Spatial distribution and machine learning prediction of sexually transmitted infections and associated factors among sexually active men and women in Ethiopia, evidence from EDHS 2016.

INTRODUCTION: Sexually transmitted infections (STIs) are the major public health problem globally, affecting millions of people every day. The burden is high in the Sub-Saharan region, including Ethiopia. Besides, there is little evidence on the distribution of STIs across Ethiopian regions. Hence, having a better understanding of the infections is of great importance to lessen their burden on society. Therefore, this article aimed to assess predictors of STIs using machine learning techniques and their geographic distribution across Ethiopian regions. Assessing the predictors of STIs and their spatial distribution could help policymakers to understand the problems better and design interventions accordingly. METHODS: A community-based cross-sectional study was conducted from January 18, 2016, to June 27, 2016, using the 2016 Ethiopian Demography and Health Survey (EDHS) dataset. We applied spatial autocorrelation analysis using Global Moran's I statistics to detect latent STI clusters. Spatial scan statics was done to identify local significant clusters based on the Bernoulli model using the SaTScan™ for spatial distribution and Supervised machine learning models such as C5.0 Decision tree, Random Forest, Support Vector Machine, Naïve Bayes, and Logistic regression were applied to the 2016 EDHS dataset for STI prediction and their performances were analyzed. Association rules were done using an unsupervised machine learning algorithm. RESULTS: The spatial distribution of STI in Ethiopia was clustered across the country with a global Moran's index = 0.06 and p value = 0.04. The Random Forest algorithm was best for STI prediction with 69.48% balanced accuracy and 68.50% area under the curve. The random forest model showed that region, wealth, age category, educational level, age at first sex, working status, marital status, media access, alcohol drinking, chat chewing, and sex of the respondent were the top 11 predictors of STI in Ethiopia. CONCLUSION: Applying random forest machine learning algorithm for STI prediction in Ethiopia is the proposed model to identify the predictors of STIs.

Prediction of contraceptive discontinuation among reproductive-age women in Ethiopia using Ethiopian Demographic and Health Survey 2016 Dataset: A Machine Learning Approach.

BACKGROUND: Globally, 38% of contraceptive users discontinue the use of a method within the first twelve months. In Ethiopia, about 35% of contraceptive users also discontinue within twelve months. Discontinuation reduces contraceptive coverage, family planning program effectiveness and contributes to undesired fertility. Hence understanding potential predictors of contraceptive discontinuation is crucial to reducing its undesired outcomes. Predicting the risk of discontinuing contraceptives is also used as an early-warning system to notify family planning programs. Thus, this study could enable to predict and determine the predictors for contraceptive discontinuation in Ethiopia. METHODOLOGY: Secondary data analysis was done on the 2016 Ethiopian Demographic and Health Survey. Eight machine learning algorithms were employed on a total sample of 5885 women and evaluated using performance metrics to predict and identify important predictors of discontinuation through python software. Feature importance method was used to select top predictors of contraceptive discontinuation. Finally, association rule mining was applied to discover the relationship between contraceptive discontinuation and its top predictors by using R statistical software. RESULT: Random forest was the best predictive model with 68% accuracy which identified the top predictors of contraceptive discontinuation. Association rule mining identified women's age, women's education level, family size, husband's desire for children, husband's education level, and women's fertility preference as predictors most frequently associated with contraceptive discontinuation. CONCLUSION: Results have shown that machine learning algorithms can accurately predict the discontinuation status of contraceptives, making them potentially valuable as decision-support tools for the relevant stakeholders. Through association rule mining analysis of a large dataset, our findings also revealed previously unknown patterns and relationships between contraceptive discontinuation and numerous predictors.

Machine learning to predict virological failure among HIV patients on antiretroviral therapy in the University of Gondar Comprehensive and Specialized Hospital, in Amhara Region, Ethiopia, 2022.

BACKGROUND: Treatment with effective antiretroviral therapy (ART) reduces viral load as well as HIV-related morbidity and mortality in HIV-positive patients. Despite the expanded availability of antiretroviral therapy around the world, virological failure remains a serious problem for HIV-positive patients. Thus, Machine learning predictive algorithms have the potential to improve the quality of care and predict the needs of HIV patients by analyzing huge amounts of data, and enhancing prediction capabilities. This study used different machine learning classification algorithms to predict the features that cause virological failure in HIV-positive patients. METHOD: An institution-based secondary data was used to conduct patients who were on antiretroviral therapy at the University of Gondar Comprehensive and Specialized Hospital from January 2020 to May 2022. Patients' data were extracted from the electronic database using a structured checklist and imported into Python version three software for data pre-processing and analysis. Then, seven supervised classification machine-learning algorithms for model development were trained. The performances of the predictive models were evaluated using accuracy, sensitivity, specificity, precision, f1-score, and AUC. Association rule mining was used to generate the best rule for the association between independent features and the target feature. RESULT: Out of 5264 study participants, 1893 (35.06%) males and 3371 (64.04%) females were included. The random forest classifier (sensitivity = 1.00, precision = 0.987, f1-score = 0.993, AUC = 0.9989) outperformed in predicting virological failure among all selected classifiers. Random forest feature importance and association rules identified the top eight predictors (Male, younger age, longer duration on ART, not taking CPT, not taking TPT, secondary educational status, TDF-3TC-EFV, and low CD4 counts) of virological failure based on the importance ranking, and the CD-4 count was recognized as the most important predictor feature. CONCLUSION: The random forest classifier outperformed in predicting and identifying the relevant predictors of virological failure. The results of this study could be very helpful to health professionals in determining the optimal virological outcome.

