Predicting skilled delivery service use in Ethiopia: dual application of logistic regression and machine learning algorithms

Prediction of stunting and its socioeconomic determinants among adolescent girls in Ethiopia using machine learning algorithms

BACKGROUND

Stunting is a vital indicator of chronic undernutrition that reveals a failure to reach linear growth. Investigating growth and nutrition status during adolescence, in addition to infancy and childhood is very crucial. However, the available studies in Ethiopia have been usually focused in early childhood and they used the traditional stastical methods. Therefore, this study aimed to employ multiple machine learning algorithms to identify the most effective model for the prediction of stunting among adolescent girls in Ethiopia.

METHODS

A total of 3156 weighted samples of adolescent girls aged 15-19 years were used from the 2016 Ethiopian Demographic and Health Survey dataset. The data was pre-processed, and 80% and 20% of the observations were used for training, and testing the model, respectively. Eight machine learning algorithms were included for consideration of model building and comparison. The performance of the predictive model was evaluated using evaluation metrics value through Python software. The synthetic minority oversampling technique was used for data balancing and Boruta algorithm was used to identify best features. Association rule mining using an Apriori algorithm was employed to generate the best rule for the association between the independent feature and the targeted feature using R software.

RESULTS

The random forest classifier (sensitivity = 81%, accuracy = 77%, precision = 75%, f1-score = 78%, AUC = 85%) outperformed in predicting stunting compared to other ML algorithms considered in this study. Region, poor wealth index, no formal education, unimproved toilet facility, rural residence, not used contraceptive method, religion, age, no media exposure, occupation, and having one or more children were the top attributes to predict stunting. Association rule mining was identified the top seven best rules that most frequently associated with stunting among adolescent girls in Ethiopia.

CONCLUSION

The random forest classifier outperformed in predicting and identifying the relevant predictors of stunting. Results have shown that machine learning algorithms can accurately predict stunting, making them potentially valuable as decision-support tools for the relevant stakeholders and giving emphasis for the identified predictors could be an important intervention to halt stunting among adolescent girls.

Women Autonomy in Health Care Decision Making and Associated Factors Among Postpartum Women in Southern Ethiopia: A Cross-Sectional Study

Background and Aims

Women's autonomy in healthcare decision-making is crucial for improving maternal and child health. Despite its importance, there is limited evidence on autonomous healthcare decision making particularly in postpartum women. Thus, this study aimed to assess the prevalence of postpartum women's autonomy in healthcare decision making and its associated factors in Chencha town, Gamo zone, southern Ethiopia.

Methods

A community based cross-sectional study was conducted among 617 postpartum women in southern Ethiopia from October 1 to November 30, 2023. A study participants were selected by a simple random sampling technique. The data were collected through pretested and interviewer administered questionnaire. Following coding and entry into Epi-data version 3.1, the data were exported into statistical package for social science software (SPSS version 26) for analysis. A logistic regression model was fitted and, variables with p < 0.05 were declared to be significantly associated with women autonomy in healthcare decision-making.

Results

In this study, 61.6% of postpartum women have autonomous in their health care decision making with 95% confidence interval (CI): 57.4, 65.3. Women age over 35 years (AOR = 3.2, 95% CI: 1.7, 6.0), enrollment in community-based health insurance (AOR = 1.5 95% CI: 1.0, 2.3), having four and above antenatal care visits (AOR = 2.5, 95% CI: 1.6, 3.8), using skilled delivery service (AOR = 4.3, 95% CI: 2.9, 6.6), having primary educational level (AOR = 4.9, 95% CI: 3.0, 8.0), and secondary and above educational level (AOR = 5, 95% CI: 3.1, 8.0) were positively associated with women autonomy in health care decision making.

Conclusion

This study revealed that majority of postpartum women were autonomous in their healthcare decision making. Maternal age, educational status, enrollment in community-based health insurance, having frequent ANC follow-up and using skilled delivery service were factors significantly associated with women's autonomy. Focus should be given to improve women antenatal care follow-up and the enrollment of community-based health insurance.

