COVID-19 mortality prediction in Hungarian ICU settings implementing random forest algorithm.

The emergence of newer SARS-CoV-2 variants of concern (VOCs) profoundly changed the ICU demography; this shift in the virus's genotype and its correlation to lethality in the ICUs is still not fully investigated. We aimed to survey ICU patients' clinical and laboratory parameters in correlation with SARS-CoV-2 variant genotypes to lethality. 503 COVID-19 ICU patients were included in our study beginning in January 2021 through November 2022 in Hungary. Furthermore, we implemented random forest (RF) as a potential predictor regarding SARS-CoV-2 lethality among 649 ICU patients in two ICU centers. Survival analysis and comparison of hypertension (HT), diabetes mellitus (DM), and vaccination effects were conducted. Logistic regression identified DM as a significant mortality risk factor (OR: 1.55, 95% CI 1.06-2.29, p = 0.025), while HT showed marginal significance. Additionally, vaccination demonstrated protection against mortality (p = 0.028). RF detected lethality with 81.42% accuracy (95% CI 73.01-88.11%, [AUC]: 91.6%), key predictors being PaO2/FiO2 ratio, lymphocyte count, and chest Computed Tomography Severity Score (CTSS). Although a smaller number of patients require ICU treatment among Omicron cases, the likelihood of survival has not proportionately increased for those who are admitted to the ICU. In conclusion, our RF model supports more effective clinical decision-making among ICU COVID-19 patients.

Diagnostic accuracy of SARS-CoV-2 Panbio™ rapid antigen diagnostic tests in a 4,440-case clinical follow-up.

Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) Rapid Antigen Detection Testing (RADT) has been subjected to several evaluations in reference to diagnostic accuracy, ranging from small scale up to large population studies including nation-wide community-based studies. All confirmed the diagnostic accuracy of the tests which were strongly dependent upon the infection's population prevalence. In our retrospective study, parallel SARS-CoV-2 Panbio™ RADT assay, including real-time reverse transcription quantitative polymerase chain reaction (RT-qPCR) tests, were aimed to evaluate diagnostic performance regarding the rapid antigen diagnostic testing. Out of 4,440 paired tests, 609 samples tested positive using RT-qPCR, resulting in a prevalence of 13.7%. Panbio detected 251 (5.7%) positive tested samples. Overall sensitivity was 41.2% (95% CI 37.4-45.2%) and overall specificity was 99.7% (95% CI 99.4-99.8%). Positive predictive value (PPV) was 95.1% (95% CI 91.8-97.1%) and the negative predictive value (NPV) was 91.4% (95% CI 90.5-92.2%). RADT sensitivity increased with stratification in reference to the results according to PCR Cycle threshold (Ct) and presence of the symptoms considerably influenced PPV and NPV. Sensitivity in the group of Ct values ≤ 20 was 91.2%, 68.6% within the Ct range of 20-25, 47.9% in the group of Ct values between 25 and 30, and 12.6% in the group of Ct values between 30 and 35. A follow-up of the positive cases aligned with RT-qPCR testing and comparison of the general population enrolled in the testing in which the fatal cases occurred enabled us to estimate real clinical diagnostic performance regarding the SARS-CoV-2 Panbio RADT. Based upon our results, we recommend the SARS-CoV-2 Panbio RADT tests be carried out as the primary test, without parallel PCR testing, only among high population prevalence rates of the infection and to be used for symptomatic individuals with average or low severe disease developmental risk. In the case of high risk regarding the development of severe infection complications, a parallel SARS-CoV-2 RT-qPCR is needed to be carried out to attain proper diagnostic accuracy and avoid delaying appropriate medical care.