scholarly journals Predictive analytics framework for accurate estimation of child mortality rates for Internet of Things enabled smart healthcare systems

2020 ◽  
Vol 16 (5) ◽  
pp. 155014772092889 ◽  
Author(s):  
Muhammad Islam ◽  
Muhammad Usman ◽  
Azhar Mahmood ◽  
Aaqif Afzaal Abbasi ◽  
Oh-Young Song
Keyword(s):  
Mortality Rate ◽  
Child Mortality ◽  
Death Rate ◽  
Predictive Analytics ◽  
Healthcare Systems ◽  
Data Sets ◽  
Demographic Health Survey ◽  
Live Births ◽  
Under Five ◽  
Smart Healthcare

Globally, under-five child mortality is a substantial health problem. In developing countries, reducing child mortality and improving child health are the key priorities in health sectors. Despite the significant reduction in deaths of under-five children globally, developing countries are still struggling to maintain an acceptable mortality rate. Globally, the death rate of under-five children is 41 per 1000 live births. However, the death rate of children in developing nations like Pakistan and Ethiopia per 1000 live births is 74 and 54, respectively. Such nations find it very challenging to decrease the mortality rate. Data analytics on healthcare data plays a pivotal role in identifying the trends and highlighting the key factors behind the children deaths. Similarly, predictive analytics with the help of Internet of Things based frameworks significantly advances the smart healthcare systems to forecast death trends for timely intervention. Moreover, it helps in capturing hidden associations between health-related variables and key death factors among children. In this study, a predictive analytics framework has been developed to predict the death rates with high accuracy and to find the significant determinants that cause high child mortality. Our framework uses an automated method of information gain to rank the information-rich mortality variables for accurate predictions. Ethiopian Demographic Health Survey and Pakistan Demographic Health Survey data sets have been used for the validation of our proposed framework. These real-world data sets have been tested using machine learning classifiers, such as Naïve Bayes, decision tree, rule induction, random forest, and multi-layer perceptron, for the prediction task. It has been revealed through our experimentation that Naïve Bayes classifier predicts the child mortality rate with the highest average accuracy of 96.4% and decision tree helps in identifying key classification rules covering the factors behind children deaths.

scholarly journals Akses Remaja dengan Komplikasi Kehamilan terhadap Pelayanan Persalinan dan Kelangsungan Hidup Anak di Indonesia

2020 ◽  
Vol 29 (4) ◽  
Author(s):  
Tin Afifah ◽  
Novianti Novianti ◽  
Suparmi Suparmi ◽  
Kemal Nazaruddin Siregar ◽  
Nurillah Amaliah ◽  
...  
Keyword(s):  
Infant Mortality ◽  
Adolescent Pregnancy ◽  
Neonatal Mortality ◽  
Pregnancy Complications ◽  
Death Rate ◽  
Health Facilities ◽  
Childhood Mortality ◽  
Pregnant Adolescents ◽  
Live Births ◽  
Under Five

