Correlates of facility-based delivery among women of reproductive age from the Digo community residing in Kwale, Kenya

Intimate partner violence influences modern family planning use among married women in Tanzania: cross-sectional study

BACKGROUND

Married women who experience intimate partner violence (IPV) are less likely to negotiate with their partners on modern family planning (FP) use. This study aimed to determine the influence of intimate partner violence and sociodemographics on modern family planning use.

METHODS

A community-based cross-sectional study was conducted in the Mara region, Tanzania from April to July 2020. A total of 366 married women were interviewed. Data were collected using a structured interviewer-administered questionnaire. Analysis was done using SPSS version 25, and a binary logistic regression model was used to determine the predictors of modern FP use. The significance level was set at a p-value less than 0.05.

RESULTS

The overall prevalence of IPV was 73% with 54.1% physical, 36.3% psychological, and 25.4%, sexual violence. The prevalence of modern FP use was 62%, and the most (49.1%) common method practiced by married women was injection (Depo Provera). Physical violence (AOR = 0.32, p = 0.0056), and psychological violence (AOR = 0.22, p = 0.0022) had significantly reduced odds of modern FP use. Religion (AOR = 4.6, p = 0.0085), and availability of preferred modern FP methods (AOR = 9.27, p < 0.0001) had significantly increased odds of modern FP use.

CONCLUSION

In this study, there is a positive association between the use of modern FP methods and IPV. To prevent IPV and its negative health consequences, it is crucial to involve community leaders and primary healthcare workers. They can help in identifying the best strategies to prevent IPV and promote the use of modern FP methods. It is equally important to involve male partners in reproductive health decisions, including the use of modern FP methods. This approach will help reduce reproductive coercion.

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.

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.

Identifying Programmatic Factors that Increase Likelihood of Health Facility Delivery: Results from a Community Health Worker Program in Zanzibar

INTRODUCTION

Community health worker (CHW) interventions have been utilized to address barriers that prevent pregnant women from delivering in health facilities in low- and middle-income countries (LMICs). The objective of this research was to assess the programmatic factors that increase the likelihood of health facility delivery within a large digital health-supported CHW program in Zanzibar, Tanzania.

METHODS

This study included 36,693 women who were enrolled in the Safer Deliveries program with a live birth between January 1, 2017 and July 31, 2019. We assessed whether long-term enrollment, recency of CHW pregnancy visit prior to delivery, and number of routine home pregnancy visits were associated with an increased likelihood of health facility delivery compared to home delivery. We used Chi-squared tests to assess bivariate relationships and performed logistic regression analyses to assess the association between each programmatic variable and health facility delivery, adjusting for relevant confounders.

RESULTS

We found that long-term enrollment was significantly associated with increased likelihood of health facility delivery, with the strongest relationship among women with a previous home delivery (OR = 1.4, 95%CI [1.0,1.7]). Among first-time mothers, two or more pregnancy visits by a CHW was positively associated with health facility delivery (OR = 1.8, 95%CI [1.2, 2.7]). Recent pregnancy visit by a CHW was positively associated with health facility delivery, but was not significant at the α = 0.05 level.

DISCUSSION

In this program, we found evidence that at least two routine home pregnancy visits, longer length of enrollment in the program, and recency of home visit to the delivery date were strategies to increase health facility delivery rates among enrolled mothers. Maternal and child health programs should undertake similar evaluations to improve program delivery.

Effect of four or more antenatal care visits on facility delivery and early postnatal care services utilization in Uganda: a propensity score matched analysis

Introduction

Maternal mortality remains a global public health issue, more predominantly in developing countries, and is associated with poor maternal health services utilization. Antenatal care (ANC) visits are positively associated with facility delivery and postnatal care (PNC) utilization. However, ANC in itself may not lead to such association but due to differences that exist among users (women). The purpose of this study, therefore, is to examine the effect of four or more ANC visits on facility delivery and early PNC and also the effect of facility-based delivery on early PNC using Propensity Score Matched Analysis (PSMA).

Methods

The present study utilized the 2016 Uganda Demographic and Health Survey (UDHS) dataset. Women aged 15 – 49 years who had given birth three years preceding the survey were considered for this study. Propensity score-matched analysis was used to analyze the effect of four or more ANC visits on facility delivery and early PNC and also the effect of facility-based delivery on early PNC.

Results

The results revealed a significant and positive effect of four or more ANC visits on facility delivery [ATT (Average Treatment Effect of the Treated) = 0.118, 95% CI: 0.063 – 0.173] and early PNC [ATT = 0.099, 95% CI: 0.076 – 0.121]. It also found a positive and significant effect of facility-based delivery on early PNC [ATT = 0.518, 95% CI: 0.489 – 0.547].

Conclusion

Policies geared towards the provision of four or more ANC visits are an effective intervention towards improved facility-based delivery and early PNC utilisation in Uganda.

