Risk factors of neonatal mortality and child mortality in Bangladesh

Effect of maternal vaccination on infant morbidity in Bangladesh

BACKGROUND

Risk factors of infant mortality in Africa and south Asian countries have been broadly discussed. However, infant morbidity is largely underestimated. We analyzed the data from a randomized vaccine trial in Bangladesh to identify and assess the effect of risk factors on infant morbidity.

METHODS

Pregnant women were randomly assigned to receive either inactivated influenza vaccine or pneumococcal polysaccharide vaccine and the infants were randomly assigned to receive 7-valent pneumococcal conjugate vaccine or Hib conjugate vaccine at week 6, 10 and 14. The data were collected from August 2004 through December 2005. Each pair of infant and mother were followed for 24 weeks after birth with weekly visits. Generalized estimating equations (GEE) for repeated measurements and Poisson regression models were used to identify the risk factors and evaluate their effect on the longitudinal incidence and total number of episodes of respiratory illness with fever (RIF), diarrhea disease, ear problem and pneumonia.

RESULTS

A total of 340 pregnant women were randomized with mean age of 25 years. The baseline mother and infant characteristics were similar between two treatment groups. Exclusive breastfeeding and higher paternal education level were common factors associated with lower infant morbidity of RIF (adjusted OR = 0.40 and 0.94 with p < 0.01 and p = 0.02, respectively), diarrhea disease (adjusted OR = 0.39 and 0.95 with p < 0.01 and p = 0.04, respectively), and ear problem (adjusted OR = 0.20 and 0.76 with p < 0.01 and p < 0.01, respectively). Maternal influenza vaccine significantly reduced the incidence of RIF (adjusted OR = 0.54; p < 0.01) but not diarrhea disease or ear problem (p > 0.05). Female infants had lower incidence of diarrhea disease (adjusted OR = 0.67; p = 0.01) and ear problem (adjusted OR = 0.12; p = 0.01).

CONCLUSIONS

Maternal influenza vaccination, exclusive breastfeeding, female children, and higher paternal education level significantly reduced the infant morbidity within the 24 weeks after birth in Bangladesh.

Exploring causes of neonatal mortality in south east of Iran: A qualitative study

AIM

Neonatal mortality (NM) is a significant global challenge that has a profound impact on families, particularly mothers. To address this challenge, the first step is to identify its underlying causes. Accordingly, this study aimed to explore the phenomenon by consulting with stakeholders, including mothers and experts.

STUDY DESIGN

This study utilized a qualitative design, conducting in-depth interviews with 16 mothers and 15 healthcare experts to gather information. A conventional content analysis approach was employed to analyze the data.

RESULTS

NM is influenced by personal, systemic, and socioeconomic factors. Personal factors can be further divided into those related to the neonate and those related to the mother. Systemic factors are primarily related to the healthcare system, while socioeconomic factors include low literacy, low income, lack of access to healthcare, and consanguineous marriage.

CONCLUSION

NM is influenced by a wide range of factors that require separate and targeted interventions to reduce its incidence. In the short term, priority should be given to preventable factors that can be addressed through simple interventions, such as screening mothers for urinary tract infections, educating mothers, and preparing them for pregnancy with necessary lab tests and supplements. In the long term, preventing premature birth, addressing maternal addiction, family poverty, and shortages in healthcare equipment and personnel must be thoroughly addressed.

High-risk fertility behaviours among women in sub-Saharan Africa

BACKGROUND

High-risk fertility behaviours such as too early or advanced age at delivery, shorter birth interval, birth order and a higher number of live births to a woman often lead to adverse maternal and child health outcomes. We assessed high-risk fertility behaviours and their associated factors among women in sub-Saharan Africa (SSA).

METHODS

Data on 200 716 women pooled from the demographic and health surveys of 27 countries conducted between 2010 and 2020 in SSA were analysed. High-risk fertility behaviour from four indicators, mother aged <18 years at the time of delivery; mother aged >34 years at the time of delivery; mother of a child born after a short birth interval (<24 months) and mother of high parity (>3 children), was derived. Multi-level multi-variable logistic regression analyses were carried out and the results were presented as adjusted odds ratios at 95% confidence interval.

RESULTS

Women who were in polygamous marriages had higher odds of single and multiple high-risk fertility behaviour compared with their counterparts who were in monogamous marriages. Women with middle or high maternal decision-making power had higher odds of single and multiple high-risk fertility behaviours compared with those with low decision-making power. Single and multiple high-risk fertility behaviours were lower among women with access to family planning, those with at least primary education and those whose partners had at least primary education compared with their counterparts who had no access to family planning, those with no formal education and those whose partners had no formal education.