Abstract Age-Specific Death Rate (ASDR) cases of maternal death are highest in the adolescent group (<20 years). Adolescent pregnancy is a risky pregnancy, so it is necessary to deliver at health facilities.   A complication of pregnancy in adolescents is also at risk of childhood mortality. The study aims to assess the access of pregnant adolescents with complications to delivery facilities and the relation with the survival of the child. This study is a secondary data analysis of the 2017 Indonesia Demographic and Health Survey (IDHS). The unit of analysis of live births five years preceding survey, and mother's age birth before 35 years (14,634 live births). There are 2 dependent variables: access to delivery services (skill birth attendant and health facilities); and survival of the child (neonatal, infant and under-five mortality). Interest variables is multiple high-risk category, a combination of morbidity status (complications during pregnancy) and age adolescents (<20 years) compared adults (20-34 years). Covariate variables are parity and characteristics (mother’s education, residence and wealth index). Statistical test with logistic regression, 95%CI. All pregnancies with complications were significant association with neonatal and infant mortality. Specifically adolescent pregnancy with complications is also significantly associated with under-five mortality. In adolescents with pregnancy complications had OR neonatal mortality=7.4, OR infant mortality=4.56 and OR infant mortality=3.73, compared with adults pregnant without complication. Pregnancies ages 20-34 with complications having neonatal OR=1.95 and OR infant mortality=1.64. Pregnant adolescents are significantly associated with facilities of delivery (OR<1). The conclusions are: the access of adolescents with pregnancy complications to childbirth at the health facility is still low; adolescent pregnancy with complications is significantly related to childhood mortality and the highest risk of neonatal mortality. ABSTRAK  Age Spesific Death Rate (ASDR) kasus kematian maternal tertinggi pada kelompok remaja (<20 tahun). Kehamilan pada usia remaja merupakan kehamilan berrisiko, sehingga mereka perlu akses ke fasilitas persalinan yang aman. Kehamilan dengan komplikasi pada remaja juga berisiko terhadap kematian anaknya. Tujuan studi untuk menilai akses remaja yang hamil dengan komplikasi terhadap pelayanan persalinan dan mengetahui status kelangsungan hidup anaknya. Studi ini merupakan analisis data sekunder Survei Demografi dan Kesehatan Indonesia (SDKI) 2017. Unit analisis adalah kelahiran hidup periode lima tahun sebelum survey dan saat dilahirkan usia ibu belum mencapai 35 tahun (14.634 kelahiran hidup). Variabel dependen yang diteliti ada 2: akses ke pelayanan persalinan (tenaga kesehatan dan fasilitas pelayanan kesehatan); dan kelangsungan hidup anak (kematian: neonatal, bayi, dan balita). Variabel interes adalah status ganda yaitu kombinasi status komplikasi kehamilan dan umur risiko remaja dibandingkan umur tidak berisiko (20-34 tahun). Variabel kovariat: paritas dan karakteristik (pendidikan, tempat tinggal dan indeks kekayaan). Uji statistik dengan regresi logistik, 95%CI. Semua kehamilan dengan komplikasi berhubungan signifikan dengan kematian neonatal dan bayi bila dibandingkan dengan kehamilan usia 20-34 tanpa komplikasi. Khusus kehamilan remaja dengan komplikasi juga berhubungan signifikan dengan kematian balita. Pada remaja dengan komplikasi kehamilan mempunyai OR kematian neonatal=7,4, OR kematian bayi=4,56 dan OR kematian balita=3,73. Kehamilan usia 20-34 dengan komplikasi mempunyai OR neonatal=1,95 dan OR kematian bayi=1,64. Remaja hamil berhubungan signifikan dengan persalinan di fasyankes (OR<1). Kesimpulan studi ini adalah akses remaja dengan kehamilan komplikasi terhadap persalinan di fasyankes masih rendah. Kehamilan remaja dengan komplikasi berhubungan signifikan dengan kematian anak, dan risiko paling tinggi terhadap kematian neonatus.   

scholarly journals Logistic Regression Additive Model: Application to Tanzania Demographic and Health Survey Data

2017 ◽  
Vol 10 (1) ◽  
pp. 294-302 ◽  
Author(s):  
W.J. Dlamini ◽  
S.F. Melesse ◽  
H.G. Mwambi
Keyword(s):  
Mortality Rate ◽  
Survey Data ◽  
Child Mortality ◽  
Additive Model ◽  
Well Being ◽  
Additive Models ◽  
Cluster Sampling ◽  
African Region ◽  
Under Five ◽  
Number Of Children

Background:The well-being of a child reflects household, community and national involvement on family health. Currently, the global under-five child mortality rate is falling faster compared to any time in the past two decades. However, the progress remained insufficient to match the Millennium Development Goal 4 targets especially in the Sub-Saharan African region.Objective:This study aims to visualize and identify factors associated with under-five child mortality in Tanzania, which is essential for formulating appropriate health program and policies.Methods:The survey data used for this paper was taken from 2011-2012 Tanzania HIV/AIDS and Malaria Indictor Survey. The study utilizes statistical model that accommodate a response, which is dichotomous and account for non-linear relationship between binary response and independent variable. Generalized additive models was adopted for the analysis. The sample was selected using stratified, two-stage cluster sampling that gave a sample size of 10494 mothers. The model was fitted using proc gam in statistical analysis software version 9.3.Results:The results showed that human immunodeficiency virus status of the mother and breastfeeding were associated with under-five child mortality. Furthermore, the results also indicated that under-five child mortality had a quadratic pattern relationship with the number of children ever born, the number of children alive, the number of children five or under in a household and child birth order number.Conclusion:Based on the study, our findings confirmed that under-five mortality is a serious problem in the Tanzania. Therefore, there is a need to intensify child health interventions to reduce the under-five mortality rate even further with the development of policies and programs to reduce under-five child mortality.

