Artificial neural network based prediction of the lung tissue involvement as an independent in-hospital mortality and mechanical ventilation risk factor in COVID-19.

INTRODUCTION: During COVID-19 pandemic, artificial neural network (ANN) systems have been providing aid for clinical decisions. However, to achieve optimal results, these models should link multiple clinical data points to simple models. This study aimed to model the in-hospital mortality and mechanical ventilation risk using a two step approach combining clinical variables and ANN-analyzed lung inflammation data. METHODS: A data set of 4317 COVID-19 hospitalized patients, including 266 patients requiring mechanical ventilation, was analyzed. Demographic and clinical data (including the length of hospital stay and mortality) and chest computed tomography (CT) data were collected. Lung involvement was analyzed using a trained ANN. The combined data were then analyzed using unadjusted and multivariate Cox proportional hazards models. RESULTS: Overall in-hospital mortality associated with ANN-assigned percentage of the lung involvement (hazard ratio [HR]: 5.72, 95% confidence interval [CI]: 4.4-7.43, p < 0.001 for the patients with >50% of lung tissue affected by COVID-19 pneumonia), age category (HR: 5.34, 95% CI: 3.32-8.59 for cases >80 years, p < 0.001), procalcitonin (HR: 2.1, 95% CI: 1.59-2.76, p < 0.001, C-reactive protein level (CRP) (HR: 2.11, 95% CI: 1.25-3.56, p = 0.004), glomerular filtration rate (eGFR) (HR: 1.82, 95% CI: 1.37-2.42, p < 0.001) and troponin (HR: 2.14, 95% CI: 1.69-2.72, p < 0.001). Furthermore, the risk of mechanical ventilation is also associated with ANN-based percentage of lung inflammation (HR: 13.2, 95% CI: 8.65-20.4, p < 0.001 for patients with >50% involvement), age, procalcitonin (HR: 1.91, 95% CI: 1.14-3.2, p = 0.14, eGFR (HR: 1.82, 95% CI: 1.2-2.74, p = 0.004) and clinical variables, including diabetes (HR: 2.5, 95% CI: 1.91-3.27, p < 0.001), cardiovascular and cerebrovascular disease (HR: 3.16, 95% CI: 2.38-4.2, p < 0.001) and chronic pulmonary disease (HR: 2.31, 95% CI: 1.44-3.7, p < 0.001). CONCLUSIONS: ANN-based lung tissue involvement is the strongest predictor of unfavorable outcomes in COVID-19 and represents a valuable support tool for clinical decisions.

Immune restoration affects 10-year survival in people living with HIV/AIDS.

INTRODUCTION: In recent years, a reduction in the life expectancy gap between people living with HIV (PLWH) and the general population has been observed, irrespective of CD4 lymphocyte count, due to widespread access to antiretroviral treatment. The increase in the life expectancy of PLWH has increased awareness of both the ageing process and gender discrepancies in immune restoration and survival. MATERIALS AND METHODS: Longitudinal data were collected for 2240 patients followed up at the Hospital for Infectious Diseases in Warsaw, Poland (n = 1482), and the Department of Acquired Immunodeficiency, Pomeranian Medical University, Szczecin, Poland (n = 758). Immune restoration was measured from the time of starting combination antiretroviral therapy until achieving 500 CD4 lymphocytes/µL, 800 CD4 lymphocytes/µL, and CD4/CD8 lymphocyte ratios of > 0.8 and > 1.0. Full recovery was achieved when the patient was restored to both 800 CD4 lymphocytes/µL and a CD4/CD8 lymphocyte ratio > 1.0. RESULTS: For all endpoints, immune restoration had a protective effect by reducing mortality. Patients who achieved immune restoration had a greater chance of reduced mortality than those who did not achieve immune restoration: for CD4 count > 500 cells/µL, HR = 5.4 (interquartile range: 3.09-9.41), p < 0.001; for CD4 > 800 cells/µL, HR = 5.37 (2.52-11.43), p < 0.001; for CD4/CD8 ratio > 0.8, HR = 3.16 (1.81-5.51), p < 0.001; for CD4/CD8 ratio > 1.0, HR = 2.67 (1.49-5.24), p = 0.001, and for full immune recovery, HR = 3.62 (1.63-8.04), p = 0.002. CONCLUSIONS: Immune restoration remains a powerful factor in improving the survival of PLWH, regardless of the speed of recovery.

Factors Influencing Immune Restoration in People Living with HIV/AIDS.

Introduction: Immune restoration is a key clinical aspect that is pursued in the care of human immunodeficiency virus (HIV)-infected patients. Despite effective antiretroviral treatment and undetectable viremia, immune recovery is often incomplete. Materials and methods: Data from 311 Caucasian patients were collected. SNP in CCR2(rs1799864), CX3CR1(rs3732378), HLAC-35(rs9264942), and CCR5(promoter, rs1799988); a 32bp deletion(Δ32) in CCR5; and HLA-B*5701 genotypes were correlated with clinical data and selected endpoints. Kaplan−Meier and Cox proportional hazards models were used to analyze the effects of genetic factors over time. Results: For HLA-B*5701, the effect on the CD4+/CD8+ >0.8 cell ratio was lost within 48 months (HR = 2.04, 95% CI: 1.04−4.03), and the effect on the CD4+ cell count >500 cells/µL was lost within 12 months (HR = 2.12, CI: 1.11−4.04). The effect of CCR2 GG on the CD4+/CD8+ >0.8 cell ratio was lost within 36 months (HR = 1.7, CI: 1.05−2.75). For CCR5 wt/Δ32, the effect on the CD4+/CD8+ >1.0 cell ratio was lost within 24 months (HR = 2.0, CI: 1.08−3.69), and the effect on the CD4+ >800 cells/µL cell count was lost within 18 months (HR = 1.98, CI: 1.14−4.73). Conclusions: Selected genetic polymorphisms, namely CCR2 GG and CCR5 Δ32, and the presence of the HLA-B*5701 allele positively influenced immune restoration in cART-treated patients with HIV/AIDS.