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.

Objectives: Personal health record systems allow users to manage their health information in a confidential manner. However, there is little evidence about healthcare providers’ intentions to use such technologies in resource-limited settings. Therefore, this study aimed to assess predicting healthcare providers’ acceptance of electronic personal health record systems. Methods: An institutional-based cross-sectional study was conducted from 19 July to 23 August 2022 at teaching hospitals in the Amhara regional state of Ethiopia. A total of 638 health professionals participated in the study. Simple random sampling techniques were used to select the study participants. Structural equation modelling analysis was employed using AMOS V.26 software. Result: Perceived ease of use had a significant effect on the intention to use electronic personal health records (β=0. 377, p<0.01), perceived usefulness (β=0.104, p<0.05) and attitude (β=0.204, p<0.01); perceived ease of use and information technology experience had a significant effect on perceived usefulness (β=0.077, p<0.05); and digital literacy (β=0.087, p<0.05) and attitude had also a strong effect on intention to use electronic personal health records (β=0.361, p<0.01). The relationship between perceived ease of use and the intention to use was mediated by attitude (β=0.076, p<0.01). Conclusion: Perceived ease of use, attitude and digital literacy had a significant effect on the intention to use electronic personal health records. The perceived ease of use had a greater influence on the intention to use electronic personal health record systems. Thus, capacity building and technical support could enhance health providers’ acceptance of using electronic personal health records in Ethiopia.

Background: eHealth is the use of information and communications technologies in support of health and health-related fields, including healthcare services, health surveillance, health literature, and health education knowledge and research, has the potential to improve the delivery and support of healthcare services by promoting information sharing and evidence-based health practice. Acceptance of e-health in Ethiopia using systematic review is uncertain. As a result, this study aimed to assess barriers and facilitators of the sustainable acceptance of e-health system adoption in Ethiopia through a systematic review of the literature. Methods: The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) checklist was used to conduct this study. Relevant articles have been searched in Google Scholar, Medline, PubMed, Embrace, Web of Science, Scopus, Cochrane Library, and empirical research done in Ethiopia is the main emphasis of the search strategy. The total number of studies that satisfied the criteria for inclusion was ten. In this research, empirical data related to e-health acceptance factors were retrieved, examined, and summarized by the authors. Results: This systematic review identified a total of 25 predictors that have been found in the ten studies. The identified facilitators were effort expectancy, performance expectancy, facilitating conditions, social influences, attitude, computer literacy, participant age, perceived enjoyment, and educational status, duration of mobile device use, organizational culture, and habit. Moreover, technology anxiety was the most barrier to sustainable acceptance of e-health systems in Ethiopia. Conclusions: The most common facilitator identified from the predictors was effort expectancy, which played a major role in the adoption of the e-health system in Ethiopia. Therefore, eHealth implementers and managers in those settings should give users of the system priority in improving the technical infrastructure by regularly providing them with basic facilitating conditions. They should also pay attention to the system they want to implement because doing so will improve the users’ perception of the system’s value and attitude.

Unmet need for contraceptives is a public health issue globally that affects maternal and child health. Reducing unmet need reduces the risk of abortion or childbearing by preventing unintended pregnancy. The unmet need for family planning is a frequently used indicator for monitoring family planning programs. This study aimed to identify predictors of unmet need for family planning using advanced machine learning modeling on recent PMA 2019 survey data. The study was conducted using secondary data from PMA Ethiopia 2019 cross-sectional household and female survey which was carried out from September 2019 to December 2019. Eight machine learning classifiers were employed on a total weighted sample of 5819 women and evaluated using performance metrics to predict and identify important predictors of unmet need of family planning with Python 3.10 version software. Data preparation techniques such as removing outliers, handling missing values, handling unbalanced categories, feature engineering, and data splitting were applied to smooth the data for further analysis. Finally, Shapley Additive exPlanations (SHAP) analysis was used to identify the top predictors of unmet need and explain the contribution of the predictors on the model’s output. Random Forest was the best predictive model with a performance of 85% accuracy and 0.93 area under the curve on balanced training data through tenfold cross-validation. The SHAP analysis based on random forest model revealed that husband/partner disapproval to use family planning, number of household members, women education being primary, being from Amhara region, and previously delivered in health facility were the top important predictors of unmet need for family planning in Ethiopia. Findings from this study suggest various sociocultural and economic factors might be considered while implementing health policies intended to decrease unmet needs for family planning in Ethiopia. In particular, the husband’s/partner’s involvement in family planning sessions should be emphasized as it has a significant impact on women’s demand for contraceptives.

Background: Maintaining and effectively utilizing maternal continuum of care could save an estimated 860,000 additional mothers and newborn lives each year. In Ethiopia, the number of maternal and neonatal deaths occurred during pregnancy, childbirth, and the postpartum period was very high. It is indisputable that area-based heterogeneity of zero utilization for a standard maternal continuum of care is critical to improve maternal and child health interventions. However, none of the previous studies explored the spatial distribution of zero utilization for maternal continuum of care. Hence, this study was aimed to explore geographical variation and predictors of zero utilization for a standard maternal continuum of care among women in Ethiopia. Methods: A total of 4178 women who gave birth five years preceding the 2016 Ethiopian demographic and health survey were included. ArcGIS version 10.7, SaT Scan version 9.6, and GWR version 4.0 Software was used to handle mapping, hotspot, ordinary least square, Bernoulli model analysis, and to model spatial relationships. Finally, a statistical decision was made at a p-value< 0.05 and at 95% confidence interval. Main findings: The proportion of mothers who had zero utilization of a standard maternal continuum of care was 48.8% (95% CI: 47.3–50.4). Hot spot (high risk) regions for zero utilization of maternal continuum of care was detected in Afder, Warder, Korahe and Gode Zones of Somali region and West Arsi Zone of Oromia region. Respondents who had poor wealth index, uneducated mothers, and mothers who declared distance as a big problem could increase zero utilization of maternal continuum of care by 0.24, 0.27, and 0.1 times. Conclusion: Five women out of ten could not utilize any components of a standard maternal continuum of care. Hot spot (high risk) areas was detected in Afder, Warder, Korahe and Gode Zones of Somali region and West Arsi Zone of Oromia region. Poor wealth index, uneducated mothers, and mothers who declare distance as a big problem were factors significantly associated with zero utilization of maternal continuum of care. Thus, geographical based intervention could be held to curve the high prevalence of zero utilization of maternal continuum of care.