ABSTRACT
BACKGROUND: On March 11, 2020, coronavirus disease (COVID-19) was declared a global threat by the World Health Organization (WHO). It quickly became apparent that reducing inpatient mortality rates and early phase prediction of possible deterioration or severe disease course relied on finding more specific biomarkers. OBJECTIVES: This retrospective study assessed initial clinical, laboratory and radiological features of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected patients and explored their impact on mortality and the course of the disease. Such efforts aimed to facilitate the identification of high-risk patients and to improve the formulation of treatment plans for these individuals. MATERIAL AND METHODS: The cohort comprised 111 consecutive adult inpatients diagnosed with COVID-19 and hospitalized in the Internal Medicine Ward of the University Clinical Center of prof. K. Gibinski of the Medical University of Silesia in Katowice, Poland, a COVID-19 Treatment Unit, between November 16, 2020 and February 15, 2021. All available clinical, laboratory and radiological findings were extracted from electronic records and assessed as possible risk factors for poor prognosis. RESULTS: Clinicasl and radiological features with higher frequency in COVID-19 non-survivors included older age, history of smoking, concomitant cardiovascular diseases, low oxygen saturation (SpO2), and high infection risk assessed on admission as well as high opacity score, percentage of opacity and percentage of high opacity in computed tomography. Non-survivors had decreased serum lymphocytes, monocytes, calcium, magnesium, and hemoglobin oxygen saturation. They also had increased red cell distribution width (RDW), C-reactive protein (CRP), procalcitonin, alkaline phosphatase (ALP), creatinine, blood urea nitrogen (BUN), D-dimer, troponin, and N-terminal prohormone of brain natriuretic peptide (NT-proBNP) levels, as well as a base deficit. CONCLUSIONS: This retrospective study identified several markers associated with a fatal course of COVID-19. The early assessment of SARS-CoV-2-infected inpatients should consider these markers.
ABSTRACT
This systematic review focuses on using artificial intelligence (AI) to detect COVID-19 infection with the help of X-ray images. Methodology: In January 2022, the authors searched PubMed, Embase and Scopus using specific medical subject headings terms and filters. All articles were independently reviewed by two reviewers. All conflicts resulting from a misunderstanding were resolved by a third independent researcher. After assessing abstracts and article usefulness, eliminating repetitions and applying inclusion and exclusion criteria, six studies were found to be qualified for this study. Results: The findings from individual studies differed due to the various approaches of the authors. Sensitivity was 72.59%-100%, specificity was 79%-99.9%, precision was 74.74%-98.7%, accuracy was 76.18%-99.81%, and the area under the curve was 95.24%-97.7%. Conclusion: AI computational models used to assess chest X-rays in the process of diagnosing COVID-19 should achieve sufficiently high sensitivity and specificity. Their results and performance should be repeatable to make them dependable for clinicians. Moreover, these additional diagnostic tools should be more affordable and faster than the currently available procedures. The performance and calculations of AI-based systems should take clinical data into account.