Detecting the most critical clinical variables of COVID-19 breakthrough infection in vaccinated persons using machine learning.

Background: COVID-19 vaccines offer different levels of immune protection but do not provide 100% protection. Vaccinated persons with pre-existing comorbidities may be at an increased risk of SARS-CoV-2 breakthrough infection or reinfection. The aim of this study is to identify the critical variables associated with a higher probability of SARS-CoV-2 breakthrough infection using machine learning. Methods: A dataset comprising symptoms and feedback from 257 persons, of whom 203 were vaccinated and 54 unvaccinated, was used for the investigation. Three machine learning algorithms - Deep Multilayer Perceptron (Deep MLP), XGBoost, and Logistic Regression - were trained with the original (imbalanced) dataset and the balanced dataset created by using the Random Oversampling Technique (ROT), and the Synthetic Minority Oversampling Technique (SMOTE). We compared the performance of the classification algorithms when the features highly correlated with breakthrough infection were used and when all features in the dataset were used. Result: The results show that when highly correlated features were considered as predictors, with Random Oversampling to address data imbalance, the XGBoost classifier has the best performance (F1 = 0.96; accuracy = 0.96; AUC = 0.98; G-Mean = 0.98; MCC = 0.88). The Deep MLP had the second best performance (F1 = 0.94; accuracy = 0.94; AUC = 0.92; G-Mean = 0.70; MCC = 0.42), while Logistic Regression had less accurate performance (F1 = 0.89; accuracy = 0.88; AUC = 0.89; G-Mean = 0.89; MCC = 0.68). We also used Shapley Additive Explanations (SHAP) to investigate the interpretability of the models. We found that body temperature, total cholesterol, glucose level, blood pressure, waist circumference, body weight, body mass index (BMI), haemoglobin level, and physical activity per week are the most critical variables indicating a higher risk of breakthrough infection. Conclusion: These results, evident from our unique data source derived from apparently healthy volunteers with cardiovascular risk factors, follow the expected pattern of positive or negative correlations previously reported in the literature. This information strengthens the body of knowledge currently applied in public health guidelines and may also be used by medical practitioners in the future to reduce the risk of SARS-CoV-2 breakthrough infection.

HIV test-and-treat policy improves clinical outcomes in Zambian adults from Southern Province: a multicenter retrospective cohort study.

Background: Globally, most countries have implemented a test-and-treat policy to reduce morbidity and mortality associated with HIV infection. However, the impact of this strategy has not been critically appraised in many settings, including Zambia. We evaluated the retention and clinical outcomes of adults enrolled in antiretroviral therapy (ART) and assessed the impact of the test-and-treat policy. Methods: We conducted a retrospective cohort study among 6,640 individuals who initiated ART between January 1, 2014 and July 31, 2016 [before test-and-treat cohort (BTT), n = 2,991] and between August 1, 2016 and October 1, 2020 [after test-and-treat cohort (ATT), n = 3,649] in 12 districts of the Southern province. To assess factors associated with retention, we used logistic regression (xtlogit model). Results: The median age [interquartile range (IQR)] was 34.8 years (28.0, 42.1), and 60.2% (n = 3,995) were women. The overall retention was 83.4% [95% confidence interval (CI) 82.6, 84.4], and it was significantly higher among the ATT cohort, 90.6 vs. 74.8%, p < 0.001. The reasons for attrition were higher in the BTT compared to the ATT cohorts: stopped treatment (0.3 vs. 0.1%), transferred out (9.3 vs. 3.2%), lost to follow-up (13.5 vs. 5.9%), and death (1.4 vs. 0.2%). Retention in care was significantly associated with the ATT cohort, increasing age and baseline body mass index (BMI), rural residence, and WHO stage 2, while non-retention was associated with never being married, divorced, and being in WHO stage 3. Conclusion: The retention rate and attrition factors improved in the ATT compared to the BTT cohorts. Drivers of retention were test-and-treat policy, older age, high BMI, rural residence, marital status, and WHO stage 1. Therefore, there is need for interventions targeting young people, urban residents, non-married people, and those in the symptomatic WHO stages and with low BMI. Our findings highlight improved ART retention after the implementation of the test-and-treat policy.

Evaluating determinants of treatment outcomes among tuberculosis patients in the mining district of Butha Buthe, Lesotho.