Predicting place of delivery choice among childbearing women in East Africa: a comparative analysis of advanced machine learning techniques

Background

Sub-Saharan Africa faces high neonatal and maternal mortality rates due to limited access to skilled healthcare during delivery. This study aims to improve the classification of health facilities and home deliveries using advanced machine learning techniques and to explore factors influencing women's choices of delivery locations in East Africa.

Method

The study focused on 86,009 childbearing women in East Africa. A comparative analysis of 12 advanced machine learning algorithms was conducted, utilizing various data balancing techniques and hyperparameter optimization methods to enhance model performance.

Result

The prevalence of health facility delivery in East Africa was found to be 83.71%. The findings showed that the support vector machine (SVM) algorithm and CatBoost performed best in predicting the place of delivery, in which both of those algorithms scored an accuracy of 95% and an AUC of 0.98 after optimized with Bayesian optimization tuning and insignificant difference between them in all comprehensive analysis of metrics performance. Factors associated with facility-based deliveries were identified using association rule mining, including parental education levels, timing of initial antenatal care (ANC) check-ups, wealth status, marital status, mobile phone ownership, religious affiliation, media accessibility, and birth order.

Conclusion

This study underscores the vital role of machine learning algorithms in predicting health facility deliveries. A slight decline in facility deliveries from previous reports highlights the urgent need for targeted interventions to meet Sustainable Development Goals (SDGs), particularly in maternal health. The study recommends promoting facility-based deliveries. These include raising awareness about skilled birth attendance, encouraging early ANC check-up, addressing financial barriers through targeted support programs, implementing culturally sensitive interventions, utilizing media campaigns, and mobile health initiatives. Design specific interventions tailored to the birth order of the child, recognizing that mothers may have different informational needs depending on whether it is their first or subsequent delivery. Furthermore, we recommended researchers to explore a variety of techniques and validate findings using more recent data.

Estimates and determinants of health facility delivery in the Birhan cohort in Ethiopia

Health facility delivery is one of the critical indicators to monitor progress towards the provision of skilled delivery care and reduction in perinatal mortality. In Ethiopia, utilization of health facilities for skilled delivery care has been increasing but varies greatly by region and among specific socio-demography groups. We aimed to measure the prevalence and determinants of health facility delivery in the Amhara region in Ethiopia. From December 2018 to November 2020, we conducted a longitudinal study from a cohort of 2801 pregnant women and described the location of delivery and the association with determinants. We interviewed a subset of women who delivered in the community and analyzed responses using the three delays model to understand reasons for not using health facility services. A multivariable poisson regression model with robust error variance was used to estimate the presence and magnitude of association between location of delivery and the determinants. Of the 2,482 pregnant women followed through to birth, 73.6% (n = 1,826) gave birth in health facilities, 24.3% (n = 604) gave birth at home and 2.1% (n = 52) delivered on the way to a health facility. Determinants associated with increased likelihood of delivery at a health facility included formal maternal education, shorter travel times to health facilities, primiparity, higher wealth index and having attended at least one ANC visit. Most common reasons mothers gave for not delivering in a health facility were delays in individual/family decision to seek care. The proportion of deliveries occurring in health facilities is increasing but falls below targets. Interventions that focus on the identified social-demographic determinants and delays are warranted.

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.

Completion of the maternal continuity of care and associated factors among women who gave birth in the last 6 months in Kena District, southern Ethiopia: A community-based cross-sectional study, 2023

BACKGROUND

The maternity continuum of care includes attending at least four antenatal care (ANC) visits, delivering in a health facility, and receiving postnatal care. However, in many developing nations, including Ethiopia, completion of this continuum is low, contributing to high maternal mortality. So far, no studies have assessed this issue in the study area.

OBJECTIVE

To assess the completion of maternity continuum of care and associated factors among women who gave birth in the last 6 months in Kena district, southern, Ethiopia, 2023.

DESIGN

Cross-sectional study using quantitative data collection method.

METHODS

The study was conducted among 592 women in southern Ethiopia from April to June 2023. A study participants were selected by a simple random sampling technique. Data were collected using a structured, pretested, interviewer-administered questionnaire. Then, data were entered into EpiData 3.1 and analyzed using statistical package for social science software (SPSS version 26). Logistic regression was used to identify factors related to the maternity continuum of care, with statistical significance set at p < 0.05.