CONCLUSION

Family structure, women's decision-making power, access to family planning, women's level of education and partners' level of education were identified as predictors of high-risk fertility behaviours in SSA. These findings are crucial in addressing maternal health and fertility challenges. Policy makers, maternal health and fertility stakeholders in countries with high prevalence of high parity and short birth intervals should organize programs that will help to reduce the prevalence of these high-risk factors, taking into consideration the factors that predispose women to high-risk fertility behaviours.

Examining the influence of correlates on different quantile survival times: infant mortality in Bangladesh

BACKGROUND

Several studies have identified factors influencing infant mortality, but, to the best of knowledge, no studies assessed the factors considering unequal effects on different survival times of infant mortality in Bangladesh. In this study, it was examined how a set of covariates behaves on different quantile survival times related with the infant mortality.

METHODS

Data obtained from Bangladesh multiple indicator cluster survey (BMICS), 2019 have been used for purpose of the study. A total of 9,183 reproductive women were included in the study who gave their most recent live births within two years preceding the survey. Kaplan-Meier product limit approach has been applied to find the survival probabilities for the infant mortality, and the log-rank test has also been used to observe the unadjusted association between infant mortality and selected covariates. To examine the unequal effects of the covariates on different quantile survival time of infant mortality, the Laplace survival regression model has been fitted. The results obtained from this model have also been compared with the results obtained from the classical accelerated failure time (AFT) and Cox proportional hazard (Cox PH) models.

RESULTS

The infant mortality in Bangladesh is still high which is around 28 per 1000 live births. In all the selected survival regression models, the directions of regression coefficients were similar, but the heterogenous effects of covariates on survival time were observed in quantile survival model. Several correlates such as maternal age, education, gender of index child, previous birth interval, skilled antenatal care provider, immediate breastfeeding etc. were identified as potential factors having higher impact on initial survival times.

CONCLUSION

Infant mortality was significantly influenced by the factors more in the beginning of the infant's life period than at later stages, suggesting that receiving proper care at an early age will raise the likelihood of survival. Policy-making interventions are required to reduce the infant deaths, and the study findings may assist policy makers to revise the programs so that the sustainable development goal 3.2 can be achieved in Bangladesh.

Socioeconomic inequality in the prevalence of low birth weight and its associated determinants in Bangladesh

BACKGROUND AND OBJECTIVE

Low birth weight (LBW) is a major risk factor of child mortality and morbidity during infancy (0-3 years) and early childhood (3-8 years) in low and lower-middle-income countries, including Bangladesh. LBW is a vital public health concern in Bangladesh. The objective of the research was to investigate the socioeconomic inequality in the prevalence of LBW among singleton births and identify the significantly associated determinants of singleton LBW in Bangladesh.

MATERIALS AND METHODS

The data utilized in this research was derived from the latest nationally representative Bangladesh Demographic and Health Survey, 2017-18, and included a total of 2327 respondents. The concentration index (C-index) and concentration curve were used to investigate the socioeconomic inequality in LBW among the singleton newborn babies. Additionally, an adjusted binary logistic regression model was utilized for calculating adjusted odds ratio and p-value (<0.05) to identify the significant determinants of LBW.

RESULTS

The overall prevalence of LBW among singleton births in Bangladesh was 14.27%. We observed that LBW rates were inequitably distributed across the socioeconomic groups (C-index: -0.096, 95% confidence interval: [-0.175, -0.016], P = 0.029), with a higher concentration of LBW infants among mothers living in the lowest wealth quintile (poorest). Regression analysis revealed that maternal age, region, maternal education level, wealth index, height, age at 1st birth, and the child's aliveness (alive or died) at the time of the survey were significantly associated determinants of LBW in Bangladesh.

CONCLUSION

In this study, socioeconomic disparity in the prevalence of singleton LBW was evident in Bangladesh. Incidence of LBW might be reduced by improving the socioeconomic status of poor families, paying special attention to mothers who have no education and live in low-income households in the eastern divisions (e.g., Sylhet, Chittagong). Governments, agencies, and non-governmental organizations should address the multifaceted issues and implement preventive programs and policies in Bangladesh to reduce LBW.

Multicenter Study on COVID-19 Lung Computed Tomography Segmentation with varying Glass Ground Opacities using Unseen Deep Learning Artificial Intelligence Paradigms: COVLIAS 1.0 Validation