Background: Before the COVID-19 pandemic, tuberculosis (TB) was the leading infectious cause of death globally. In low- and middle-income countries (LMIC) including Lesotho, treatment outcome is lower than the recommended rate and poor TB treatment outcomes remain a programmatic challenge. The aim of this study was to determine unfavourable treatment outcomes and associated risk factors among TB patients in Butha Buthe district. Methods: This was a retrospective record review of TB patients registered between January 2015 and December 2020. Data were collected from TB registers and patients' files and entered Microsoft Excel 2012. Analysis was conducted using R and INLA statistical software. Descriptive statistics were presented as frequencies and percentages. The differences between groups were compared using Pearson's X 2 test in bivariate analysis. Frailty Cox proportional hazards model was used to determine the risk of unfavourable outcomes among the variables. Results: A total of 1792 TB patients were enrolled in the study with about 70% males (1,257). Majority (71.7%) of the patients were between 20 and 59 years old, with 48% of the patients being unemployed. Almost a quarter of the patients (23.1%) had unfavourable outcomes with death (342 patients) being the most common unfavourable outcome. Our study has shown that patients older than 59 years, and unemployment increased the risk of having unfavourable treatment outcomes. Death was the most common unfavourable outcome followed by lost-to-follow up. We also observed that the patients in the initiation phase of treatment died at a faster rate compared to those in the continuation phase (p=0.02). Conclusion: TB treatment programs should have efficient follow-up methods geared more toward elderly patients. Active case finding to identify population at risk should be part of a TB program which would improve early diagnosis and treatment initiation. Patients in the intensive phase of the treatment program should be monitored more closely to determine adverse drug effects and nutritional requirement to prevent death during this phase of treatment.

Latent class analysis: an innovative approach for identification of clinical and laboratory markers of disease severity among COVID-19 patients admitted to the intensive care unit.

Objective: The aim of this study was to identify clinical and laboratory phenotype distribution patterns and their usefulness as prognostic markers in COVID-19 patients admitted to the intensive care unit (ICU) at Tygerberg Hospital, Cape Town. Methods and results: A latent class analysis (LCA) model was applied in a prospective, observational cohort study. Data from 343 COVID-19 patients were analysed. Two distinct phenotypes (1 and 2) were identified, comprising 68.46% and 31.54% of patients, respectively. The phenotype 2 patients were characterized by increased coagulopathy markers (D-dimer, median value 1.73 ng/L vs 0.94 ng/L; p < 0.001), end-organ dysfunction (creatinine, median value 79 µmol/L vs 69.5 µmol/L; p < 0.003), under-perfusion markers (lactate, median value 1.60 mmol/L vs 1.20 mmol/L; p < 0.001), abnormal cardiac function markers (median N-terminal pro-brain natriuretic peptide (NT-proBNP) 314 pg/ml vs 63.5 pg/ml; p < 0.001 and median high-sensitivity cardiac troponin (Hs-TropT) 39 ng/L vs 12 ng/L; p < 0.001), and acute inflammatory syndrome (median neutrophil-to-lymphocyte ratio 15.08 vs 8.68; p < 0.001 and median monocyte value 0.68 × 109/L vs 0.45 × 109/L; p < 0.001). Conclusion: The identification of COVID-19 phenotypes and sub-phenotypes in ICU patients could help as a prognostic marker in the day-to-day management of COVID-19 patients admitted to the ICU.

Predicting COVID-19 outcomes from clinical and laboratory parameters in an intensive care facility during the second wave of the pandemic in South Africa.

Background: The second wave of coronavirus disease 2019 (COVID-19) in South Africa was caused by the Beta variant of severe acute respiratory syndrome coronavirurus-2. This study aimed to explore clinical and biochemical parameters that could predict outcome in patients with COVID-19. Methods: A prospective study was conducted between 5 November 2020 and 30 April 2021 among patients with confirmed COVID-19 admitted to the intensive care unit (ICU) of a tertiary hospital. The Cox proportional hazards model in Stata 16 was used to assess risk factors associated with survival or death. Factors with P<0.05 were considered significant. Results: Patients who died were found to have significantly lower median pH (P<0.001), higher median arterial partial pressure of carbon dioxide (P<0.001), higher D-dimer levels (P=0.001), higher troponin T levels (P=0.001), higher N-terminal-prohormone B-type natriuretic peptide levels (P=0.007) and higher C-reactive protein levels (P=0.010) compared with patients who survived. Increased standard bicarbonate (HCO3std) was associated with lower risk of death (hazard ratio 0.96, 95% confidence interval 0.93-0.99). Conclusions: The mortality of patients with COVID-19 admitted to the ICU was associated with elevated D-dimer and a low HCO3std level. Large studies are warranted to increase the identification of patients at risk of poor prognosis, and to improve the clinical approach.

