Predictive Linear Regression Model for Premature Birth Risk Assessment System

We propose two new nonparametric predictive models: the multi-step nonparametric predictive regression model and the multi-step additive predictive regression model, in which the predictive variables are locally stationary time series. We define estimation methods and establish the large sample properties of these methods in the short horizon and the long horizon case. We apply our methods to stock return prediction using a number of standard predictors such as dividend yield. The empirical results show that all of these models can substantially outperform the traditional linear predictive regression model in terms of both in-sample and out-of-sample performance. In addition, we _nd that these models can always beat the historical mean model in terms of in-sample fitting, and also for some cases in terms of the out-of-sample forecasting. We also compare our methods with the linear regression and historical mean methods according to an economic metric. In particular, we show how our methods can be used to deliver a trading strategy that beats the buy and hold strategy (and linear regression based alternatives) over our sample period.

BackgroundNeonatal mortality accounts for almost 40 per cent of under-five child mortality, globally. An understanding of the factors related to neonatal mortality is important to guide the development of focused and evidence-based health interventions to prevent neonatal deaths. This study aimed to identify the determinants of neonatal mortality in Indonesia, for a nationally representative sample of births from 1997 to 2002.MethodsThe data source for the analysis was the 2002–2003 Indonesia Demographic and Health Survey from which survival information of 15,952 singleton live-born infants born between 1997 and 2002 was examined. Multilevel logistic regression using a hierarchical approach was performed to analyze the factors associated with neonatal deaths, using community, socio-economic status and proximate determinants.ResultsAt the community level, the odds of neonatal death was significantly higher for infants from East Java (OR = 5.01, p = 0.00), and for North, Central and Southeast Sulawesi and Gorontalo combined (OR = 3.17, p = 0.03) compared to the lowest neonatal mortality regions of Bali, South Sulawesi and Jambi provinces. A progressive reduction in the odds was found as the percentage of deliveries assisted by trained delivery attendants in the cluster increased. The odds of neonatal death were higher for infants born to both mother and father who were employed (OR = 1.84, p = 0.00) and for infants born to father who were unemployed (OR = 2.99, p = 0.02). The odds were also higher for higher rank infants with a short birth interval (OR = 2.82, p = 0.00), male infants (OR = 1.49, p = 0.01), smaller than average-sized infants (OR = 2.80, p = 0.00), and infant's whose mother had a history of delivery complications (OR = 1.81, p = 0.00). Infants receiving any postnatal care were significantly protected from neonatal death (OR = 0.63, p = 0.03).ConclusionPublic health interventions directed at reducing neonatal death should address community, household and individual level factors which significantly influence neonatal mortality in Indonesia. Low birth weight and short birth interval infants as well as perinatal health services factors, such as the availability of skilled birth attendance and postnatal care utilization should be taken into account when planning the interventions to reduce neonatal mortality in Indonesia.

PurposeAssessing the risks and preventable causes of maternal and neonatal mortality requires the availability of good-quality antenatal information. In Indonesia, however, access to reliable information on pregnancy-related results remains challenging. This research has proposed a research-based policy recommendation to improve availability and accessibility to vital information on antenatal examinations.Patients and MethodsDescriptive statistics were used to characterize midwives’ capabilities in routinely gathering and recording antenatal information during pregnancy. The investigation was carried out among 19 midwives in South Kalimantan, Indonesia, from April 2016 to October 2017. Antenatal data on 4946 women (retrospective study) and 381 women (prospective study) have been accessed through a scientific and technical training program.ResultsTo date, lack of timely access to antenatal information has hampered the process of reducing neonatal mortality in Indonesia. The post-training statistical analysis showed that the training has significantly improved midwives’ scientific knowledge and technical abilities in providing more reliable data on antenatal measurements.ConclusionConsistent scientific and technical training among midwives is required to update their knowledge and skills, particularly those relating to documenting the results of antenatal examinations at different stages of pregnancy and using that information to assess potential risks and identify necessary interventions. This should also be followed by routine monitoring on the quality of collected antenatal data. This can be one of the enabling actions to achieve the 2030 Sustainable Development Goals target in reducing neonatal mortality in Indonesia.

