Structural equation modeling on the relationship between maternal characteristics and pregnancy complications: A study based on National Family Health Survey

Predicting risk of preterm birth in singleton pregnancies using machine learning algorithms

We aimed to develop, train, and validate machine learning models for predicting preterm birth (<37 weeks' gestation) in singleton pregnancies at different gestational intervals. Models were developed based on complete data from 22,603 singleton pregnancies from a prospective population-based cohort study that was conducted in 51 midwifery clinics and hospitals in Wenzhou City of China between 2014 and 2016. We applied Catboost, Random Forest, Stacked Model, Deep Neural Networks (DNN), and Support Vector Machine (SVM) algorithms, as well as logistic regression, to conduct feature selection and predictive modeling. Feature selection was implemented based on permutation-based feature importance lists derived from the machine learning models including all features, using a balanced training data set. To develop prediction models, the top 10%, 25%, and 50% most important predictive features were selected. Prediction models were developed with the training data set with 5-fold cross-validation for internal validation. Model performance was assessed using area under the receiver operating curve (AUC) values. The CatBoost-based prediction model after 26 weeks' gestation performed best with an AUC value of 0.70 (0.67, 0.73), accuracy of 0.81, sensitivity of 0.47, and specificity of 0.83. Number of antenatal care visits before 24 weeks' gestation, aspartate aminotransferase level at registration, symphysis fundal height, maternal weight, abdominal circumference, and blood pressure emerged as strong predictors after 26 completed weeks. The application of machine learning on pregnancy surveillance data is a promising approach to predict preterm birth and we identified several modifiable antenatal predictors.

A Review of the National Family Health Survey Data in Addressing India’s Maternal Health Situation

Objective: This study aims to understand the trend of research conducted on issues of maternal health in India considering data provided in five rounds of National Family Health Survey (NFHS).

Methods: Systematic review of literature has been conducted using multi-stage search and review process adapted from Page et al.’s (2021) PRISMA. Initially 14,570 studies were identified and only 134 articles meeting selection criterion were considered in this study.

Results: Approximately 32% studies have focused on regional and state variation of maternal health status; while 27% dealt with utilization of maternal healthcare services; and 19% the socio-economic determinants of maternal health. While few studies have discussed the place of delivery, antenatal care and post-natal care visits, only five studies focus on issues related to women’s autonomy, including their health-seeking behaviour, knowledge, attitude and practices related to maternal health.

Conclusion: Non-communicable diseases and its role in maternal health still remains an unexplored domain of research on maternal health in India. Moreover, there exists geographical skewness in the number of studies conducted, focusing especially on few provinces while none on few others.

How socioeconomic status, social capital and functional independence are associated with subjective wellbeing among older Indian adults? A structural equation modeling analysis

Background

Subjective well-being (SWB) is of particular interest among gerontologists and health researchers with important implications for interventions especially in poor-resource settings. This study aimed to explore the possible pathways from socioeconomic status (SES), functional independence and social capital towards SWB among older adults in India.

Methods

Cross-sectional data from the “Building a Knowledge Base on Population Aging in India” (BKPAI) survey with a total sample of 9231 older adults aged 60 years and above were used. The outcome variable was low SWB (LSWB). The study used univariate and bivariate analysis for reporting the initial results. Further, the study employed the structural equation modeling (SEM) technique using maximum likelihood estimation (MLE) procedure to estimate the covariance matrix.

Results

Overall, about 27% of older adults reported LSWB. Reporting LSWB was more prevalent among older adults who had no income (30.8%) and those who had income but not sufficient to fulfil their basic needs (39.4%, p < 0.001). The prevalence of reporting LSWB was significantly higher among older adults who had no asset ownership (36.5%, p < 0.001) than those who had asset ownership. The path from the SEM shows that LSWB and SES are negatively related to each other. Moreover, LSWB had significant negative relationship with independence (β = -0.032, p < 0.001) and social capital (β = -0.020; p < 0.001). In addition, results found a positive relationship between SES and independence (β = 0.019; p < 0.001), SES and social capital (β = 0.016; p < 0.001), and independence and social capital (β = 0.033; p < 0.001).

