Predictive model and risk analysis for coronary heart disease in people living with HIV using machine learning.

OBJECTIVE: This study aimed to construct a coronary heart disease (CHD) risk-prediction model in people living with human immunodeficiency virus (PLHIV) with the help of machine learning (ML) per electronic medical records (EMRs). METHODS: Sixty-one medical characteristics (including demography information, laboratory measurements, and complicating disease) readily available from EMRs were retained for clinical analysis. These characteristics further aided the development of prediction models by using seven ML algorithms [light gradient-boosting machine (LightGBM), support vector machine (SVM), eXtreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), decision tree, multilayer perceptron (MLP), and logistic regression]. The performance of this model was assessed using the area under the receiver operating characteristic curve (AUC). Shapley additive explanation (SHAP) was further applied to interpret the findings of the best-performing model. RESULTS: The LightGBM model exhibited the highest AUC (0.849; 95% CI, 0.814-0.883). Additionally, the SHAP plot per the LightGBM depicted that age, heart failure, hypertension, glucose, serum creatinine, indirect bilirubin, serum uric acid, and amylase can help identify PLHIV who were at a high or low risk of developing CHD. CONCLUSION: This study developed a CHD risk prediction model for PLHIV utilizing ML techniques and EMR data. The LightGBM model exhibited improved comprehensive performance and thus had higher reliability in assessing the risk predictors of CHD. Hence, it can potentially facilitate the development of clinical management techniques for PLHIV care in the era of EMRs.

HERVK-mediated regulation of neighboring genes: implications for breast cancer prognosis.

Human endogenous retroviruses (HERVs) are the remnants of ancient retroviral infections integrated into the human genome. Although most HERVs are silenced or rendered inactive by various regulatory mechanisms, they retain the potential to influence the nearby genes. We analyzed the regulatory map of 91 HERV-Ks on neighboring genes in human breast cancer and investigated the impact of HERV-Ks on the tumor microenvironment (TME) and prognosis of breast cancer. Nine RNA-seq datasets were obtained from GEO and NCBI SRA. Differentially expressed genes and HERV-Ks were analyzed using DESeq2. Validation of high-risk prognostic candidate genes using TCGA data. These included Overall survival (multivariate Cox regression model), immune infiltration analysis (TIMER), tumor mutation burden (maftools), and drug sensitivity analysis (GSCA). A total of 88 candidate genes related to breast cancer prognosis were screened, of which CD48, SLAMF7, SLAMF1, IGLL1, IGHA1, and LRRC8A were key genes. Functionally, these six key genes were significantly enriched in some immune function-related pathways, which may be associated with poor prognosis for breast cancer (p = 0.00016), and the expression levels of these genes were significantly correlated with the sensitivity of breast cancer treatment-related drugs. Mechanistically, they may influence breast cancer development by modulating the infiltration of various immune cells into the TME. We further experimentally validated these genes to confirm the results obtained from bioinformatics analysis. This study represents the first report on the regulatory potential of HERV-K in the neighboring breast cancer genome. We identified three key HERV-Ks and five neighboring genes that hold promise as novel targets for future interventions and treatments for breast cancer.

Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records.

Background: Cytopenia is a frequent complication among HIV-infected patients who require hospitalization. It can have a negative impact on the treatment outcomes for these patients. However, by leveraging machine learning techniques and electronic medical records, a predictive model can be developed to evaluate the risk of cytopenia during hospitalization in HIV patients. Such a model is crucial for designing a more individualized and evidence-based treatment strategy for HIV patients. Method: The present study was conducted on HIV patients who were admitted to Guangxi Chest Hospital between June 2016 and October 2021. We extracted a total of 66 clinical features from the electronic medical records and employed them to train five machine learning prediction models (artificial neural network [ANN], adaptive boosting [AdaBoost], k-nearest neighbour [KNN] and support vector machine [SVM], decision tree [DT]). The models were tested using 20% of the data. The performance of the models was evaluated using indicators such as the area under the receiver operating characteristic curve (AUC). The best predictive models were interpreted using the shapley additive explanation (SHAP). Result: The ANN models have better predictive power. According to the SHAP interpretation of the ANN model, hypoproteinemia and cancer were the most important predictive features of cytopenia in HIV hospitalized patients. Meanwhile, the lower hemoglobin-to-RDW ratio (HGB/RDW), low-density lipoprotein cholesterol (LDL-C) levels, CD4+ T cell counts, and creatinine clearance (Ccr) levels increase the risk of cytopenia in HIV hospitalized patients. Conclusion: The present study constructed a risk prediction model for cytopenia in HIV patients during hospitalization with machine learning and electronic medical record information. The prediction model is important for the rational management of HIV hospitalized patients and the personalized treatment plan setting.