BackgroundLow birth weight (LBW) is a leading cause of neonatal morbidity and mortality, and increases various disease risks across life stages. Prediction models of LBW have been developed before, but have limitations including small sample sizes, absence of genetic factors and no stratification of neonate into preterm and term birth groups. In this study, we challenged the development of early prediction models of LBW based on environmental and genetic factors in preterm and term birth groups, and clarified influential variables for LBW prediction.MethodsWe selected 22,711 neonates, their 21,581 mothers and 8,593 fathers from the Tohoku Medical Megabank Project Birth and Three-Generation cohort study. To establish early prediction models of LBW for preterm birth and term birth groups, we trained AI-based models using genetic and environmental factors of lifestyles. We then clarified influential environmental and genetic factors for predicting LBW in the term and preterm groups.ResultsWe identified 2,327 (10.22%) LBW neonates consisting of 1,077 preterm births and 1,248 term births. Our early prediction models archived the area under curve 0.96 and 0.95 for term LBW and preterm LBW models, respectively. We revealed that environmental factors regarding eating habits and genetic features related to fetal growth were influential for predicting LBW in the term LBW model. On the other hand, we identified that genomic features related to toll-like receptor regulations and infection reactions are influential genetic factors for prediction in the preterm LBW model.ConclusionsWe developed precise early prediction models of LBW based on lifestyle factors in the term birth group and genetic factors in the preterm birth group. Because of its accuracy and generalisability, our prediction model could contribute to risk assessment of LBW in the early stage of pregnancy and control LBW risk in the term birth group. Our prediction model could also contribute to precise prediction of LBW based on genetic factors in the preterm birth group. We then identified parental genetic and maternal environmental factors during pregnancy influencing LBW prediction, which are major targets for understanding the LBW to address serious burdens on newborns' health throughout life.

In this paper, we propose three new predictive models: the multi-step nonparametric predictive regression model and the multi-step additive predictive regression model, in which the predictive variables are locally stationary time series; and the multi-step time-varying coefficient predictive regression model, in which the predictive variables are stochastically nonstationary. We also establish the estimation theory and asymptotic properties for these models in the short horizon and long horizon case. To evaluate the effectiveness of these models, we investigate their capability of stock return prediction. The empirical results show that all of these models can substantially outperform the traditional linear predictive regression model in terms of both in-sample and out-of-sample performance. In addition, we find that these models can always beat the historical mean model in terms of in-sample fitting, and also for some cases in terms of the out-of-sample forecasting.

Most genomic prediction models are linear regression models that assume continuous and normally distributed phenotypes, but responses to diseases such as stripe rust (caused by Puccinia striiformis f. sp. tritici) are commonly recorded in ordinal scales and percentages. Disease severity (SEV) and infection type (IT) data in germplasm screening nurseries generally do not follow these assumptions. On this regard, researchers may ignore the lack of normality, transform the phenotypes, use generalized linear models, or use supervised learning algorithms and classification models with no restriction on the distribution of response variables, which are less sensitive when modeling ordinal scores. The goal of this research was to compare classification and regression genomic selection models for skewed phenotypes using stripe rust SEV and IT in winter wheat. We extensively compared both regression and classification prediction models using two training populations composed of breeding lines phenotyped in 4 years (2016–2018 and 2020) and a diversity panel phenotyped in 4 years (2013–2016). The prediction models used 19,861 genotyping-by-sequencing single-nucleotide polymorphism markers. Overall, square root transformed phenotypes using ridge regression best linear unbiased prediction and support vector machine regression models displayed the highest combination of accuracy and relative efficiency across the regression and classification models. Furthermore, a classification system based on support vector machine and ordinal Bayesian models with a 2-Class scale for SEV reached the highest class accuracy of 0.99. This study showed that breeders can use linear and non-parametric regression models within their own breeding lines over combined years to accurately predict skewed phenotypes.

