Comparison of predictors for terminal disease progression in simian immunodeficiency virus/simian-HIV-infected rhesus macaques

Artificial Intelligence and Machine Learning Based Prediction of Viral Load and CD4 Status of People Living with HIV (PLWH) on Anti-Retroviral Treatment in Gedeo Zone Public Hospitals

Background

Despite the success made in scaling up HIV treatment activities, there remains a tremendous unmet demand for the monitoring of the disease progression and treatment success, which threatens HIV/AIDS treatment and control. This research presented the assessments of viral load and CD4 classification of adults enrolled in ART care using machine learning algorithms.

Methods

We trained, validated, and tested eight machine learning (ML) classifier algorithms with historical data, including demographics, clinical, and laboratory data. Data were extracted from the ART registry database of Yirgacheffe Primary Hospital and Dilla University Referral Hospital. ML classifiers were trained to predict virological failure (viral load >1000 copies/mL) and poor CD4 (CD4 cell count <200 cells/mL). The model predictive performances were evaluated using accuracy, sensitivity, specificity, precision, f1-score, F-beta scores, and AUC.

Results

The mean age of the sample participants was 41.6 years (SD = 10.9). The experimental results showed that XGB classifier ranked as the best algorithm for viral load prediction in terms of sensitivity (97%), f1-score (96%), AUC (0.99), accuracy (96%), followed by RF. The GB classifier exhibited a better predictive capability in predicting participants with a CD4 cell count <200 cells/mL.

Conclusion

In this study, the XGB and RF models had the highest accuracy and outperformed on various evaluation metrics among the models examined for viral load classification. In the prediction of participants CD4, GB model had the highest accuracy.

Early treatment with anti-α4β7 antibody facilitates increased gut macrophage maturity in SIV-infected rhesus macaques

Despite advances in combination antiretroviral therapy (cART), people living with HIV (PLWH) continue to experience gastrointestinal dysfunction. Infusions of anti-α4β7 monoclonal antibodies (mAbs) have been proposed to increase virologic control during simian immunodeficiency virus (SIV) infection in macaques with mixed results. Recent evidences suggested that therapeutic efficacy of vedolizumab (a humanized anti-α4β7 mAb), during inflammatory bowel diseases depends on microbiome composition, myeloid cell differentiation, and macrophage phenotype. We tested this hypothesis in SIV-infected, anti-α4β7 mAb-treated macaques and provide flow cytometric and microscopic evidence that anti-α4β7 administered to SIV-infected macaques increases the maturity of macrophage phenotypes typically lost in the small intestines during SIV disease progression. Further, this increase in mature macrophage phenotype was associated with tissue viral loads. These phenotypes were also associated with dysbiosis markers in the gut previously identified as predictors of HIV replication and immune activation in PLWH. These findings provide a novel model of anti-α4β7 efficacy offering new avenues for targeting pathogenic mucosal immune response during HIV/SIV infection.

Mice with humanized immune system as novel models to study HIV-associated pulmonary hypertension

People living with HIV and who receive antiretroviral therapy have a significantly improved lifespan, compared to the early days without therapy. Unfortunately, persisting viral replication in the lungs sustains chronic inflammation, which may cause pulmonary vascular dysfunction and ultimate life-threatening Pulmonary Hypertension (PH). The mechanisms involved in the progression of HIV and PH remain unclear. The study of HIV-PH is limited due to the lack of tractable animal models that recapitulate infection and pathobiological aspects of PH. On one hand, mice with humanized immune systems (hu-mice) are highly relevant to HIV research but their suitability for HIV-PH research deserves investigation. On another hand, the Hypoxia-Sugen is a well-established model for experimental PH that combines hypoxia with the VEGF antagonist SU5416. To test the suitability of hu-mice, we combined HIV with either SU5416 or hypoxia. Using right heart catheterization, we found that combining HIV+SU5416 exacerbated PH. HIV infection increases human pro-inflammatory cytokines in the lungs, compared to uninfected mice. Histopathological examinations showed pulmonary vascular inflammation with arterial muscularization in HIV-PH. We also found an increase in endothelial-monocyte activating polypeptide II (EMAP II) when combining HIV+SU5416. Therefore, combinations of HIV with SU5416 or hypoxia recapitulate PH in hu-mice, creating well-suited models for infectious mechanistic pulmonary vascular research in small animals.

Monocytes in HIV and SIV Infection and Aging: Implications for Inflamm-Aging and Accelerated Aging

Before the antiretroviral therapy (ART) era, people living with HIV (PLWH) experienced complications due to AIDS more so than aging. With ART and the extended lifespan of PLWH, HIV comorbidities also include aging-most likely due to accelerated aging-as well as a cardiovascular, neurocognitive disorders, lung and kidney disease, and malignancies. The broad evidence suggests that HIV with ART is associated with accentuated aging, and that the age-related comorbidities occur earlier, due in part to chronic immune activation, co-infections, and possibly the effects of ART alone. Normally the immune system undergoes alterations of lymphocyte and monocyte populations with aging, that include diminished naïve T- and B-lymphocyte numbers, a reliance on memory lymphocytes, and a skewed production of myeloid cells leading to age-related inflammation, termed "inflamm-aging". Specifically, absolute numbers and relative proportions of monocytes and monocyte subpopulations are skewed with age along with myeloid mitochondrial dysfunction, resulting in increased accumulation of reactive oxygen species (ROS). Additionally, an increase in biomarkers of myeloid activation (IL-6, sCD14, and sCD163) occurs with chronic HIV infection and with age, and may contribute to immunosenescence. Chronic HIV infection accelerates aging; meanwhile, ART treatment may slow age-related acceleration, but is not sufficient to stop aging or age-related comorbidities. Overall, a better understanding of the mechanisms behind accentuated aging with HIV and the effects of myeloid activation and turnover is needed for future therapies.