scholarly journals Spending on Health is a Complex Phenomenon in our Country

2018 ◽  
Vol 24 (S) ◽  
pp. 829-830
Author(s):  
Sumair Anwar
Keyword(s):  
Mortality Rate ◽  
Neonatal Period ◽  
Health Indicators ◽  
Complex Phenomenon ◽  
Live Births ◽  
Under Five ◽  
Under Five Children ◽  
The Past

According to WHO statistics 2017, amongst health indicators of countries worldwide, Pakistan’s under five children mortality rate has been recorded up to 81.1 per 1000 live births, which is second highest in the list of SAARC countries.1 In Pakistan, over 57% of deaths under 5 years occur during the neonatal period (42 per 1000 live births) and have not changed over the past 6 years.2

Does population health influence FDI inflows into Ghana?

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mustapha Immurana
Keyword(s):  
Mortality Rate ◽  
Infant Mortality ◽  
Population Health ◽  
Death Rate ◽  
Health Indicators ◽  
Least Square ◽  
Infant Mortality Rate ◽  
Fdi Inflows ◽  
Content Type ◽  
Under Five

PurposeGhana is one of the countries instituting several measures toward attracting more Foreign Direct Investment (FDI) inflows. This is because, FDI is largely viewed as essential to socioeconomic development. However, while population health can influence FDI inflows, it has received very little attention. This study, therefore, investigates empirically, as to focusing on population health could be a useful tool in Ghana’s attempt to attract more FDI inflows.Design/methodology/approachThe study uses time series data on Ghana from 1980 to 2018 to achieve its objective. Life expectancy, death rate, infant mortality rate, under-five mortality rate and incidence of malaria are used as proxies for population health, while the Ordinary Least Square (OLS) and the Instrumental Variable Two-Stage Least Square (IV2SLS) regressions are employed as empirical estimation techniques.FindingsUsing the OLS regression, except the incidence of malaria, the study finds all the other population health indicators to significantly influence FDI inflows. However, after controlling for endogeneity using the IV2SLS regression, all population health indicators are found to be significant as regards their effects on FDI inflows.Practical implicationsPaying attention to population health could be an effective strategy that can be employed by policymakers in the quest to get more FDI inflows into Ghana.Originality/valueThis study, to the best of our knowledge, is the first study solely devoted to Ghana, which doing so helps in devising country-specific policies with regard to the effect of population health on FDI inflows. Further, this study becomes the first to use death rate, infant mortality rate and under-five mortality rate in examining the effect of population health on FDI inflows. Thus, since there are various causes of deaths, using indicators that capture deaths from all factors helps in giving a much broader picture with regard to the FDI population health nexus. Also, this study is the first to use up to five different population health indicators in examining the effect of population health on FDI inflows, which aids in revealing whether FDI is sensitive to the population health indicator used.

scholarly journals Neonatal mortality and child health in a remote rural area in Nepal: a mixed methods study

2019 ◽  
Vol 3 (1) ◽  
pp. e000519
Author(s):  
Bindu Kumari Karki ◽  
Guenter Kittel
Keyword(s):  
Mixed Methods ◽  
Mortality Rate ◽  
Health Services ◽  
Neonatal Mortality ◽  
Rural Area ◽  
Acute Lower Respiratory Infection ◽  
Cultural Perceptions ◽  
Live Births ◽  
Under Five ◽  
Remote Rural Area