Variations in COVID-19 lesions such as glass ground opacities (GGO), consolidations, and crazy paving can compromise the ability of solo-deep learning (SDL) or hybrid-deep learning (HDL) artificial intelligence (AI) models in predicting automated COVID-19 lung segmentation in Computed Tomography (CT) from unseen data leading to poor clinical manifestations. As the first study of its kind, “COVLIAS 1.0-Unseen” proves two hypotheses, (i) contrast adjustment is vital for AI, and (ii) HDL is superior to SDL. In a multicenter study, 10,000 CT slices were collected from 72 Italian (ITA) patients with low-GGO, and 80 Croatian (CRO) patients with high-GGO. Hounsfield Units (HU) were automatically adjusted to train the AI models and predict from test data, leading to four combinations—two Unseen sets: (i) train-CRO:test-ITA, (ii) train-ITA:test-CRO, and two Seen sets: (iii) train-CRO:test-CRO, (iv) train-ITA:test-ITA. COVILAS used three SDL models: PSPNet, SegNet, UNet and six HDL models: VGG-PSPNet, VGG-SegNet, VGG-UNet, ResNet-PSPNet, ResNet-SegNet, and ResNet-UNet. Two trained, blinded senior radiologists conducted ground truth annotations. Five types of performance metrics were used to validate COVLIAS 1.0-Unseen which was further benchmarked against MedSeg, an open-source web-based system. After HU adjustment for DS and JI, HDL (Unseen AI) > SDL (Unseen AI) by 4% and 5%, respectively. For CC, HDL (Unseen AI) > SDL (Unseen AI) by 6%. The COVLIAS-MedSeg difference was < 5%, meeting regulatory guidelines.Unseen AI was successfully demonstrated using automated HU adjustment. HDL was found to be superior to SDL.

Eight pruning deep learning models for low storage and high-speed COVID-19 computed tomography lung segmentation and heatmap-based lesion localization: A multicenter study using COVLIAS 2.0

BACKGROUND

COVLIAS 1.0: an automated lung segmentation was designed for COVID-19 diagnosis. It has issues related to storage space and speed. This study shows that COVLIAS 2.0 uses pruned AI (PAI) networks for improving both storage and speed, wiliest high performance on lung segmentation and lesion localization.

METHOD

ology: The proposed study uses multicenter ∼9,000 CT slices from two different nations, namely, CroMed from Croatia (80 patients, experimental data), and NovMed from Italy (72 patients, validation data). We hypothesize that by using pruning and evolutionary optimization algorithms, the size of the AI models can be reduced significantly, ensuring optimal performance. Eight different pruning techniques (i) differential evolution (DE), (ii) genetic algorithm (GA), (iii) particle swarm optimization algorithm (PSO), and (iv) whale optimization algorithm (WO) in two deep learning frameworks (i) Fully connected network (FCN) and (ii) SegNet were designed. COVLIAS 2.0 was validated using "Unseen NovMed" and benchmarked against MedSeg. Statistical tests for stability and reliability were also conducted.

RESULTS

Pruning algorithms (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO showed improvement in storage by 92.4%, 95.3%, 98.7%, and 99.8% respectively when compared against solo FCN, and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO showed improvement by 97.1%, 97.9%, 98.8%, and 99.2% respectively when compared against solo SegNet. AUC > 0.94 (p < 0.0001) on CroMed and > 0.86 (p < 0.0001) on NovMed data set for all eight EA model. PAI <0.25 s per image. DenseNet-121-based Grad-CAM heatmaps showed validation on glass ground opacity lesions.

CONCLUSIONS

Eight PAI networks that were successfully validated are five times faster, storage efficient, and could be used in clinical settings.

Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson’s Disease Affected by COVID-19: A Narrative Review

Background and Motivation: Parkinson’s disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

Role of Artificial Intelligence in Radiogenomics for Cancers in the Era of Precision Medicine

Simple Summary

Recently, radiogenomics has played a significant role and offered a new understanding of cancer’s biology and behavior in response to standard therapy. It also provides a more precise prognosis, investigation, and analysis of the patient’s cancer. Over the years, Artificial Intelligence (AI) has provided a significant strength in radiogenomics. In this paper, we offer computational and oncological prospects of the role of AI in radiogenomics, as well as its offers, achievements, opportunities, and limitations in the current clinical practices.

Abstract

Radiogenomics, a combination of “Radiomics” and “Genomics,” using Artificial Intelligence (AI) has recently emerged as the state-of-the-art science in precision medicine, especially in oncology care. Radiogenomics syndicates large-scale quantifiable data extracted from radiological medical images enveloped with personalized genomic phenotypes. It fabricates a prediction model through various AI methods to stratify the risk of patients, monitor therapeutic approaches, and assess clinical outcomes. It has recently shown tremendous achievements in prognosis, treatment planning, survival prediction, heterogeneity analysis, reoccurrence, and progression-free survival for human cancer study. Although AI has shown immense performance in oncology care in various clinical aspects, it has several challenges and limitations. The proposed review provides an overview of radiogenomics with the viewpoints on the role of AI in terms of its promises for computational as well as oncological aspects and offers achievements and opportunities in the era of precision medicine. The review also presents various recommendations to diminish these obstacles.