Estimating district HIV prevalence in Zambia using small-area estimation methods (SAE).

BACKGROUND: The HIV/AIDS pandemic has had a very devastating impact at a global level, with the Eastern and Southern African region being the hardest hit. The considerable geographical variation in the pandemic means varying impact of the disease in different settings, requiring differentiated interventions. While information on the prevalence of HIV at regional and national levels is readily available, the burden of the disease at smaller area levels, where health services are organized and delivered, is not well documented. This affects the targeting of HIV resources. There is need, therefore, for studies to estimate HIV prevalence at appropriate levels to improve HIV-related planning and resource allocation. METHODS: We estimated the district-level prevalence of HIV using Small-Area Estimation (SAE) technique by utilizing the 2016 Zambia Population-Based HIV Impact Assessment Survey (ZAMPHIA) data and auxiliary data from the 2010 Zambian Census of Population and Housing and the HIV sentinel surveillance data from selected antenatal care clinics (ANC). SAE models were fitted in R Programming to ascertain the best HIV predicting model. We then used the Fay-Herriot (FH) model to obtain weighted, more precise and reliable HIV prevalence for all the districts. RESULTS: The results revealed variations in the district HIV prevalence in Zambia, with the prevalence ranging from as low as 4.2% to as high as 23.5%. Approximately 32% of the districts (n = 24) had HIV prevalence above the national average, with one district having almost twice as much prevalence as the national level. Some rural districts have very high HIV prevalence rates. CONCLUSIONS: HIV prevalence in Zambian is highest in districts located near international borders, along the main transit routes and adjacent to other districts with very high prevalence. The variations in the burden of HIV across districts in Zambia point to the need for a differentiated approach in HIV programming within the country. HIV resources need to be prioritized toward districts with high population mobility.

Association between socioeconomic status and fertility among adolescents aged 15 to 19: an analysis of the 2013/2014 Zambia Demographic Health Survey (ZDHS).

BACKGROUND: Adolescents face significant barriers to access and utilization of sexual and reproductive health services in many low-income settings, which in turn may be associated with adverse consequences such as early pregnancy, sexually transmitted infections, unsafe abortion and mortality. There is evidence suggesting that limited access to sexual and reproductive health information and services among adolescents contributes to these outcomes. We aimed to find out the factors that affect the fertility of adolescents aged 15 to 19 years in Zambia and to identify possible drivers of adolescents' fertility. METHODS: Secondary analysis of the ZDHS 2013/14 data was carried out to find out the factors that affect the fertility rate of adolescents aged 15 to 19 years using multivariate logistic regression (n = 3666). RESULTS: Overall, 23.1% of adolescents had given birth at least once in the 5 years leading to the survey (n = 3666, 99.4% response), and 49.8% were rural-based while 50.2% were urban-based. The median number of schooling was 8 years (IQR 6-10). About 52% of the adolescents were in the poorer, poor and medium wealth quintiles while the other 48% were in the rich and richer quintiles. Factors found to affect fertility include residence, wealth status, educational attainment, marriage and abortion. An urban-based adolescent with a lower socioeconomic status was 2.4 times more likely to give birth compared to rural-based poorer adolescents (aOR = 2.4, 95% CI: 1.5, 3.7, p < 0.001). Although odds of giving birth were much higher among rural-based married adolescents (aOR = 8.0, 95% CI: 5.4, 11.9, p < 0.001) compared to urban married adolescents (aOR = 5.5, 95% CI: 8.3, 16.0, p < 0.001), and these relationships both statistically significant, higher educational attainment (aOR = 0.7, 95% CI: 0.6, 0.8 p < 0.001) and abortion (aOR = 0.3, 95% CI: 0.1, 0.8, p = 0.020) reduced these odds, particularly for rural-based adolescents. CONCLUSION: Despite response aimed at reducing adolescent fertility, low wealth status, low educational attainment and early marriage remain significant drivers of adolescent fertility in Zambia. There is a need to address sexual and reproductive health needs of urban-based adolescents with a lower socioeconomic status.