ObjectiveTo assess neonatal and under-five mortality and the health situation for children in Dolpa, a remote rural area of Nepal.Study designMixed methods: quantitative (retrospective cross sectional) and qualitative (semistructured interviews).RationaleProgress in reducing child and newborn mortality in Nepal has reached the remote areas to a limited extent. Furthermore, there may be substantial under-reporting and data may be unreliable.Setting and participantsThe population of Dolpa district is approximately 35 000. We visited 10 randomly selected villages (plus one settlement) with approximately 12 000 inhabitants.MethodologyRecords of the number of deliveries, neonatal and under-five deaths were collected. 100 children (10 different villages) were evaluated for common diseases present during the month prior to the investigation. 20 interviews were conducted about the cultural perceptions of neonatal death and morbidity; in each village at least one interview was undertaken.ResultsThe population of the 10 villages (plus one settlement) under investigation was 12 287. 300 deliveries have taken place during the last 12 months before the study. There were 30 children reported to have died; out of those 20 were in the neonatal period. This reflects an estimated neonatal mortality rate in Dolpa district of 67/1000 live births (95% CI 41-101/1000) and an estimated under-five mortality rate of 100/1000 (95% CI 70-140/1000). In the previous month, out of 100 children surveyed there had been 11 cases of acute lower respiratory infection (ALRI), 7 cases of diarrhoea, 3 cases of isolated malnutrition and 5 cases of malnutrition combined with ALRI or diarrhoea.Based on qualitative interviews traditional beliefs still play a major role, and are partly a hindrance to progress in health. There is also mistrust in the health services and misconceptions about ‘modern’ medicine and treatment facilities.ConclusionDespite progress in child morbidity and mortality in Nepal, some areas remain underserved by health services and neonatal mortality is far above the Nepalese average, which is 29/1000 live births. There is a substantial need to increase and train health staff. Health promotion should be encouraged but cultural perceptions have to be understood if positive behavioural change is to be achieved.

scholarly journals Child malnutrition and mortality in Swaziland: Situation analaysis of the immediate, underlying and basic causes

2012 ◽  
Vol 12 (50) ◽  
pp. 5994-6006
Author(s):  
SKS Masuku-Maseko ◽  
◽  
EE Owaga ◽  
Keyword(s):  
Health Care ◽  
Mortality Rate ◽  
Urban Areas ◽  
Child Nutrition ◽  
Child Malnutrition ◽  
Live Births ◽  
Under Five ◽  
Childhood Malnutrition ◽  
Under Five Children ◽  
Depth Analysis

Malnutrition is a major confounding factor for child morbidity and mortality in developing countries. In Swaziland, about 31% of the under-five children are stunted in growth, where-as 1% and 6% are wasted and underweight, respectively. Hhohho region has the highest prevalence of underweight children (8.2%) relative to other regions such as Shiselweni (7.3%), Lubombo (6.7%) and Manzini (6.4%). The prevalence of infant and under-five children mortality rate (per 1,000 live births) are 85 and 102 deaths, respectively. Lubombo region has the highest cases of under-five mortality rate (deaths per 1,000 live births) of 115 when compared to rates in other regions, namely; Manzini (112), Shiselweni (100) and Hhohho (96). Despite the several child healthcare programmes, the problem of high child malnutrition places a significant hindrance towards the attainment of the Millennium Development Goals (MDG) 4 on reduction of child mortality. Potential determinants of childhood malnutrition and mortality in Swaziland can be categorized into three levels, namely: (a) immediate causes (inadequate dietary intake of protein, energy and micronutrients; diseases such as pneumonia, diarrhoeal diseases and HIV/AIDS, (b) underlying causes (inadequate access to food due to poverty and decline in food production; inadequate care of children and women, insufficient health services and unhealthy environment), and (c) basic causes (inadequate mother’s education and nutrition knowledge, insufficient human resources in child health care; inadequate policies on child nutrition and health care; inequitable distribution of household and national socioeconomic resources). This paper presents an in-depth analysis of the causal factors of childhood malnutrition and mortality in Swaziland, and further explores opportunities that could be adopted to address the malnutrition and mortality problem. It also aims to reinforce that in order to ensure effectiveness and sustainability of intervention programmes, there is need for multi-dimensional strategies and collaboration between all the stakeholders concerned with child nutrition, health and socio-economic development. However, the interventions must recognize the existing socio-economic differentials between the rural and urban areas, and the administrative regions.