Cardiovascular/Stroke Risk Assessment in Patients with Erectile Dysfunction-A Role of Carotid Wall Arterial Imaging and Plaque Tissue Characterization Using Artificial Intelligence Paradigm: A Narrative Review

PURPOSE

The role of erectile dysfunction (ED) has recently shown an association with the risk of stroke and coronary heart disease (CHD) via the atherosclerotic pathway. Cardiovascular disease (CVD)/stroke risk has been widely understood with the help of carotid artery disease (CTAD), a surrogate biomarker for CHD. The proposed study emphasizes artificial intelligence-based frameworks such as machine learning (ML) and deep learning (DL) that can accurately predict the severity of CVD/stroke risk using carotid wall arterial imaging in ED patients.

METHODS

Using the PRISMA model, 231 of the best studies were selected. The proposed study mainly consists of two components: (i) the pathophysiology of ED and its link with coronary artery disease (COAD) and CHD in the ED framework and (ii) the ultrasonic-image morphological changes in the carotid arterial walls by quantifying the wall parameters and the characterization of the wall tissue by adapting the ML/DL-based methods, both for the prediction of the severity of CVD risk. The proposed study analyzes the hypothesis that ML/DL can lead to an accurate and early diagnosis of the CVD/stroke risk in ED patients. Our finding suggests that the routine ED patient practice can be amended for ML/DL-based CVD/stroke risk assessment using carotid wall arterial imaging leading to fast, reliable, and accurate CVD/stroke risk stratification.

SUMMARY

We conclude that ML and DL methods are very powerful tools for the characterization of CVD/stroke in patients with varying ED conditions. We anticipate a rapid growth of these tools for early and better CVD/stroke risk management in ED patients.

Socioeconomic inequalities in stillbirth and neonatal mortality rates: evidence on Particularly Vulnerable Tribal Groups in eastern India

Background

Tribal peoples are among the most marginalised groups worldwide. Evidence on birth outcomes in these groups is scant. We describe inequalities in Stillbirth Rate (SBR), Neonatal Mortality Rate (NMR), and uptake of maternal and newborn health services between tribal and less disadvantaged groups in eastern India, and examine the contribution of poverty and education to these inequalities.

Methods

We used data from a demographic surveillance system covering a 1 million population in Jharkhand State (March 2017 – August 2019) to describe SBR, NMR, and service uptake. We used logistic regression analysis combined with Stata’s adjrr-command to estimate absolute and relative inequalities by caste/tribe (comparing Particularly Vulnerable Tribal Groups (PVTG) and other Scheduled Tribes (ST) with the less marginalised Other Backward Class (OBC)/none, using the Indian government classification), and by maternal education and household wealth.

Results

PVTGs had a higher NMR (59/1000) than OBC/none (31/1000) (rate ratio (RR): 1.92, 95%CI: 1.55–2.38). This was partly explained by wealth and education, but inequalities remained large after adjustment (adjusted RR: 1.59, 95%CI: 1.28–1.98). NMR was also higher among other STs (44/1000), but disparities were smaller (RR: 1.47, 95%CI: 1.23–1.75). There was a systematic gradient in NMR by maternal education and household wealth. SBRs were only higher in poorer groups (RR_{poorest vs. least poor}:1.56, 95%CI: 1.14–2.13). Uptake of facility-based services was low among PVTGs (e.g. institutional birth: 25% vs. 69% in OBC/none) and among poorer and less educated women. However, 65% of PVTG women with an institutional birth used a maternity vehicle vs. 34% among OBC/none. Visits from frontline workers (Accredited Social Health Activists [ASHAs]) were similar across groups, and ASHA accompaniment of institutional births was similar across caste/tribe groups, and higher among poorer and less educated women. Attendance in participatory women’s groups was similar across caste/tribe groups, and somewhat higher among richer and better educated women.

Conclusions

PVTGs are highly disadvantaged in terms of birth outcomes. Targeted interventions that reduce geographical barriers to facility-based care and address root causes of high poverty and low education in PVTGs are a priority. For population-level impact, they are to be combined with broader policies to reduce socio-economic mortality inequalities. Community-based interventions reach disadvantaged groups and have potential to reduce the mortality gap.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12939-022-01655-y.