Adolescents go through serious challenges related to accessing and using sexual and reproductive health services in many low-income settings, and may also be related to negative consequences such as early pregnancy, sexually transmitted infections and unsafe abortion and death. Research has revealed that limited access to sexual and reproductive health information and services among young people contributes to these negative consequences. This analysis aimed to find out the factors that affect the fertility of 3666 adolescents aged 15 to 19 years in Zambia and to identify possible drivers of adolescents' fertility, using the Zambia Demographic and Health Survey conducted in 2013/2014. A little over a quarter of the adolescents had given birth at least once in the five years leading to the survey. About half of the young people were rural-basedwhile the other half were urban-based, with an average of about 8 years in school. The rural-based adolescents had slightly lower average years in school compared to the urban-based; 7 years and 9 years respectively. Living in a rural area, residing in a home with a low wealth status and being married were all linked to higher chances of giving birth, while terminating a pregnancy and having more years of education were linked to lower chances of giving birth among the adolescents. Urban-based adolescents with lower wealth status were also linked to higher chances of giving birth compared to urban-based adolescents with higher wealth status. These results suggest that while residing in rural areas and being married increase the chances of higher fertility, the adolescents in urban areas but with lower wealth status also need interventions aimed at reducing their fertility.

Metabolic syndrome in Zambian adults with human immunodeficiency virus on antiretroviral therapy: Prevalence and associated factors.

ABSTRACT: Metabolic syndrome (MetS) is a constellation of factors including hypertension, abdominal obesity, dyslipidemia, and insulin resistance that separately and together significantly increase risk for cardiovascular disease (CVD) and diabetes. In sub-Saharan Africa, with a substantial burden of human immunodeficiency virus (HIV) and increasing prevalence of CVD and diabetes, there is a paucity of epidemiological data on demographic, laboratory, and clinical characteristics associated with MetS among people with HIV (people with human [PWH]). Therefore, this study aimed to determine the burden and factors influencing MetS in antiretroviral therapy (ART)-experienced individuals in Zambia.We collected cross-sectional demographic, lifestyle, anthropometric, clinical, and laboratory data in a cohort of ART-experienced (on ART for ≥6 months) adults in 24 urban HIV treatment clinics of Zambia between August, 2016 and May, 2020. MetS was defined as having ≥3 of the following characteristics: low high density lipoprotein cholesterol (HDL-c) (<1.0 mmol/L for men, <1.3 for women), elevated waist circumference (≥94 cm for men, ≥80 cm for women), elevated triglycerides (≥1.7 mmol/L), elevated fasting blood glucose (≥5.6 mmol/L), and elevated blood pressure (BP) (systolic BP ≥130 or diastolic BP ≥85 mm Hg). Virological failure (VF) was defined as HIV viral load ≥1000 copies/mL. The following statistical methods were used: Chi-square test, Wilcoxon rank-sum test, and multivariable logistic regression.Among 1108 participants, the median age (interquartile range [IQR]) was 41 years (34, 49); 666 (60.1%) were females. The prevalence of MetS was 26.3% (95% confidence interval [CI] 23.9-29.1). Age (adjusted odds ratio [OR] 1.07; 95% CI 1.04-1.11), female sex (OR 3.02; 95% CI 1.55-5.91), VF (OR 1.98; 95% CI 1.01-3.87), dolutegravir (DTG)-based regimen (OR 2.10; 95% CI 1.05-4.20), hip-circumference (OR 1.03; 95% CI 1.01-1.05), T-lymphocyte count (OR 2.23; 95% CI 1.44-3.43), high-sensitivity C-reactive protein (hsCRP) (OR 1.14; 95% CI 1.01-1.29), and fasting insulin (OR 1.02; 95% CI 1.01-1.04) were significantly associated with MetS.Metabolic syndrome was highly prevalent among HIV+ adults receiving ART in Zambia and associated with demographic, clinical, anthropometric, and inflammatory characteristics. The association between MetS and dolutegravir requires further investigation, as does elucidation of the impact of MetS on ART outcomes in sub-Saharan African PWH.