scholarly journals Associations between cesarean delivery and child mortality: A national record linkage longitudinal study of 17.8 million births in Brazil

PLoS Medicine ◽  
2021 ◽  
Vol 18 (10) ◽  
pp. e1003791
Author(s):  
Enny S. Paixao ◽  
Christian Bottomley ◽  
Julia M. Pescarini ◽  
Kerry L. M. Wong ◽  
Luciana L. Cardim ◽  
...  
Keyword(s):  
Mortality Rate ◽  
Cesarean Delivery ◽  
Child Mortality ◽  
Neonatal Period ◽  
Relative Rate ◽  
Child Survival ◽  
Routine Data ◽  
Live Births ◽  
Medical Indication ◽  
Vaginal Deliveries

Background There is an increasing use of cesarean delivery (CD) based on preference rather than on medical indication. However, the extent to which nonmedically indicated CD benefits or harms child survival remains unclear. Our hypothesis was that in groups with a low indication for CD, this procedure would be associated with higher child mortality and in groups with a clear medical indication CD would be associated with improved child survival chances. Methods and findings We conducted a population-based cohort study in Brazil by linking routine data on live births between January 1, 2012 and December 31, 2018 and assessing mortality up to 5 years of age. Women with a live birth who contributed records during this period were classified into one of 10 Robson groups based on their pregnancy and delivery characteristics. We used propensity scores to match CD with vaginal deliveries (1:1) and prelabor CD with unscheduled CD (1:1) and estimated associations with child mortality using Cox regressions. A total of 17,838,115 live births were analyzed. After propensity score matching (PSM), we found that live births to women in groups with low expected frequencies of CD (Robson groups 1 to 4) had a higher death rate up to age 5 years if they were born via CD compared with vaginal deliveries (HR = 1.25, 95% CI: 1.22 to 1.28; p < 0.001). The relative rate was greatest in the neonatal period (HR = 1.39, 95% CI: 1.34 to 1.45; p < 0.001). There was no difference in mortality rate when comparing offspring born by a prelabor CD to those born by unscheduled CD. For the live births to women with a CD in a prior pregnancy (Robson group 5), the relative rates for child mortality were similar for those born by CD compared with vaginal deliveries (HR = 1.05, 95% CI: 1.00 to 1.10; p = 0.024). In contrast, for live births to women in groups with high expected rates of CD (Robson groups 6 to 10), the child mortality rate was lower for CD than for vaginal deliveries (HR = 0.90, 95% CI: 0.89 to 0.91; p < 0.001), particularly in the neonatal period (HR = 0.84, 95% CI: 0.83 to 0.85; p < 0.001). Our results should be interpreted with caution in clinical practice, since relevant clinical data on CD indication were not available. Conclusions In this study, we observed that in Robson groups with low expected frequencies of CD, this procedure was associated with a 25% increase in child mortality. However, in groups with high expected frequencies of CD, the findings suggest that clinically indicated CD is associated with a reduction in child mortality.

scholarly journals Household factors and under-five mortality in Bankass, Mali: results from a cross-sectional survey

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
David C. Boettiger ◽  
Emily Treleaven ◽  
Kassoum Kayentao ◽  
Mahamadou Guindo ◽  
Mama Coumaré ◽  
...  
Keyword(s):  
Mortality Rate ◽  
Reading Ability ◽  
Cox Regression ◽  
Household Wealth ◽  
Reproductive Age ◽  
Male Mortality ◽  
Live Births ◽  
Under Five ◽  
Factors Associated ◽  
Household Factors