Cardiovascular/Stroke Risk Stratification in Parkinson's Disease Patients Using Atherosclerosis Pathway and Artificial Intelligence Paradigm: A Systematic Review

Parkinson’s disease (PD) is a severe, incurable, and costly condition leading to heart failure. The link between PD and cardiovascular disease (CVD) is not available, leading to controversies and poor prognosis. Artificial Intelligence (AI) has already shown promise for CVD/stroke risk stratification. However, due to a lack of sample size, comorbidity, insufficient validation, clinical examination, and a lack of big data configuration, there have been no well-explained bias-free AI investigations to establish the CVD/Stroke risk stratification in the PD framework. The study has two objectives: (i) to establish a solid link between PD and CVD/stroke; and (ii) to use the AI paradigm to examine a well-defined CVD/stroke risk stratification in the PD framework. The PRISMA search strategy selected 223 studies for CVD/stroke risk, of which 54 and 44 studies were related to the link between PD-CVD, and PD-stroke, respectively, 59 studies for joint PD-CVD-Stroke framework, and 66 studies were only for the early PD diagnosis without CVD/stroke link. Sequential biological links were used for establishing the hypothesis. For AI design, PD risk factors as covariates along with CVD/stroke as the gold standard were used for predicting the CVD/stroke risk. The most fundamental cause of CVD/stroke damage due to PD is cardiac autonomic dysfunction due to neurodegeneration that leads to heart failure and its edema, and this validated our hypothesis. Finally, we present the novel AI solutions for CVD/stroke risk prediction in the PD framework. The study also recommends strategies for removing the bias in AI for CVD/stroke risk prediction using the PD framework.

Child marriage and its association with morbidity and mortality of under-5 years old children in Bangladesh

INTRODUCTION

Child marriage is a significant social and health concern in many low- and middle-income countries (LMICs). This harmful practice violates children's rights and continues to be widespread across developing nations like Bangladesh. This study investigated the mortality trend among Bangladeshi children and the impact of child marriage on under-5 children morbidity and mortality in Bangladesh.

METHODS AND MATERIALS

A sample of 8,321 children under-5 years old was analyzed using bivariate and multivariate statistical techniques collected from the recent 2017-18 BDHS data. Chi-square test and logistic regression (unadjusted and adjusted) were used to determine the influence of covariates on the target variable.

RESULTS

Results revealed that child mortality was significantly higher among children whose mothers married at an early age than their counterparts. Although the general trend in the prevalence of different childhood mortality in Bangladesh was declining gradually from 1993 to 2018, it was still high in 2018. Also, marriage after 18 years lessens likelihood of diarrhea (adjusted OR = 0.93; 95% CI: 0.76-1.16) and cough (adjusted OR = 0.91; 95% CI: 0.78-1.17) among children. Furthermore, findings reveal that likelihood of different child mortality is higher among early married women.

CONCLUSION

Immediate intervention through rigorous enforcement of policies and different programs to raise the age at marriage and by lessening socioeconomic disparities can combat the prevalence of high morbidity and mortality of under-5 years old children. Findings from this study will be helpful to accelerate strategies for achieving the Sustainable Development Goals (SDGs) related to child and maternal health by 2030.

Association of breast feeding and birth interval with child mortality in Pakistan: a cross-sectional study using nationally representative Demographic and Health Survey data

OBJECTIVES

This study analysed the association between breast feeding (BF) and birth interval (BI) (both succeeding and preceding) with neonatal mortality (NM), infant mortality (IM) and under-5 mortality (U5M).

DESIGN

This cross-sectional study used data from the Pakistan Demographic and Health Survey 2017-2018.

SETTINGS

All provinces, Islamabad and Federally Administered Tribal Areas were included in the analysis.

PARTICIPANTS

A total of 12 769 children born to ever-married multiparous women aged 30-49 years who gave live birth within 5 years preceding the interview. Multiple births are not included.

DATA ANALYSIS

Multivariate logistic regression analysis was used.

RESULTS

We found that BF was associated with nearly 98% lower risk of NM (OR 0.015; 95% CI: 0.01 to 0.03; p<0.001), 96% lower risk of IM (OR 0.038; 95% CI: 0.02 to 0.06; p<0.001) and 94% lower risk of U5M (OR 0.050; 95% CI: 0.03 to 0.08; p<0.001). Compared with optimal preceding birth interval (PBI) (36+ months), short PBI (<18 months) was associated with around six times higher risk of NM (OR 5.661; 95% CI: 2.78 to 11.53; p<0.001), over five times risk of IM (OR 4.704; 95% CI: 2.70 to 8.19; p<0.001) and over five times risk of U5M (OR 4.745; 95% CI: 2.79 to 8.07; p<0.001). Disaggregating the data by child's gender, place of residence and mother's occupational status showed that being ever breast fed was associated with a smaller risk of NM, IM and U5M in all three disaggregations. However, the risk of smaller PBI <18 months was generally more pronounced in female children (NM and U5M) or when the children lived in rural areas (NM, IM and U5M). PBI <18 months was associated with greater risk of NM and IM, and smaller risk of U5M when mothers did a paid job.

CONCLUSION

This study's significance lies in the fact that it has found BF and BI to be consistent protective factors against NM, IM and U5M. Given Pakistan's economic constraints, optimal BF and BI are the most cost-effective interventions to reduce child mortality.

