Decision trees for early prediction of inadequate immune response to coronavirus infections: a pilot study on COVID-19.

Introduction: Few artificial intelligence models exist to predict severe forms of COVID-19. Most rely on post-infection laboratory data, hindering early treatment for high-risk individuals. Methods: This study developed a machine learning model to predict inherent risk of severe symptoms after contracting SARS-CoV-2. Using a Decision Tree trained on 153 Alpha variant patients, demographic, clinical and immunogenetic markers were considered. Model performance was assessed on Alpha and Delta variant datasets. Key risk factors included age, gender, absence of KIR2DS2 gene (alone or with HLA-C C1 group alleles), presence of 14-bp polymorphism in HLA-G gene, presence of KIR2DS5 gene, and presence of KIR telomeric region A/A. Results: The model achieved 83.01% accuracy for Alpha variant and 78.57% for Delta variant, with True Positive Rates of 80.82 and 77.78%, and True Negative Rates of 85.00% and 79.17%, respectively. The model showed high sensitivity in identifying individuals at risk. Discussion: The present study demonstrates the potential of AI algorithms, combined with demographic, epidemiologic, and immunogenetic data, in identifying individuals at high risk of severe COVID-19 and facilitating early treatment. Further studies are required for routine clinical integration.

Human Leukocyte Antigen Complex and Other Immunogenetic and Clinical Factors Influence Susceptibility or Protection to SARS-CoV-2 Infection and Severity of the Disease Course. The Sardinian Experience.

Aim: SARS-CoV-2 infection is a world-wide public health problem. Several aspects of its pathogenesis and the related clinical consequences still need elucidation. In Italy, Sardinia has had very low numbers of infections. Taking advantage of the low genetic polymorphism in the Sardinian population, we analyzed clinical, genetic and immunogenetic factors, with particular attention to HLA class I and II molecules, to evaluate their influence on susceptibility to SARS-CoV-2 infection and the clinical outcome. Method and Materials: We recruited 619 healthy Sardinian controls and 182 SARS-CoV-2 patients. Thirty-nine patients required hospital care and 143 were without symptoms, pauci-symptomatic or with mild disease. For all participants, we collected demographic and clinical data and analyzed the HLA allele and haplotype frequencies. Results: Male sex and older age were more frequent in hospitalized patients, none of whom had been vaccinated during the previous seasonal flu vaccination campaignes. Compared to the group of asymptomatic or pauci-symptomatic patients, hospitalized patients also had a higher frequency of autoimmune diseases and glucose-6-phosphate-dehydrogenase (G6PDH) deficiency. None of these patients carried the beta-thalassemia trait, a relatively common finding in the Sardinian population. The extended haplotype HLA-A*02:05, B*58:01, C*07:01, DRB1*03:01 [OR 0.1 (95% CI 0-0.6), Pc = 0.015] was absent in all 182 patients, while the HLA-C*04:01 allele and the three-loci haplotype HLA-A*30:02, B*14:02, C*08:02 [OR 3.8 (95% CI 1.8-8.1), Pc = 0.025] were more frequently represented in patients than controls. In a comparison between in-patients and home care patients, the HLA-DRB1*08:01 allele was exclusively present in the hospitalized patients [OR > 2.5 (95% CI 2.7-220.6), Pc = 0.024]. Conclusion: The data emerging from our study suggest that the extended haplotype HLA-A*02:05, B*58:01, C*07:01, DRB1*03:01 has a protective effect against SARS-CoV-2 infection in the Sardinian population. Genetic factors that resulted to have a negative influence on the disease course were presence of the HLA-DRB1*08:01 allele and G6PDH deficiency, but not the beta-thalassemic trait. Absence of influenza vaccination could be a predisposing factor for more severe disease.

Influence of Immunogenetic Biomarkers in the Clinical Outcome of HTLV-1 Infected Persons.

Human T-lymphotropic virus 1, a member of the Retroviridae family, causes a neglected, silent, persistent infection affecting circa 5 to 10 million people around the world, with biology, immune pathology, clinical diseases, epidemiology, and laboratory issues still unsolved. Most of the infected subjects are asymptomatic, but severe clinical disorders appear as a neurodegenerative disease (HTLV-1 associated myelopathy-HAM) or a lymphoprolipherative disorder (Adult T Leukemia/Lymphoma-ATLL) and in other target organs of the human body. HTLV-1 infections are frequently asymptomatic, but there is a large spectrum of diseases that have been described along the years. The mechanisms by which the virus interacts with the host, the different modes of response of the host to the infection, and the immunogenic characteristics of the host are some of the interesting and unanswered questions that may direct the outcome of the disease. The most relevant published results dealing with the genetic variations of the host, the immune response to HTLV-1 infection, and the outcome of the infection are presented herein, including Human Leucocyte Antigen (HLA), Killer Immunoglobulin-like Receptors (KIR), interleukin 6, 10, 28, Fas and Fas ligand, IFN-gamma, TNF-A, and Mannose-binding lectin. In summary, there are still several unmet research needs in the field of useful biomarkers on HTLV-1 pathogenesis.

Autoimmune hepatitis: current challenges and future prospects.

Autoimmune hepatitis (AIH) is a chronic progressive liver disease characterized by high levels of aminotransferases and autoantibodies, hypergammaglobulinemia, and interface hepatitis. AIH affects all races and all ages worldwide, regardless of sex, although a preponderance of females is a constant finding. The etiology of AIH has not been completely elucidated, but immunogenetic background and environmental parameters may contribute to its development. The most important genetic factor is human leukocyte antigens (HLAs), especially HLA-DR, whereas the role of environmental factors is not completely understood. Immunologically, disruption of the immune tolerance to autologous liver antigens may be a trigger of AIH. The diagnosis of classical AIH is fairly easy, though not without pitfalls. In contrast, the diagnosis of atypical AIH poses great challenges. There is confusion as to the definition of the disease entity and its boundaries in the diagnosis of overlap syndrome, drug-induced autoimmune hepatitis, and AIH with concomitant nonalcoholic fatty liver disease (NAFLD) or chronic hepatitis C. Centrilobular zonal necrosis is now included in the histological spectrum of AIH. However, the definition and the significance of AIH presenting with centrilobular zonal necrosis have not been examined extensively. In ~20% of AIH patients who are treated for the first time with standard therapy, remission is not achieved. The development of more effective and better tolerated novel therapies is an urgent need. In this review, we discuss the current challenges and the future prospects in relation to the diagnosis and treatment of AIH, which have been attracting considerable recent attention.