Impact of the Helping Mothers Survive Bleeding After Birth learning programme on care provider skills and maternal health outcomes in low-income countries - An integrative review

Ensemble machine learning framework for predicting maternal health risk during pregnancy

Maternal health risks can cause a range of complications for women during pregnancy. High blood pressure, abnormal glucose levels, depression, anxiety, and other maternal health conditions can all lead to pregnancy complications. Proper identification and monitoring of risk factors can assist to reduce pregnancy complications. The primary goal of this research is to use real-world datasets to identify and predict Maternal Health Risk (MHR) factors. As a result, we developed and implemented the Quad-Ensemble Machine Learning framework to predict Maternal Health Risk Classification (QEML-MHRC). The methodology used a vacxsriety of Machine Learning (ML) models, which then integrated with four ensemble ML techniques to improve prediction. The dataset collected from various maternity hospitals and clinics subjected to nineteen training and testing tests. According to the exploratory data analysis, the most significant risk factors for pregnant women include high blood pressure, low blood pressure, and high blood sugar levels. The study proposed a novel approach to dealing with high-risk factors linked to maternal health. Dealing with class-specific performance elaborated further to properly understand the distinction between high, low, and medium risks. All tests yielded outstanding results when predicting the amount of risk during pregnancy. In terms of class performance, the dataset associated with the "HR" class outperformed the others, predicting 90% correctly. GBT with ensemble stacking outperformed and demonstrated remarkable performance for all evaluation measure (0.86) across all classes in the dataset. The key success of the models used in this work is the ability to measure model performance using a class-wise distribution. The proposed approach can help medical experts assess maternal health risks, saving lives and preventing complications throughout pregnancy. The prediction approach presented in this study can detect high-risk pregnancies early on, allowing for timely intervention and treatment. This study's development and findings have the potential to raise public awareness of maternal health issues.

Usefulness of a low-cost simulation model for teaching internal manual aortic compression. A survey-based mannequin evaluation

OBJECTIVE

To evaluate the users' opinion on internal manual aortic compression (IMAC) training, using a low-cost simulation model.

METHODS

An educational strategy was designed to teach IMAC, which included: (1) guided reading of educational material and viewing an explanatory video of IMAC; (2) an introductory lecture with the anatomical considerations, documentation of the cessation of femoral arterial flow during IMAC, and real clinical cases in which this procedure was used; and (3) simulated practice of IMAC with a new low-cost manikin. The educational strategy was applied during three postpartum hemorrhage workshops in three Latin American countries and the opinions of the participants were measured with a survey.

RESULTS

Almost all of the participants in the IMAC workshop, including the simulation with the low-cost mannikin, highlighted the usefulness of the strategy (scores of 4/5 and 5/5 on the Likert scale) and would recommend it to colleagues.

CONCLUSION

We present a low-cost simulation model for IMAC as the basis of an educational strategy perceived as very useful by most participants. The execution of this strategy in other populations and its impact on postpartum hemorrhage management should be evaluated in further studies.

Using process-oriented groups reflections with health care providers to improve childbirth care in the Democratic Republic of Congo - An implementation study

OBJECTIVE

The ability to systematically reflect on care during labour and birth needs to be developed among health care providers. This study investigates the experiences of health care providers who have participated in process-oriented group reflections. The activity of group reflections was one of the three pillars of a training intervention seeking to implement evidence-based care routines during labour and birth that could contribute to reduced mortality and improved maternal and newborn health in the Democratic Republic of Congo (DRC).

METHODS

Using a qualitative approach, we interviewed 131 health care providers, in focus groups (n = 19) and individually (n = 2). Analysis of transcribed interviews was conducted using qualitative content analysis according to Elo and Kyngäs.

RESULTS

Group reflections added essential knowledge to the other components of the three-pillar training intervention. Through sharing and analysing care situations health care providers got increased self-awareness, tools to achieve structured and safe care routines, and to practice teamworking.

CONCLUSION

Using a structured model of process-oriented group reflection for health care providers on care during labour and birth proved to be a vital aspect of the training intervention, as it added knowledge to the skills gained through theoretical and simulation-based education. The three-pillar training intervention improved care routines that supported healthy births and management of complications. We recommend that structured and secure group reflections be included in similar training activities in the DRC and elsewhere, and assessed in further studies.

"Safer Births Bundle of Care" Implementation and Perinatal Impact at 30 Hospitals in Tanzania-Halfway Evaluation

Safer Births Bundle of Care (SBBC) consists of innovative clinical and training tools for improved labour care and newborn resuscitation, integrated with new strategies for continuous quality improvement. After implementation, we hypothesised a reduction in 24-h newborn deaths, fresh stillbirths, and maternal deaths by 50%, 20%, and 10%, respectively. This is a 3-year stepped-wedged cluster randomised implementation study, including 30 facilities within five regions in Tanzania. Data collectors at each facility enter labour and newborn care indicators, patient characteristics and outcomes. This halfway evaluation reports data from March 2021 through July 2022. In total, 138,357 deliveries were recorded; 67,690 pre- and 70,667 post-implementations of SBBC. There were steady trends of increased 24-h newborn and maternal survival in four regions after SBBC initiation. In the first region, with 13 months of implementation (n = 15,658 deliveries), an estimated additional 100 newborns and 20 women were saved. Reported fresh stillbirths seemed to fluctuate across time, and increased in three regions after the start of SBBC. Uptake of the bundle varied between regions. This SBBC halfway evaluation indicates steady reductions in 24-h newborn and maternal mortality, in line with our hypotheses, in four of five regions. Enhanced focus on uptake of the bundle and the quality improvement component is necessary to fully reach the SBBC impact potential as we move forward.