Socio-demographic and environmental risk factors associated with multiple under-five child loss among mothers in Bangladesh

Background

Despite the substantial decline in child mortality globally over the last decade, reducing neonatal and under-five mortality in Bangladesh remains a challenge. Mothers who experienced multiple child losses could have substantial adverse personal and public health consequences. Hence, prevention of child loss would be extremely desirable during women’s reproductive years. The main objective of this study was to determine the risk factors associated with multiple under-five child loss from the same mother in Bangladesh.

Methods

In this study, a total of 15,877 eligible women who had given birth at least once were identified from the 2014 Bangladesh Demographic and Health Survey. A variety of count regression models were considered for identifying socio-demographic and environmental factors associated with multiple child loss measured as the number of lifetime under-five child mortality (U5M) experienced per woman.

Results

Of the total sample, approximately one-fifth (18.9%, n = 3003) of mothers experienced at least one child’s death during their reproductive period. The regression analysis results revealed that women in non-Muslim families, with smaller household sizes, with lower education, who were more advanced in their childbearing years, and from an unhygienic environment were at significantly higher risk of experiencing offspring mortality. This study also identified the J-shaped effect of age at first birth on the risk of U5M.

Conclusions

This study documented that low education, poor socio-economic status, extremely young or old age at first birth, and an unhygienic environment significantly contributed to U5M per mother. Therefore, improving women’s educational attainment and socio-economic status, prompting appropriate timing of pregnancy during reproductive life span, and increasing access to healthy sanitation are recommended as possible interventions for reducing under-five child mortality from a mother. Our findings point to the need for health policy decision-makers to target interventions for socio-economically vulnerable women in Bangladesh.

Systematic Review of Artificial Intelligence in Acute Respiratory Distress Syndrome for COVID-19 Lung Patients: A Biomedical Imaging Perspective

SARS-CoV-2 has infected over ∼165 million people worldwide causing Acute Respiratory Distress Syndrome (ARDS) and has killed ∼3.4 million people. Artificial Intelligence (AI) has shown to benefit in the biomedical image such as X-ray/Computed Tomography in diagnosis of ARDS, but there are limited AI-based systematic reviews (aiSR). The purpose of this study is to understand the Risk-of-Bias (RoB) in a non-randomized AI trial for handling ARDS using novel AtheroPoint-AI-Bias (AP(ai)Bias). Our hypothesis for acceptance of a study to be in low RoB must have a mean score of 80% in a study. Using the PRISMA model, 42 best AI studies were analyzed to understand the RoB. Using the AP(ai)Bias paradigm, the top 19 studies were then chosen using the raw-cutoff of 1.9. This was obtained using the intersection of the cumulative plot of "mean score vs. study" and score distribution. Finally, these studies were benchmarked against ROBINS-I and PROBAST paradigm. Our observation showed that AP(ai)Bias, ROBINS-I, and PROBAST had only 32%, 16%, and 26% studies, respectively in low-moderate RoB (cutoff>2.5), however none of them met the RoB hypothesis. Further, the aiSR analysis recommends six primary and six secondary recommendations for the non-randomized AI for ARDS. The primary recommendations for improvement in AI-based ARDS design inclusive of (i) comorbidity, (ii) inter-and intra-observer variability studies, (iii) large data size, (iv) clinical validation, (v) granularity of COVID-19 risk, and (vi) cross-modality scientific validation. The AI is an important component for diagnosis of ARDS and the recommendations must be followed to lower the RoB.

Modelling mortality within 28 days among preterm infants at a tertiary hospital in Lusaka, Zambia: a retrospective review of hospital-based records

Introduction

globally, almost half of all deaths in children under five years of age occur among neonates. We investigated the predictors of mortality within 28 days among preterm infants at a tertiary hospital in Lusaka, Zambia.

Methods

we reviewed admission records linked to birth, mortality, and hospital discharge from 1^st January 2018 to 30^th September 2019. Information was retrieved with a follow-up period of 28 days post-delivery to discharge/mortality. We used the Weibull hazards regression to establish the best predictor model for mortality among the neonates.

Results

a total of 3237 case records of women with a median age of 27 years (IQR, 22-33) were included in the study, of which 971 (30%) delivered term infants and 2267 (70%) preterm infants. The overall median survival time of the infants was 98 hours (IQR, 34-360). Preterm birth was not associated with increased hazards of mortality compared to term birth (p=0.078). Being in the Kangaroo Mother Care compared to Neonatal Intensive Care Unit (NICU), and a unit increase in birth weight were independently associated with reduced hazards of mortality. On the other hand, having hypoxic-ischemic encephalopathy, experiencing difficulty in feeding and vaginal delivery compared to caesarean section independently increased the hazards of mortality.

Conclusion

having hypoxic-ischemic encephalopathy, vaginal delivery, and experiencing difficulty in feeding increases the risk of mortality among neonates. Interventions to reduce neonatal mortality should be directed on these factors in this setting.