RESULTS

The mean age of the enrolled women was 28.78 ± 4.6 years. Of these, 11.8% (95% confidence interval (CI): 9%-14%) of women completed the entire maternity continuum care. Women with secondary education and above (adjusted odds ratio (AOR) = 5, 95% CI: 2.5-11), autonomy in healthcare decision-making (AOR = 2.4, 95% CI: 1.3-4.6), having information on maternal health (AOR = 2.4, 95% CI: 1.3-4.6) Early initiation of ANC (AOR = 4, 95% CI: 2.27-7.1) and birth preparedness (AOR = 2.7, 95% CI: 1.5-5) were significantly associated with completion.

CONCLUSIONS

Completion of the maternity continuum of care in study area is very low. Targeted interventions should promote women's autonomy in healthcare decision-making, early ANC initiation, and birth preparedness to improve outcomes.

Predicting the drop out from the maternal, newborn and child healthcare continuum in three East African Community countries: application of machine learning models

BACKGROUND

For optimal health, the maternal, newborn, and child healthcare (MNCH) continuum necessitates that the mother/child receive the full package of antenatal, intrapartum, and postnatal care. In sub-Saharan Africa, dropping out from the MNCH continuum remains a challenge. Using machine learning, the study sought to forecast the MNCH continuum drop out and determine important predictors in three East African Community (EAC) countries.

METHODS

The study utilised Demographic Health Surveys data from the Democratic Republic of Congo (DRC) (2013/14), Kenya (2014) and Tanzania (2015/16). STATA 17 was used to perform the multivariate logistic regression. Python 3.0 was used to build five machine learning classification models namely the Logistic Regression, Random Forest, Decision Tree, Support Vector Machine and Artificial Neural Network. Performance of the models was assessed using Accuracy, Precision, Recall, Specificity, F1 score and area under the Receiver Operating Characteristics (AUROC).

RESULTS

The prevalence of the drop out from the MNCH continuum was 91.0% in the DRC, 72.4% in Kenya and 93.6% in Tanzania. Living in the rural areas significantly increased the odds of dropping out from the MNCH continuum in the DRC (AOR:1.76;95%CI:1.30-2.38), Kenya (AOR:1.23;95%CI:1.03-1.47) and Tanzania (AOR:1.41;95%CI:1.01-1.97). Lower maternal education also conferred a significant increase in the DRC (AOR:2.16;95%CI:1.67-2.79), Kenya (AOR:1.56;95%CI:1.30-1.84) and Tanzania (AOR:1.70;95%CI:1.24-2.34). Non exposure to mass media also conferred a significant positive influence in the DRC (AOR:1.49;95%CI:1.15-1.95), Kenya (AOR:1.46;95%CI:1.19-1.80) and Tanzania (AOR:1.65;95%CI:1.13-2.40). The Random Forest exhibited superior predictive accuracy (Accuracy = 75.7%, Precision = 79.1%, Recall = 92.1%, Specificity = 51.6%, F1 score = 85.1%, AUROC = 70%). The top four predictors with the greatest influence were household wealth, place of residence, maternal education and exposure to mass media.

CONCLUSIONS

The MNCH continuum dropout rate is very high in the EAC countries. Maternal education, place of residence, and mass media exposure were common contributing factors to the drop out from MNCH continuum. The Random Forest had the highest predictive accuracy. Household wealth, place of residence, maternal education and exposure to mass media were ranked among the top four features with significant influence. The findings of this study can be used to support evidence-based decisions in MNCH interventions and to develop web-based services to improve continuity of care retention.

Predicting facility-based delivery in Zanzibar: The vulnerability of machine learning algorithms to adversarial attacks

Background

Community health worker (CHW)-led maternal health programs have contributed to increased facility-based deliveries and decreased maternal mortality in sub-Saharan Africa. The recent adoption of mobile devices in these programs provides an opportunity for real-time implementation of machine learning predictive models to identify women most at risk for home-based delivery. However, it is possible that falsified data could be entered into the model to get a specific prediction result - known as an "adversarial attack". The goal of this paper is to evaluate the algorithm's vulnerability to adversarial attacks.