Information seeking about COVID-19 and associated factors among chronic patients in Bahir Dar city public hospitals, Northwest Ethiopia: a cross-sectional study.

BACKGROUND: The health impacts of COVID-19 are not evenly distributed in societies. Chronic patients are highly affected and develop dangerous symptoms of COVID-19. Understanding their information seeking about COVID-19 may help to improve the effectiveness of public health strategies in the future, the adoption of safety measures, and minimize the spread of the pandemic. However, there is little evidence on information seeking specifically on COVID-19 in this study setting. Therefore, this study aimed to assess information seeking about COVID-19 and associated factors among chronic patients. METHOD: An institutional-based cross-sectional study supplemented with qualitative data was conducted at Bahir Dar city public hospitals in Northwest Ethiopia from April 8 to June 15, 2021. A total of 423 chronic patients were selected using systematic random sampling techniques with an interval of 5. Bi-variable and multivariable logistic regression analysis was fitted to identify factors associated with information seeking about COVID-19. A p-value < 0.05 was used to declare statistical significance. Qualitative data were analyzed using a thematic approach. Finally, it was triangulated with quantitative findings. RESULT: The proportion of information seeking about COVID-19 among chronic patients was 44.0% (95% CI = 39.0, 49.0). Being living in urban [AOR = 4.4, 95% CI (2.01, 9.58)], having high perceived susceptibility to COVID-19 [AOR = 3.4, 95%CI (1.98, 5.70)], having high perceived severity to COVID-19 [AOR = 1.7, 95%CI (1.04, 2.91)], having high self-efficacy to COVID-19 [AOR = 4.3, 95%CI (2.52, 7.34)], and having adequate health literacy [AOR = 1.8, 95%CI (1.10, 3.03)] were significant factors associated with information-seeking about COVID-19. CONCLUSION: The overall proportion of information seeking about COVID-19 among chronic patients was low. Thus, health promotion programs should emphasize the chronic patients living in a rural area; enhance perceived risk and severity of COVID-19, enhancing self-efficacy and health literacy interventions to improve information seeking.

Prediction of incomplete immunization among under-five children in East Africa from recent demographic and health surveys: a machine learning approach.

The World Health Organization as part of the goal of universal vaccination coverage by 2030 for all individuals. The global under-five mortality rate declined from 59% in 1990 to 38% in 2019, due to high immunization coverage. Despite the significant improvements in immunization coverage, about 20 million children were either unvaccinated or had incomplete immunization, making them more susceptible to mortality and morbidity. This study aimed to identify predictors of incomplete vaccination among children under-5 years in East Africa. An analysis of secondary data from six east African countries using Demographic and Health Survey dataset from 2016 to the recent 2021 was performed. A total weighted sample of 27,806 children aged (12-35) months was included in this study. Data were extracted using STATA version 17 statistical software and imported to a Jupyter notebook for further analysis. A supervised machine learning algorithm was implemented using different classification models. All analysis and calculations were performed using Python 3 programming language in Jupyter Notebook using imblearn, sklearn, XGBoost, and shap packages. XGBoost classifier demonstrated the best performance with accuracy (79.01%), recall (89.88%), F1-score (81.10%), precision (73.89%), and AUC 86%. Predictors of incomplete immunization are identified using XGBoost models with help of Shapely additive eXplanation. This study revealed that the number of living children during birth, antenatal care follow-up, maternal age, place of delivery, birth order, preceding birth interval and mothers' occupation were the top predicting factors of incomplete immunization. Thus, family planning programs should prioritize the number of living children during birth and the preceding birth interval by enhancing maternal education. In conclusion promoting institutional delivery and increasing the number of antenatal care follow-ups by more than fourfold is encouraged.

The boundary-spanning mechanisms of Nobel Prize winning papers.

The breakthrough potentials of research papers can be explained by their boundary-spanning qualities. Here, for the first time, we apply the structural variation analysis (SVA) model and its affiliated metrics to investigate the extent to which such qualities characterize a group of Nobel Prize winning papers. We find that these papers share remarkable boundary-spanning traits, marked by exceptional abilities to connect disparate and topically-diverse clusters of research papers. Further, their publications exert structural variations on a scale that significantly alters the betweenness centrality distributions in existing intellectual space. Overall, SVA not only provides a set of leading indicators for describing future Nobel Prize winning papers, but also broadens our understanding of similar prize-winning properties that may have been overlooked among other regular publications.