Child mortality associated with maternal HIV status: a retrospective analysis in Rwanda, 2005-2015

INTRODUCTION

Child mortality remains highest in regions of the world most affected by HIV/AIDS. The aim of this study was to assess child mortality rates in relation to maternal HIV status from 2005 to 2015, the period of rapid HIV treatment scale-up in Rwanda.

METHODS

We used data from the 2005, 2010 and 2015 Rwanda Demographic Health Surveys to derive under-2 mortality rates by survey year and mother's HIV status and to build a multivariable logistic regression model to establish the association of independent predictors of under-2 mortality stratified by mother's HIV status.

RESULTS

In total, 12 010 live births were reported by mothers in the study period. Our findings show a higher mortality among children born to mothers with HIV compared with HIV negative mothers in 2005 (216.9 vs 100.7 per 1000 live births) and a significant reduction in mortality for both groups in 2015 (72.0 and 42.4 per 1000 live births, respectively). In the pooled reduced multivariable model, the odds of child mortality was higher among children born to mothers with HIV, (adjusted OR, AOR 2.09; 95% CI 1.57 to 2.78). The odds of child mortality were reduced in 2010 (AOR 0.69; 95% CI 0.59 to 0.81) and 2015 (AOR 0.35; 95% CI 0.28 to 0.44) compared with 2005. Other independent predictors of under-2 mortality included living in smaller families of 1-2 members (AOR 5.25; 95% CI 3.59 to 7.68), being twin (AOR 4.93; 95% CI 3.51 to 6.92) and being offspring from mothers not using contraceptives at the time of the survey (AOR 1.6; 95% CI 1.38 to 1.99). Higher education of mothers (completed primary school: (AOR 0.74; 95% CI 0.64 to 0.87) and secondary or higher education: (AOR 0.53; 95% CI 0.38 to 0.74)) was also associated with reduced child mortality.

CONCLUSIONS

This study shows an important decline in under-2 child mortality among children born to both mothers with and without HIV in Rwanda over a 10-year span.

Rate, Risk Factors, and Causes of Neonatal Deaths in Jordan: Analysis of Data From Jordan Stillbirth and Neonatal Surveillance System (JSANDS)

Background: It has been estimated that 27.8 million neonates will die worldwide between 2018 and 2030 if no improvements in neonatal and maternal care take place. The aim of this study was to determine the rate, risk factors, and causes of neonatal mortality in Jordan. Methods: In August 2019, an electronic stillbirths and neonatal deaths surveillance system (JSANDS) was established in in three large cities through five hospitals. Data on all births, neonatal mortality and their causes, and other characteristics in the period between August 2019 and January 2020 were exported from the JSANDS and analyzed. Results: A total of 10,328 births [10,226 live births (LB) and 102 stillbirths] were registered in the study period, with a rate of 14.1 deaths per 1,000 LBs; 76% were early neonatal deaths and 24% were late deaths. The odds of deaths in the Ministry of Health hospitals were almost 21 times (OR = 20.8, 95% CI: 2.8, 153.1) higher than that in private hospitals. Low birthweight and pre-term babies were significantly more likely to die during the neonatal period compared to full-term babies. The odds of neonatal mortality were significantly higher among babies born to housewives compared to those who were born to employed women (OR = 2.7; 95% CI: 1.2, 6.0). Main causes of neonatal deaths that occurred pre-discharge were respiratory and cardiovascular disorders (43%) and low birthweight and pre-term (33%). The main maternal conditions that attributed to these deaths were complications of the placenta and cord, complications of pregnancy, and medical and surgical conditions. The main cause of neonatal deaths that occurred post-discharge were low birthweight and pre-term (42%). Conclusions: The rate of neonatal mortality have not decreased since 2012 and the majority of neonatal deaths occurred could have been prevented. Regular antenatal visits, in which any possible diseases or complications of pregnant women or fetal anomalies, need to be fully documented and monitored with appropriate and timely medical intervention to minimize such deaths.

Investigation of Socioeconomic Determinants on Child Death in South Asian Countries: A Panel Cointegration Analysis

This article is aimed to examine the relationship between socioeconomic factors and child mortality in South Asia because the relationship between child mortality and socioeconomic factors cannot be overlooked for better progress. Panel data were obtained from (World Development Indicators) and (Human Development Index) for the period 1990-2017. The data were quantitative. Levin, Lin, and Chu and I'm, Pesaran, and Shin test were used to check the stationarity of data. A cointegration test was applied to check the long-run association. Granger causality test was used to determine the direction of the relationship. Fully modified ordinary least squares and dynamic ordinary least squares techniques were used to examine the long-run and short-run impact of socioeconomic determinants on child mortality. The findings from this study showed the significant impact of education, unemployment, and health expenditure, access to improved water and sanitation facilities, and income inequality on child mortality. Overall results showed that there is a negative association between education and child mortality, access to improved water and access to sanitation facilities and child mortality, and health expenditure and child mortality, but there is a positive association between unemployment and income inequality with child mortality. The rate of child mortality is still very alarming in South Asian countries.