Abstract Background Rural parts of Mali carry a disproportionate burden of the country’s high under-five mortality rate. A range of household factors are associated with poor under-five health in resource-limited settings. However, it is unknown which most influence the under-five mortality rate in rural Mali. We aimed to describe household factors associated with under-five mortality in Bankass, a remote region in central Mali. Methods We analysed baseline household survey data from a trial being conducted in Bankass. The survey was administered to households between December 2016 and January 2017. Under-five deaths in the five years prior to baseline were documented along with detailed information on household factors and women’s birth histories. Factors associated with under-five mortality were analysed using Cox regression. Results Our study population comprised of 17,408 under-five children from 8322 households. In the five years prior to baseline, the under-five mortality rate was 152.6 per 1000 live births (158.8 and 146.0 per 1000 live births for males and females, respectively). Living a greater distance from a primary health center was associated with a higher probability of under-five mortality for both males (adjusted hazard ratio [aHR] 1.53 for ≥10 km versus < 2 km, 95% confidence interval [CI] 1.25–1.88) and females (aHR 1.59 for ≥10 km versus < 2 km, 95% CI 1.27–1.99). Under-five male mortality was additionally associated with lower household wealth quintile (aHR 1.47 for poorest versus wealthiest, 95%CI 1.21–1.78), lower reading ability among women of reproductive age in the household (aHR 1.73 for cannot read versus can read, 95%CI 1.04–2.86), and living in a household with access to electricity (aHR 1.16 for access versus no access, 95%CI 1.00–1.34). Conclusions U5 mortality is very high in Bankass and is associated with living a greater distance from healthcare and several other household factors that may be amenable to intervention or facilitate program targeting.

scholarly journals Under-five Mortality and Associated Factors among Children Born from 15-49 Years Old Mothers in Haramaya Town, Eastern Ethiopia

2021 ◽  
Author(s):  
Mohammed Ahmed ◽  
Melake Demena ◽  
Zelalem Teklemariam ◽  
Assefa Desalew ◽  
Nega Assefa
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Mortality Rate ◽  
Logistic Regression Analysis ◽  
Associated Factors ◽  
Household Size ◽  
P Value ◽  
Live Births ◽  
Under Five ◽  
Colostrum Feeding

Abstract Background: The global under-five mortality rate has dropped from almost 90 deaths per 1,000 live births in 1990 to 43 in 2015. The Ethiopian Mini Demographic Health Survey, 2019 shows 55 under-five deaths per 1,000 live births. In the eastern part of Ethiopia, evidence from the Kersa Health and Demographic Surveillance System in Kersa district of East Hararghe Zone, Oromia Region suggested the decline of under-five mortality rate from 131.8 per 1000 live births in 2008 to 77.4 per 1000 live births in 2013. The death rates still remain far from the Sustainable Development Goals’ target reduction to 25 or less per 1000 live births by 2030. However, the magnitude and determinants of under-five mortality is not studied in Haramaya town. Objective: To assess the under-five mortality rate and associated factors among children born during August 07, 2015- August 06, 2020 in Haramaya town, east Ethiopia by August 07–31/2020. Methodology: Quantitative cross-sectional population-based study was conducted on 391 pairs of 15-49 years old mothers and their live-born under-five children selected using systematic random sampling technique from Haramaya town to cmpare mortality between <=24 and >=25 mother’s age groups. Data were collected using interview-based questionnaire; double entered into EpiData 3.1; and then exported to statistical package for social sciences program version 20.0 for analysis. Binary logistic regression analysis (p-value <0.20) was performed to examine crude association of predictors with under-five mortality, and then multiple logistic regression analysis (p-value <0.05) to measure the statistical association. Results: The death of 28 out of 372 live births gave an under-five mortality rate of 75 per 1000 live births. Children born in households with less than 6 members had 7. 98 times higher odds of dying than those born in households with at least 6 members (AOR =7.98, 95% CI =1.59-40.17). Those children who did not feed colostrum were associated with 17.45 times increased risk of under-five deaths compared to colostrum-fed ones (AOR =17.45, 95% CI =6.54-46.55). Conclusion: The study suggests that 75 per 1000 live births die before celebrating their fifth birth day. Household size and colostrum feeding are the significantly associated factors.Recommendation: All concerned should inform the mothers the role of identified factors like household size and colostrum feeding in child survival.

Sign in / Sign up

Export Citation Format

Share Document