Do Indonesian midwifery-led birth units provide safe, accessible care? A secondary analysis of demographic health survey cross-sectional data.

<p><em>Almost 100% neonatal death was occured in Developing countries including Indonesia. Indonesia managed to reduce child mortality start from 1991 to 2012. Neonatal mortalityrate in Indonesiais still highon 19/1000 live births based on the IDHS 2007 and 2012. The objective of this research is to investigate the determinant of neonatal mortality in Indonesia. The study was a quantitative research, using the data Indonesia Demographic and Health Survey in 2012 were analyzed using retrospective cohort analysis strategy. Children born alive period 2007-2012 amounted to 12,750 inhabitants, into the sample. Analysis of data using univariable analysis in the form of a frequency distribution, such as the log-rank bivariate. The results of the data analysis are presented in tables or pictures, followed by discussion.Kaplan-Meier curves showed that neonatal mortality in Indonesia mainly occurred on the first day of life and on the early neonatal period. The results of bivariate analysis with log-rank test showed significant relationship betweenneonatal deaths in Indonesia and breastfeeding (p value: 0.000), the size of a baby's birth (p value: 0.000), frequency of ANC visits (p value: 0.001) and maternal age (p value: 0.007). The result showing that more than one factorsin Indonesia have an increased risk of neonatal mortality.</em></p>

To examine the relationship between frequency of antenatal care visits, as a whole and in each trimester, and neonatal mortality in Indonesia. 13 055 single births from the fifth Indonesia Demographic Health Survey in 2006-07. Estimate adjusted odds ratios (ORs) and their 95% confidence intervals (95% CIs). Pregnant women who had more antenatal care visits experienced a lower risk of neonatal mortality and more benefit in the last trimester: the ORs against the 0-1 visit group, were 0.76 (95% CI 0.45-1.29) for 2 visits group, 0.54 (95% CI 0.33-0.87) for 3 visits group and 0.31 (95% CI 0.17-0.57) for 4 visits group, respectively. Individual ORs as a whole period were not significant, but ORs declined markedly at 7 visits or more. The results may provide a valuable recommendation for the care of pregnant women in Indonesia.

Background: Neonatal mortality is a reflection of a country's health status and until now, health development is still an important government program. The purpose of this study was to determine the relationship between Low Birth Weight (LBW) and neonatal mortality in Indonesia after confounding factors (education, household wealth index, age, smoking, parity, birth spacing, antenatal visits and history of abortion) were controlled and to determine the size of Population Attributable Risk of LBW to neonatal mortality in Indonesia. Indonesia 2017. Methods: The design of this research was cross-sectional with multivariate logistic regression analysis using secondary data from the 2017 IDHS. The sample in this study were women who had been married and gave birth to live babies from 2012-2017 as many as 16.343 samples. Results: The study showed that there is a relationship between LBW and neonatal mortality (OR=6.79, 95% CI=4.98-9.26, p value=0.000). Then the dominant factor that is most related to neonatal mortality is LBW with a p value of 0.000 and parity with a p value of 0.005. Conclusion: In order to reduce neonatal mortality, it is hoped that the government and the society can play an active role in reducing and controlling LBW by increasing antenatal care. As well as encouraging pregnant women to check their pregnancies and deliveries by skilled health workers.

In healthcare research, predictive modeling is commonly utilized to forecast risk variables and enhance treatment procedures for improved patient outcomes. Enormous quantities of data are being created as a result of recent advances in research, clinical trials, next-generation genomic sequencing, biomarkers, and transcriptional and translational studies. Understanding how to handle and comprehend scientific data to offer better treatment for patients is critical. Currently, multiple prediction models are being utilized to investigate patient outcomes. However, it is critical to recognize the limitations of these models in the research design and their unique benefits and drawbacks. In this overview, we will look at linear regression, logistic regression, decision trees, and artificial neural network prediction models, as well as their advantages and disadvantages. The two most perilous requirements for building any predictive healthcare model are feature selection and model validation. Typically, feature selection is done by a review of the literature and expert opinion on that subject. Model validation is also an essential component of every prediction model. It characteristically relates to the predictive model's performance and accuracy. It is strongly recommended that all clinical parameters should be thoroughly examined before using any prediction model.