Exploring the influencing factors for non-utilisation of healthcare facilities during childbirth: a special mixed-method study of Bangladesh and 13 other low- and middle-income countries based on Demographic and Health Survey data

Objective

To identify the associated factors affecting the decision regarding institutional delivery for pregnant women in 14 low- and middle-income countries (LMICs).

Design

A special mixed-method design was used to combine cross-sectional studies for harmonising data from Bangladesh and 13 other countries to obtain extended viewpoints on non-utilisation of institutional healthcare facilities during childbirth.

Setting

Demographic and Health Survey (DHS) data for 14 LMICs were used for the study.

Participants

There are several kinds of datasets in the DHS. Among them ‘Individual Women’s Records’ was used as this study is based on all ever-married women.

Results

In the binary logistic and meta-analysis models for Bangladesh, ORs for birth order were 0.57 and 0.51 and for respondents’ age were 1.50 and 1.07, respectively. In all 14 LMICs, the most significant factors for not using institutional facilities during childbirth were respondents’ age (OR 0.903, 95% CI 0.790 to 1.032) and birth order (OR 0.371, 95% CI 0.327 to 0.421).

Conclusion

Birth order and respondents’ age were the two most significant factors for non-utilisation of healthcare facilities during childbirth in 14 LMICs.

Classification and prediction of diabetes disease using machine learning paradigm

Background and objectives

Diabetes is a chronic disease characterized by high blood sugar. It may cause many complicated disease like stroke, kidney failure, heart attack, etc. About 422 million people were affected by diabetes disease in worldwide in 2014. The figure will be reached 642 million in 2040. The main objective of this study is to develop a machine learning (ML)-based system for predicting diabetic patients.

Materials and methods

Logistic regression (LR) is used to identify the risk factors for diabetes disease based on p value and odds ratio (OR). We have adopted four classifiers like naïve Bayes (NB), decision tree (DT), Adaboost (AB), and random forest (RF) to predict the diabetic patients. Three types of partition protocols (K2, K5, and K10) have also adopted and repeated these protocols into 20 trails. Performances of these classifiers are evaluated using accuracy (ACC) and area under the curve (AUC).

Results

We have used diabetes dataset, conducted in 2009-2012, derived from the National Health and Nutrition Examination Survey. The dataset consists of 6561 respondents with 657 diabetic and 5904 controls. LR model demonstrates that 7 factors out of 14 as age, education, BMI, systolic BP, diastolic BP, direct cholesterol, and total cholesterol are the risk factors for diabetes. The overall ACC of ML-based system is 90.62%. The combination of LR-based feature selection and RF-based classifier gives 94.25% ACC and 0.95 AUC for K10 protocol.

Conclusion

The combination of LR and RF-based classifier performs better. This combination will be very helpful for predicting diabetic patients.

Identification of Potential Type II Diabetes in a Large-Scale Chinese Population Using a Systematic Machine Learning Framework

BACKGROUND

An estimated 425 million people globally have diabetes, accounting for 12% of the world's health expenditures, and the number continues to grow, placing a huge burden on the healthcare system, especially in those remote, underserved areas.

METHODS

A total of 584,168 adult subjects who have participated in the national physical examination were enrolled in this study. The risk factors for type II diabetes mellitus (T2DM) were identified by p values and odds ratio, using logistic regression (LR) based on variables of physical measurement and a questionnaire. Combined with the risk factors selected by LR, we used a decision tree, a random forest, AdaBoost with a decision tree (AdaBoost), and an extreme gradient boosting decision tree (XGBoost) to identify individuals with T2DM, compared the performance of the four machine learning classifiers, and used the best-performing classifier to output the degree of variables' importance scores of T2DM.

RESULTS

The results indicated that XGBoost had the best performance (accuracy = 0.906, precision = 0.910, recall = 0.902, F-1 = 0.906, and AUC = 0.968). The degree of variables' importance scores in XGBoost showed that BMI was the most significant feature, followed by age, waist circumference, systolic pressure, ethnicity, smoking amount, fatty liver, hypertension, physical activity, drinking status, dietary ratio (meat to vegetables), drink amount, smoking status, and diet habit (oil loving).

CONCLUSIONS

We proposed a classifier based on LR-XGBoost which used fourteen variables of patients which are easily obtained and noninvasive as predictor variables to identify potential incidents of T2DM. The classifier can accurately screen the risk of diabetes in the early phrase, and the degree of variables' importance scores gives a clue to prevent diabetes occurrence.