Can artificial intelligence predict COVID-19 mortality?

OBJECTIVE

COVID-19 infection rapidly spread across the globe and evolved into a pandemic. Artificial intelligence (AI) has been used to predict the spread of the virus and diagnose and treat the disease. In this study, we aimed to predict whether patients admitted to the intensive care unit (ICU) due to COVID-19 infection will result in mortality.

PATIENTS AND METHODS

Ninety parameters were used for each 589 ICU patient. The nine parameters with the highest effect on mortality were determined. Four hundred seventy-one patients were used to train the AI with these nine parameters. AI was tested with 118 patient data.

RESULTS

AI estimated mortality with 83% sensitivity, 84% specificity, 84% accuracy, and 0.81 F1 score. Therefore, the area under the curve was calculated as 0.91. The results indicate that mortality among COVID-19 patients admitted to the ICU can be predicted based on their laboratory parameters on the first day.

CONCLUSIONS

These findings underscore the potential benefits of utilizing AI in managing pandemics.

The novel biomarker, neopterin, can predict the severity of COVID-19

OBJECTIVE

SARS-CoV-2 infection primarily affects T-lymphocytes, particularly CD4+ and CD8+ T cells. However, there is a need for simpler and less expensive laboratory tests with predictive values comparable to CD4+ cell counts. Thus, the goal of this study was to investigate the role of neopterin levels in predicting intensive care and mortality in coronavirus disease patients in 2019.

PATIENTS AND METHODS

This retrospective study included 87 hospitalized patients who were diagnosed with COVID-19. Patients were divided into two groups: those receiving intensive care (Severe COVID-19; S-COVID-19) and those receiving non-intensive care (Moderate COVID-19; M-COVID-19). Patients' clinical characteristics, serum neopterin levels, and other laboratory data were compared across groups.

RESULTS

The average age was 63.9±155.2 years, and 44 (%) of the participants were male. WBC (p = 0.008), neutrophil (p = 0.002), HDL (p = 0.009), ferritin, calcium, albumin, LDH, APTT, lymphocyte, INR, D-dimer, troponin, prothrombin time sedimentation, and PaO2 (p = 0.001) were all associated with death. The neopterin level in the M-COVID-19 group was 3 (min-max; 3.1-5.9) and 3.2 (2.3-7) in the S-COVID-19 group, with no statistically significant difference (p = 0.456). Gender differences between groups were not significant (p = 0.183). According to the ROC analysis, if parameters such as age, D-Dimer, troponin, ferritin, albumin, LDH, CRP, procalcitonin, and PaO2 exceed the cut-off values and lymphocyte levels are below, it can predict the need for intensive care and mortality in COVID-19 patients.

CONCLUSIONS

Although we did not find statistically significant results with neopterin in terms of mortality in COVID-19 individuals in our study, more thorough, prospective, randomized controlled studies with expanded patient populations at various phases of the disease are needed.