Methods

The dataset used in this research is from the Uzazi Salama ("Safer Deliveries") program, which operated between 2016 and 2019 in Zanzibar. We used LASSO regularized logistic regression to develop the prediction model. We used "One-At-a-Time (OAT)" adversarial attacks across four different types of input variables: binary - access to electricity at home, categorical - previous delivery location, ordinal - educational level, and continuous - gestational age. We evaluated the percent of predicted classifications that change due to these adversarial attacks.

Results

Manipulating input variables affected prediction results. The variable with the greatest vulnerability was previous delivery location, with 55.65% of predicted classifications changing when applying adversarial attacks from previously delivered at a facility to previously delivered at home, and 37.63% of predicted classifications changing when applying adversarial attacks from previously delivered at home to previously delivered at a facility.

Conclusion

This paper investigates the vulnerability of an algorithm to predict facility-based delivery when facing adversarial attacks. By understanding the effect of adversarial attacks, programs can implement data monitoring strategies to assess for and deter these manipulations. Ensuring fidelity in algorithm deployment secures that CHWs target those women who are actually at high risk of delivering at home.

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.

Skilled birth attendant utilization trends, determinant and inequality gaps in Ethiopia

BACKGROUND

Globally over half a million women die every year from potentially preventable and treatable pregnancy and childbirth complications; of which 99% occur in low-and middle-income countries (LMICs). The utilization of skilled birth attendants can timely identify treatable birth complications and save lives. However, utilization of services remained low in LMICs. This study aimed to examine the trends in the utilization of skilled birth attendants and the inequality gaps in Ethiopia using data from the Demographic and Health Surveys.

METHODS

We used data from five rounds of Ethiopian Demographic and Health Surveys conducted in the period 2000-2019. Respondents were women in the reproductive age group who had a live birth within five years preceding the surveys. We used the concentration curve and concentration index to identify the inequalities using the World Health Organization recommended Health Equity Analysis Toolkit software. We did a logistic regression analysis to examine factors associated with skilled birth attendant utilization using STATA version 14.0.

RESULT

The skilled birth attendant coverage trend showed an increment from 5.7% in 2005 to 49.8% in 2019. The inequality gaps within the wealth, residence and education categories also showed a reduction over time. The odds of utilizing SBA were higher among those having primary, secondary, and above education status [AOR = 1.61 95%CI (1.33, 1.95)], being in the upper wealth quintile [AOR = 3.46 95%CI (1.8, 4.31)] and living in urban areas [AOR = 3.53 95%CI (1.88, 6.64)].

CONCLUSION

The skilled birth attendant coverage trend showed a steady increase from 2005 to 2019 but if we continue with the current pace, it will be difficult to achieve the national target. The inequality gaps in household wealth status and residency area remain high. Efforts like strengthening the health system and engaging multisectoral agents need to be given priority to further reach the poorest and those living in rural areas to achieve national and international targets.

Machine learning for maternal health: Predicting delivery location in a community health worker program in Zanzibar

Background

Maternal and neonatal health outcomes in low- and middle-income countries (LMICs) have improved over the last two decades. However, many pregnant women still deliver at home, which increases the health risks for both the mother and the child. Community health worker programs have been broadly employed in LMICs to connect women to antenatal care and delivery locations. More recently, employment of digital tools in maternal health programs have resulted in better care delivery and served as a routine mode of data collection. Despite the availability of rich, patient-level data within these digital tools, there has been limited utilization of this type of data to inform program delivery in LMICs.

Methods

We use program data from 38,787 women enrolled in Safer Deliveries, a community health worker program in Zanzibar, to build a generalizable prediction model that accurately predicts whether a newly enrolled pregnant woman will deliver in a health facility. We use information collected during the enrollment visit, including demographic data, health characteristics and current pregnancy information. We apply four machine learning methods: logistic regression, LASSO regularized logistic regression, random forest and an artificial neural network; and three sampling techniques to address the imbalanced data: undersampling of facility deliveries, oversampling of home deliveries and addition of synthetic home deliveries using SMOTE.

Results

Our models correctly predicted the delivery location for 68%–77% of the women in the test set, with slightly higher accuracy when predicting facility delivery versus home delivery. A random forest model with a balanced training set created using undersampling of existing facility deliveries accurately identified 74.4% of women delivering at home.