Enhanced identification of women at risk for preterm birth via quantitative ultrasound: a prospective cohort study

Treatment of localized periodontal disease in pregnancy does not reduce the occurrence of preterm birth: results from the Periodontal Infections and Prematurity Study (PIPS)

Challenges in defining and classifying the preterm birth syndrome

Latar Belakang: Angka kematian neonatal di Indonesia mengalami stagnansi sejak sepuluh tahun terakhir. Dalam rangka mengakselerasi penurunan angka kematian neonatal di Indonesia, intervensi spesifik diperlukan pada faktor utama penyebab kematian. Penelitian ini bertujuan untuk mengetahui kontribusi berat badan lahir rendah terhadap kematian neonatal di Indonesia. Metode: Data Survei Demografi dan Kesehatan Indonesia tahun 2012 digunakan untuk analisis. Sejumlah 18021 kelahiran hidup dalam periode lima tahun terakhir telah dilaporkan oleh responden. T erdapat 14837 anak memiliki informasi lengkap untuk analisis. Adjusted relative risk dengan analisis survival digunakan untuk mengukur hubungan antara variable dengan kematian neonatal. Hasil: Anak yang lahir dengan berat badan rendah memiliki risiko 9.89 kali lebih tinggi untuk kematian neonatal bila dibandingkan dengan anak yang lahir dengan berat badan normal [adjusted relative risk (aRR) = 9.89; 95% confidence interval (CI): 7.41 – 13.19); P = < 0.0001]. Anak yang lahir dari ibu berumur muda (15 - 19 tahun) memiliki risiko 94% lebih tinggi bila dibandingkan dengan anak yang lahir dari ibu dengan umur antara 20-35 years. Anak dari ibu yang bekerja 81% memiliki risiko kematian neonatal lebih tinggi bila dibandingkan dengan anak yang lahir dari ibu tidak bekerja. Kesimpulan: Anak yang lahir dengan berat badan rendah dan lahir dari ibu muda memiliki risiko kematian neonatal lebih tinggi. Bayi yang lahir dengan berat badan rendah membutuhkan perawatan yang tepat untuk memperpanjang ketahanan hidup anak. ( Health Science Journal of Indonesia 2016;7(2): 113 - 117) Kata kunci: Berat badan lahir rendah, kematian neonatal, Indonesia Abstract Background: Neonatal mortality rates in Indonesia remain steady in the past decades (20 in 2002 to 19 per 1000 live births in 2012). In order to accelerate the decline in neonatal mortality rate in Indonesia, specific interventions would have to target key factors causing mortality. This study aims to examine contribution of low birth weight on neonatal mortality in Indonesia. Methods: Data from the Indonesia Demographic and Health Survey (IDHS) conducted in 2012 were used in the analysis. A total of 18021 live births in the last five years preceding the survey were reported from the mothers. Completed information of their children (14837 children) were taken for this analysis. The adjusted relative risk with cox proportional hazard regression analysis were used to assess the strength of association to neonatal mortality. Results: Children born in low birth weight were 9.89-fold higher risk of neonatal mortality compared to children born in normal weight [adjusted relative risk (aRR) = 9.89; 95% confidence interval (CI): 7.41 – 13.19); P = < 0.0001]. Children delivered from younger mothers (aged 15 - 19 years) had 94% higher risk of neonatal mortality compared to children delivered from mothers aged 20-35 years. Working mothers had 81% higher risk of neonatal mortality compared to unemployed mothers. Conclusion: Children born in a low birth weight and born from younger mothers had higher risk of neonatal mortality. Appropriate care and treatment for children born in low birth weight is needed to prolonged survival rates of the children. ( Health Science Journal of Indonesia 2016;7(2): 113 - 117) Keywords: Low birth weight, neonatal mortality, Indonesia