Epidemiology of extrapulmonary tuberculosis in central Guangxi from 2016 to 2021.

The burden of extrapulmonary tuberculosis (EPTB) has gradually increased in recent years, but not enough epidemiological data is available from central Guangxi. To better understand the epidemiology of EPTB in central Guangxi and identify risk factors associated with them, we retrospectively investigated the epidemiology of tuberculosis (TB), especially EPTB, among patients admitted to the Chest Hospital of Guangxi Zhuang Autonomous Region between 2016 and 2021. We excluded those infected with both pulmonary tuberculosis (PTB) and EPTB, reported the proportion and incidence of PTB or EPTB, and compared the demographic characteristics and risk factors of EPTB and PTB cases using univariate and multivariate logistic regression models. Among 30,893 TB patients, 67.25% (20,774) had PTB and 32.75% (10,119) had EPTB. Among EPTB, pleural, skeletal, lymphatic, pericardial, meningeal, genitourinary, intestinal, and peritoneal TB accounted for 49.44%, 27.20%, 8.55%, 4.39%, 3.36%, 1.48%, 0.87%, and 0.79%, respectively. Patients who were younger (age < 25), from rural areas, Zhuang and other ethnic groups, and diagnosed with anemia and HIV infection were more likely to develop EPTB. However, patients with diabetes and COPD were less likely to have EPTB. From 2016 to 2021, the proportion of PTB cases decreased from 69.73 to 64.07%. The percentage of EPTB cases increased from 30.27 to 35.93%, with the largest increase in skeletal TB from 21.48 to 34.13%. The epidemiology and risk factors of EPTB in central Guangxi are different from those of PTB. The incidence of EPTB is increasing and further studies are needed to determine the reasons for it.

Anemia and opportunistic infections in hospitalized people living with HIV: a retrospective study.

BACKGROUND: There is a high prevalence of anemia among people living with HIV in Guangxi, China. Therefore, we investigated anemia and opportunistic infections in hospitalized people living with HIV and explored the risk factors related to anemia in people living with HIV to actively prevent anemia in people living with HIV. METHODS: We retrospectively studied people living with HIV admitted to Guangxi Chest Hospital from June 2016 to October 2021. Detailed information on the sociodemographic and clinical features of the participants was collected. The X2 test was used to compare the prevalence between the anemic and non-anemic groups. The logistic regression analysis was applied to exclude confounding factors and identify factors related to anemia. RESULTS: Among 5645 patients with HIV, 1525 (27.02%) had anemia. The overall prevalence of mild, moderate, and severe anemia was 4.66%, 14.08%, and 8.27%, respectively. The factors significantly related to increased risk of anemia were CD4 count < 50 cells/µl (aOR = 2.221, 95% CI = [1.775, 2.779]), CD4 count 50-199 cells/µl (aOR = 1.659, 95% CI = [1.327, 2. 073]), female (aOR = 1.644, 95% CI = [1.436, 1.881]) co-infected with HCV (aOR = 1.465, 95% CI = [1.071, 2.002]), PM (aOR = 2.356, 95% CI = [1.950, 2.849]), or TB (aOR = 1.198, 95% CI = [1.053, 1.365]). CONCLUSIONS: Within Guangxi of China, 27.02% of hospitalized people living with HIV presented with anemia. Most patients with anemia were in the mild to moderate stage. The low CD4 count, female gender, and concomitant infection with Penicillium marneffei, Hepatitis C virus, or Tuberculosis were independent correlates of anemia. Thus, these findings would be helpful to clinicians in preventing and intervening in anemia in people living with HIV.

Screening and Identification of Human Endogenous Retrovirus-K mRNAs for Breast Cancer Through Integrative Analysis of Multiple Datasets.

Objective: Human endogenous retroviruses (HERVs) make up 8% of the human genome. HERVs are biologically active elements related to multiple diseases. HERV-K, a subfamily of HERVs, has been associated with certain types of cancer and suggested as an immunologic target in some tumors. The expression levels of HERV-K in breast cancer (BCa) have been studied as biomarkers and immunologic therapeutic targets. However, HERV-K has multiple copies in the human genome, and few studies determined the transcriptional profile of HERV-K copies across the human genome for BCa. Methods: Ninety-one HERV-K indexes with entire proviral sequences were used as the reference database. Nine raw sequencing datasets with 243 BCa and 137 control samples were mapped to this database by Salmon software. The differential proviral expression across several groups was analyzed by DESeq2 software. Results: First, the clustering of each dataset demonstrated that these 91 HERV-K proviruses could well cluster the BCa and control samples when the normal controls were normal cells or healthy donor tissues. Second, several common HERV-K proviruses that are closely related with BCa risk were significantly differentially expressed (p adj < 0.05 and absolute log2FC > 1.5) in the tissues and cell lines. Additionally, almost all the HERV-K proviruses had higher expression in BCa tissue than in healthy donor tissue. Notably, we first found the expression of 17p13.1 provirus that located with TP53 should regulate TP53 expression in ER+ and HER2+ BCa. Conclusion: The expression profiling of these 91 HERV-K proviruses can be used as biomarkers to distinguish individuals with BCa and healthy controls. Some proviruses, especially 17p13.1, were strongly associated with BCa risk. The results suggest that HERV-K expression profiles may be appropriate biomarkers and targets for BCa.