Conclusions

The findings highlight that higher SES, good physical functioning as well as favorable social capital are interdependent factors of late-life wellbeing and a multidimensional approach in policymaking can ensure a successful and active ageing among older Indian adults.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12889-022-14215-4.

Why women choose to deliver at home in India: a study of prevalence, factors, and socio-economic inequality

BACKGROUND

To promote institutional delivery, the Government of India, through the Janani Suraksha Yojana (JSY) program, gives monetary reward to all pregnant women who give birth at the government or private health center. Despite providing cash assistance, a higher number of women are still preferring delivering at home. Therefore, this study sought to determine the prevalence of home births and identifying the factors influencing women's choice of home deliveries.

METHODS

Data from the National Family Health Survey (NFHS) conducted during 2005-06 and 2015-16 were used in the study. The respondents were women 15-49 years; a sample of 36,850 and 190,898 women in 2005-06 and 2015-16 respectively were included in the study. Multivariate logistic regression was used to determine the factors influencing home delivery. Income-related inequality in home delivery was quantified by the concentration index (CI) and the concentration curve (CC), and decomposition analysis was used to examine the inequality in the prevalence of home deliveries.

RESULTS

The prevalence of home deliveries has reduced from 58.5% in 2005-06 to 18.9% in 2015-16. The odds of delivering babies at home were lower among women who had full ANC in 2005-06 [AOR: 0.34; CI: 0.28-0.41] and in 2015-16 [AOR: 0.41; CI: 0.38-0.45] and were higher among women with four or higher parity in 2005-06 [AOR: 1.70; CI: 1.49-1.92] and in 2015-19 [AOR: 2.16; CI: 2.03-2.30]. Furthermore, the odds of delivering babies at home were higher among rural women and were lower among women with higher education. It was found that the value of CI increased from - 0.25 to - 0.39 from 2005-06 to 2015-16; this depicts that women delivering babies at home got more concentrated among women from lower socio-economic status.

CONCLUSION

There is a need to promote institutional deliveries, particular focus to be given to poor women, women with higher parity, uneducated women, and rural women. ANC is the most concurring contact point for mothers to get relevant information about the risks and complications they may encounter during delivery. Therefore, effort should be directed to provide full ANC. Targeted interventions are called for to bring improvements in rural areas.

An assessment of the role of socio-economic, maternal and service utilization factors in increasing self-reported maternal complications in India

Background

Self-reported maternal complications are associated with maternal morbidity, deliveries by C-section, postpartum depression, and maternal death. Thus, it is necessary to examine the contribution of socio-demographic and maternal characteristics, as well as service utilization in the rising self-reporting of maternal complications (difficulty with daylight vision, convulsions, swelling of the legs, body or face, heavy vaginal bleeding or high fever) in India. The study aimed at examining the factors that have influenced the increasing prevalence of maternal complications between 2005–06 and 2015–16 in India.

Methods

Data from the two most recent rounds of the National Family Health Survey, which covered a sample of 36,850 and 190,898 women respectively who delivered in the last five years preceding the survey has been used. Logistic regression analysis was performed to carve out the factors which significantly contributed to maternal complications among women aged 15 – 49 years in India. With the help of the Fairlie decomposition technique, the study quantified the contribution of factors which influenced the changes in maternal complications in the period from 2005–06 to 2015–16.

Results

A significant increase was seen in the prevalence of maternal complications — from 43.6% to 53.7% between the years 2005–06 and 2015–16. About 21% of the increase could be explained by certain maternal, households level factors, service utilization and birth outcomes. For example, service utilization, in which 13% was attributed to the place of delivery and 6% to postnatal care, was the major contributor to the increase in maternal complications from 2005–06 to 2015–16). This was followed by individual-level factors like education (2%), body mass index (4%) and tobacco use,. It was also found that household-level factors like standard of living (-3.7%) and region (-1.4%), and birth weight contributed to the reduction of complications during the period.

Conclusion

The increase in the prevalence of maternal complications in India could be attributed mainly attributed to increase in reporting behavior, an outcome of increased utilization of maternal healthcare services, and increase in BMI. However, reduced prevalence of maternal complications can be attributed to the decrease in the prevalence of low-birth-weight babies and tobacco use among women in India.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12884-021-03997-x.