A realist review of interventions targeting maternal health in low- and middle-income countries

Maternal mortality is disproportionately higher in low- and middle-income countries compared to other parts of the world. International research efforts are reflective of the urgency to improve global maternal outcomes. The existing literature of maternal health interventions in low- and middle-income countries targets a variety of populations and intervention types. However, there is a notable lack of systemic reviews that examine the wider contextual and mechanistic factors that have contributed to the outcomes produced by interventions. This article aims to use realist synthesis design to identify and examine the relationships between the contexts, mechanisms and outcomes of maternal health interventions conducted in low- and middle-income countries. This will inform evidence-based practice for future maternal health interventions. In May 2022, we searched four electronic databases for systematic reviews of maternal health interventions in low- and middle-income countries published in the last 5 years. We used open and axial coding of contexts, mechanisms and outcomes to develop an explanatory framework for intervention effectiveness. After eligibility screening and full-text analysis, 44 papers were included. The majority of effective interventions reported good healthcare system contexts, especially the importance of infrastructural capacity to implement and sustain the intervention. Most intervention designs used increasing knowledge and awareness at an individual and healthcare-provider level to produce intended outcomes. The majority of outcomes reported related to uptake of healthcare services by women. All mechanism themes had a relationship with this outcome. Health system infrastructure must be considered in interventions to ensure effective implementation and sustainability. Healthcare-seeking behaviours are embedded within social and cultural norms, environmental conditions, family influences and provider attitudes. Therefore, effective engagement with communities and families is important to create new norms surrounding pregnancy and delivery. Future research should explore community mobilization and involvement to enable tailored interventions with optimal contextual fit.

Implementation of a three-pillar training intervention to improve maternal and neonatal healthcare in the Democratic Republic Of Congo: a process evaluation study in an urban health zone

Background

Numerous quality-improvement projects including healthcare professional training are conducted globally every year, but there is a gap between the knowledge obtained in the training and its implementation in practice and policy. A quality-improvement programme was conducted in eastern Democratic Republic of Congo (DRC) to reduce maternal and neonatal mortality and morbidity.

Objective

This study explores the implementation process, mechanisms of impact, and outcomes of a training intervention addressing labour and birth management and involving healthcare providers in an urban health zone in eastern part of DRC.

Methods

In 2019, master trainers were educated and in turn trained facilitators from seven participating healthcare facilities, which received the necessary equipment. Data comprised statistics on maternal and neonatal birth outcomes for the years before and after the training intervention, and focus group discussions (n = 18); and interviews (n = 2) with healthcare professionals, at the end of (n = 52) and after the training intervention (n = 59), respectively. The analysis was guided by a process evaluation framework, using descriptive statistics and content analysis.

Results

The three-pillar training intervention using a low-dose, high-frequency approach was successfully implemented in terms of fidelity, dose, adaptation, and reach. Several improved care routines were established, including improved planning, teamwork, and self-reflection skills, as well as improved awareness of the influence of the care environment, of having a respectful encounter, and of allowing a companion to be present with the birthing woman. The proportions of emergency caesareans decreased and of vaginal births increased without an increase in maternal and neonatal complications.

Conclusion

The findings of this study are encouraging and provide learnings for other healthcare facilities in DRC as well as other low-income countries. When designing similar training interventions, it is crucial to consider contextual factors such as incentives and to measure more salutogenic outcomes.

Ensemble learning-based feature engineering to analyze maternal health during pregnancy and health risk prediction

Maternal health is an important aspect of women’s health during pregnancy, childbirth, and the postpartum period. Specifically, during pregnancy, different health factors like age, blood disorders, heart rate, etc. can lead to pregnancy complications. Detecting such health factors can alleviate the risk of pregnancy-related complications. This study aims to develop an artificial neural network-based system for predicting maternal health risks using health data records. A novel deep neural network architecture, DT-BiLTCN is proposed that uses decision trees, a bidirectional long short-term memory network, and a temporal convolutional network. Experiments involve using a dataset of 1218 samples collected from maternal health care, hospitals, and community clinics using the IoT-based risk monitoring system. Class imbalance is resolved using the synthetic minority oversampling technique. DT-BiLTCN provides a feature set to obtain high accuracy results which in this case are provided by the support vector machine with a 98% accuracy. Maternal health exploratory data analysis reveals that the health conditions which are the strongest indications of health risk during pregnancy are diastolic and systolic blood pressure, heart rate, and age of pregnant women. Using the proposed model, timely prediction of health risks associated with pregnant women can be made thus mitigating the risk of health complications which helps to save lives.

Contextual factors influencing a training intervention aimed at improved maternal and newborn healthcare in a health zone of the Democratic Republic of Congo

Background

Maternal and neonatal mortality and morbidity in the Democratic Republic of Congo (DRC) are among the highest worldwide. As part of a quality improvement programme in a health zone in the DRC aimed at contributing to reduced maternal and neonatal mortality and morbidity, a three-pillar training intervention around childbirth was developed and implemented in collaboration between Swedish and Congolese researchers and healthcare professionals. The aim of this study is to explore contextual factors influencing this intervention.

Methods

A qualitative research design was used, with data collected through focus group discussions (n = 7) with healthcare professionals involved in the intervention before and at the end (n = 9). Transcribed discussions were inductively analysed using content analysis.

Results

Three generic categories describe the contextual factors influencing the intervention: i) Incentives motivated participants’ efforts to begin a training programme; ii) Involving the local health authorities was important; and (iii) Having physical space, electricity, and equipment in place was crucial.

Conclusions

This study and similar ones highlight that incentives of various types are crucial contextual factors that influence training interventions, and have to be considered already in the planning of such interventions. One such factor is expectations of monetary incentives. To meet this in a small research project like ours would require a reduction of the scale and thus limit the implementation of new evidence-based knowledge into practice aimed at reducing maternal mortality and morbidity.