Emerging Severe Acute Respiratory Syndrome Coronavirus 2 Mutation Hotspots Associated With Clinical Outcomes and Transmission.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the cause of the ongoing coronavirus disease 2019 (COVID-19) pandemic. Understanding the influence of mutations in the SARS-CoV-2 gene on clinical outcomes is critical for treatment and prevention. Here, we analyzed all high-coverage complete SARS-CoV-2 sequences from GISAID database from January 1, 2020, to January 1, 2021, to mine the mutation hotspots associated with clinical outcome and developed a model to predict the clinical outcome in different epidemic strains. Exploring the cause of mutation based on RNA-dependent RNA polymerase (RdRp) and RNA-editing enzyme, mutation was more likely to occur in severe and mild cases than in asymptomatic cases, especially A > G, C > T, and G > A mutations. The mutations associated with asymptomatic outcome were mainly in open reading frame 1ab (ORF1ab) and N genes; especially R6997P and V30L mutations occurred together and were correlated with asymptomatic outcome with high prevalence. D614G, Q57H, and S194L mutations were correlated with mild and severe outcome with high prevalence. Interestingly, the single-nucleotide variant (SNV) frequency was higher with high percentage of nt14408 mutation in RdRp in severe cases. The expression of ADAR and APOBEC was associated with clinical outcome. The model has shown that the asymptomatic percentage has increased over time, while there is high symptomatic percentage in Alpha, Beta, and Gamma. These findings suggest that mutation in the SARS-CoV-2 genome may have a direct association with clinical outcomes and pandemic. Our result and model are helpful to predict the prevalence of epidemic strains and to further study the mechanism of mutation causing severe disease.

Estrus-Cycle Regulation of Cortical Inhibition.

Female mammals experience cyclical changes in sexual receptivity known as the estrus cycle. Little is known about how estrus affects the cortex, although alterations in sensation, cognition and the cyclical occurrence of epilepsy suggest brain-wide processing changes. We performed in vivo juxtacellular and whole-cell recordings in somatosensory cortex of female rats and found that the estrus cycle potently altered cortical inhibition. Fast-spiking interneurons were strongly activated with social facial touch and varied their ongoing activity with the estrus cycle and estradiol in ovariectomized females, while regular-spiking excitatory neurons did not change. In situ hybridization for estrogen receptor ß (Esr2) showed co-localization with parvalbumin-positive (PV+) interneurons in deep cortical layers, mirroring the laminar distribution of our physiological findings. The fraction of neurons positive for estrogen receptor ß (Esr2) and PV co-localization (Esr2+PV+) in cortical layer V was increased in proestrus. In vivo and in vitro experiments confirmed that estrogen acts locally to increase fast-spiking interneuron excitability through an estrogen-receptor-ß-dependent mechanism.

Immune responses of mice immunized by DNA plasmids encoding PCV2 ORF 2 gene, porcine IL-15 or the both.

Porcine circovirus type 2 (PCV2) is associated with many kinds of diseases including postweaning multisystemic wasting syndrome (PMWS). It affects the immune system of swine and causes huge epidemic losses every year. In our previous study, we provided evidence that DNA plasmid bearing porcine IL-15 (pVAX-pIL-15) might serve as an immune enhancer for DNA plasmid encoding porcine reproductive and respiratory syndrome virus GP5 gene. In this study, PCV2 open reading frame (ORF)2 gene was cloned into the eukaryotic expression vector pVAX, resulting in the plasmid pVAX-PCV2-ORF2. Transient expression of the plasmid in BHK-21 cells could be detected using immunofluorescence assay. Experimental mice were divided into 5 groups and immunized with PBS, pVAX, pVAX-pIL-15, pVAX-PCV2-ORF2 or pVAX-pIL-15 plus pVAX-PCV2-ORF2. The results showed that the mice co-inoculated with pVAX-PCV2-ORF2 plus pVAX-pIL-15 had higher humoral and cellular immune responses than the others. In addition, DNA plasmid bearing PCV2 ORF2 gene had a protective effect against challenge with PCV2 in mice which could be promoted with the utilization of pIL-15.