Conclusions

This model can provide a “real-time” prediction of the delivery location for new maternal health program enrollees and may enable early provision of extra support for individuals at risk of not delivering in a health facility, which has potential to improve health outcomes for both mothers and their newborns. The framework presented here is applicable in other contexts and the selection of input features can easily be adapted to match data availability and other outcomes, both within and beyond maternal health.

Continuity of maternal healthcare services utilisation in Indonesia: analysis of determinants from the Indonesia Demographic and Health Survey

OBJECTIVE

WHO recommends that every pregnant woman and newborn receive quality care throughout the pregnancy, delivery and postnatal periods. However, Maternal Mortality Ratio in Indonesia for 2015 reached 305 per 100 000 live births, which exceeds the target of Sustainable Development Goals (<70 per 100 000 live births). Receiving at least four times antenatal care (ANC4+) and skilled birth attendant (SBA) during childbirth is crucial for preventing maternal and neonatal deaths. The study aims to assess the determinants of ANC4 +and SBA independently, evaluate the distribution of utilisation of ANC4 + and SBA services, and further investigate the associations of two levels of continuity of services utilisation in Indonesia DESIGN: Data from the Indonesia Demographic and Health Survey, a cross-sectional and large-scale national survey conducted in 2017 were used.

SETTING

This study was set in Indonesia.

PARTICIPANTS

The study involved ever-married women of reproductive age (15-49 years) and had given birth in the last 5 years prior to the survey (n=15 288). The dependent variables are the use of ANC4 + and SBA. Individual, family and community factors, such as age, age at first birth, level of education, employment status, parity, autonomy in healthcare decision-making, level of education, employment status of spouses, household income, mass media consumption residence and distance from health facilities were also measured.

RESULTS

Results showed that 11 632 (76.1%) women received ANC4 + and SBA during childbirth. Multivariate analysis revealed that age, age at first birth, and parity have a statistically significant association with continuity of services utilisation. The odds of using continuity of services were higher among women older than 34 years (adjusted OR (aOR) 1.54; 95% CI 1.31 to 1.80) compared with women aged 15-24 years. Women with a favourable distance from health facilities were more likely to receive continuity of services utilisation (aOR 1.39; 95% CI 1.24 to 1.57).

CONCLUSIONS

The continuity of services utilisation is associated with age, reproductive status, family influence and accessibility-related factors. Findings demonstrated the importance of enhancing early reproductive health education for men and women. The health system reinforcement, community empowerment and multisectoral engagement enhance accessibility to health facilities, reduce financial and geographical barriers, and produce strong quality care.

Health informatics publication trends in Saudi Arabia: a bibliometric analysis over the last twenty-four years

OBJECTIVE

Understanding health informatics (HI) publication trends in Saudi Arabia may serve as a framework for future research efforts and contribute toward meeting national "e-Health" goals. The authors' intention was to understand the state of the HI field in Saudi Arabia by exploring publication trends and their alignment with national goals.

METHODS

A scoping review was performed to identify HI publications from Saudi Arabia in PubMed, Embase, and Web of Science. We analyzed publication trends based on topics, keywords, and how they align with the Ministry of Health's (MOH's) "digital health journey" framework.

RESULTS

The total number of publications included was 242. We found 1 (0.4%) publication in 1995-1999, 11 (4.5%) publications in 2000-2009, and 230 (95.0%) publications in 2010-2019. We categorized publications into 3 main HI fields and 4 subfields: 73.1% (n=177) of publications were in clinical informatics (85.1%, n=151 medical informatics; 5.6%, n=10 pharmacy informatics; 6.8%, n=12 nursing informatics; 2.3%, n=4 dental informatics); 22.3% (n=54) were in consumer health informatics; and 4.5% (n=11) were in public health informatics. The most common keyword was "medical informatics" (21.5%, n=52). MOH framework-based analysis showed that most publications were categorized as "digitally enabled care" and "digital health foundations."

CONCLUSIONS

The years of 2000-2009 may be seen as an infancy stage of the HI field in Saudi Arabia. Exploring how the Saudi Arabian MOH's e-Health initiatives may influence research is valuable for advancing the field. Data exchange and interoperability, artificial intelligence, and intelligent health enterprises might be future research directions in Saudi Arabia.