A Pilot Study to Evaluate the Impact of the HIV Infant Tracking System (HITSystem 2.0) on Priority Prevention of Mother-to-Child Transmission (PMTCT) Outcomes

We assessed the preliminary impact of the adapted HIV Infant Tracking System (HITSystem v2.0) intervention on prevention of mother-to-child transmission (PMTCT) outcomes using a matched cluster randomized design in two Kenyan government hospitals. Between November 2017 and June 2019, n = 157 pregnant women with HIV were enrolled and followed from their first PMTCT appointment until 12-weeks postpartum. Data from 135 women were analyzed (HITSystem 2.0: n = 53, standard of care (SOC): n = 82), excluding eight deaths, eight pregnancy losses, and six transfers/moves. The primary outcome, complete PMTCT retention, is an aggregate measure of attendance at all scheduled antenatal appointments, hospital-based delivery, and infant HIV-testing before 7-weeks postnatal. HITSystem 2.0 participants were more likely to receive complete PMTCT services compared to SOC (56.6% vs. 17.1% p < 0.001). In multivariate modeling, HITSystem 2.0 was the strongest predictor of complete PMTCT retention (aOR 5.7, [1.2-90.8], p = 0.032). SOC participants had 1.91 increased hazard rate of PMTCT disengagement; (aHR 6.8, [2.2-21.1]; p < 0.001).

Religious, socio-cultural norms and gender stereotypes influence uptake and utilization of maternal health services among the Digo community in Kwale, Kenya: a qualitative study

Background

Maternal health outcomes in resource-limited settings are typically influenced by supply-side factors affecting the provision of quality health services. The extent to which demand-side factors contribute to this influence is unclear. We aimed to explore how individual and community-wide factors influenced uptake and utilization of maternal health services among the Digo community residing in Kwale County of coastal Kenya.

Methods

Between March and December 2015, we conducted 5 focus group discussions (FGDs) and 15 in-depth interviews (IDIs) with members of the Digo community predominant in Kwale county, Kenya. Respondents were sampled purposively and included female (pregnant and postpartum) as well as male adult community members. A thematic content analytic approach was used.

Results

There were a total of 47 FGD respondents, including 15 (32%) females with a median (interquartile, IQR) age of 38 (27–55) years and 6 (3–8) children. Majority (40%) reported attaining secondary-level education. All IDI respondents were female with a median (IQR) age of 27 (24–35) years and 4 (2–5) children. Majority (80%) had attained primary-level education. We found that religious and socio-cultural norms as well as gender stereotypes were important influences on the uptake and utilization of maternal health services, including facility-based delivery and contraception. Key amongst this was the unspoken deference to the counsel of a prominent matriarchal figure in the decision-making process.

Conclusions

Among the Digo community of coastal Kenya, a unique social-cultural context comprising of a religious and gendered value belief system influences women’s reproductive health and rights. These findings highlight the important role of demand-side factors in influencing maternal health outcomes. In addition to addressing supply-side factors, programs in such settings should aim to address factors that leverage inherent social capital to drive demand for maternal health services ensuring that they are not only effective, but also responsive to the local context.

Institutional delivery service use and associated factors among women who delivered during the last 2 years in Dallocha town, SNNPR, Ethiopia

Aim

To determine the institutional delivery service use and identify factors associated among women who delivered during the last two years in Dallocha town.

Design

A community-based cross-sectional study.

Methods

The study was conducted from 10 March-10 April 2016. A total of 411 study participants were selected by using systematic sampling method. The source population was all reproductive age group mothers. Bivariate and multiple logistic regression was conducted.

Results

Institutional delivery was 304 (74%). Factors associated with increased likelihood of institutional delivery were owning a radio or television, making more than four antenatal care visits, knowing at least one maternity service advantage. Not knowing about at least one benefit institutional delivery decreased the likelihood of institutional delivery.

Conclusion

Three-quarters of the mothers delivered at the health institution. Accordingly, promotion of antenatal care follow-up, in-service training of health professionals and health education is recommended.

"Our voices matter": a before-after assessment of the effect of a community-participatory intervention to promote uptake of maternal and child health services in Kwale, Kenya

Background

Community-participatory approaches are important for effective maternal and child health interventions. A community-participatory intervention (the Dialogue Model) was implemented in Kwale County, Kenya to enhance uptake of select maternal and child health services among women of reproductive age.

Methods

Community volunteers were trained to facilitate Dialogue Model sessions in community units associated with intervention health facilities in Matuga, Kwale. Selection of intervention facilities was purposive based on those that had an active community unit in existence. For each facility, uptake of family planning, antenatal care and facility-based delivery as reported in the District Health Information System (DHIS)-2 was compared pre- (October 2012 – September 2013) versus post- (January – December 2016) intervention implementation using a paired sample t-test.

Results

Between October 2013 and December 2015, a total of 570 Dialogue Model sessions were held in 12 community units associated with 10 intervention facilities. The median [interquartile range (IQR)] number of sessions per month per facility was 2 (1–3). Overall, these facilities reported 15, 2 and 74% increase in uptake of family planning, antenatal care and facility-based deliveries, respectively. This was statistically significant for family planning pre- (Mean (M) = 1014; Standard deviation (SD) = 381) versus post- (M = 1163; SD = 400); t (18) = − 0.603, P = 0.04) as well as facility-based deliveries pre- (M = 185; SD = 216) versus post- (M = 323; SD = 384); t (18) = − 0.698, P = 0.03).

Conclusions

A structured, community-participatory intervention enhanced uptake of family planning services and facility-based deliveries in a rural Kenyan setting. This approach is useful in addressing demand-side factors by providing communities with a stake in influencing their health outcomes.

Electronic supplementary material

The online version of this article (10.1186/s12913-018-3739-9) contains supplementary material, which is available to authorized users.