. (2020) Am. J. Hematol. 10.1002/ajh.25774. [Epub ahead of print] [DOI] [Google Scholar]
- 8. Zheng, H. , Zhang, M. , Yang, C. , Zhang, N. , Wang, X‐C. , Yang, X‐P. , Dong, X‐Q. , and Zheng, Y‐T. (2020) Cell Mol. Immunol. 17, 541–543. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 9. Gruson, D. , Helleputte, T. , Rousseau, P. , and Gruson, D. (2019) Clin. Biochem. 69, 1–7. [DOI] [PubMed] [Google Scholar]
- 10. Sanchez‐Pinto, L. N. , Luo, Y. , and Churpek, M. M. (2018) Chest 154, 1239–1248. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 11. Miller, D. D. , and Brow, E. W. (2018) Am. J. Med. 131, 129–133. [DOI] [PubMed] [Google Scholar]