Predicting the development of T1D and identifying its Key Performance Indicators in children; a case-control study in Saudi Arabia.

The increasing incidence of type 1 diabetes (T1D) in children is a growing global concern. It is known that genetic and environmental factors contribute to childhood T1D. An optimal model to predict the development of T1D in children using Key Performance Indicators (KPIs) would aid medical practitioners in developing intervention plans. This paper for the first time has built a model to predict the risk of developing T1D and identify its significant KPIs in children aged (0-14) in Saudi Arabia. Machine learning methods, namely Logistic Regression, Random Forest, Support Vector Machine, Naive Bayes, and Artificial Neural Network have been utilised and compared for their relative performance. Analyses were performed in a population-based case-control study from three Saudi Arabian regions. The dataset (n = 1,142) contained demographic and socioeconomic status, genetic and disease history, nutrition history, obstetric history, and maternal characteristics. The comparison between case and control groups showed that most children (cases = 68% and controls = 88%) are from urban areas, 69% (cases) and 66% (control) were delivered after a full-term pregnancy and 31% of cases group were delivered by caesarean, which was higher than the controls (χ2 = 4.12, P-value = 0.042). Models were built using all available environmental and family history factors. The efficacy of models was evaluated using Area Under the Curve, Sensitivity, F Score and Precision. Full logistic regression outperformed other models with Accuracy = 0.77, Sensitivity, F Score and Precision of 0.70, and AUC = 0.83. The most significant KPIs were early exposure to cow's milk (OR = 2.92, P = 0.000), birth weight >4 Kg (OR = 3.11, P = 0.007), residency(rural) (OR = 3.74, P = 0.000), family history (first and second degree), and maternal age >25 years. The results presented here can assist healthcare providers in collecting and monitoring influential KPIs and developing intervention strategies to reduce the childhood T1D incidence rate in Saudi Arabia.

Development of Local Birth Weight Reference Based on Gestational Age and Sex in South Kalimantan Province, Indonesia.

Purpose: Percentile reference of babies' birth weight is an effective reference tool for early detection of the risk of neonatal morbidity and impaired growth. However, the lack of minimum local and national perinatal data makes its development in Indonesia difficult. This study aims to develop a local birth weight percentile reference for babies based on gestational age and sex by utilizing local data in South Kalimantan Province which is one of the provinces with the highest neonatal mortality rate in Indonesia. Patients and Methods: All single live newborns who were born and were recorded in 20 primary healthcare centers, between 1 June 2016 and 30 June 2017, were included in the study. Birth weight percentiles of infants were calculated using the weighted average method. The study focused on neonates born with gestational age from 36 to 40 weeks. Results: A local birth weight reference for babies has been developed. According to our local reference, the proportion of male newborns with a birth weight < 10th percentile was higher (7.0%) than the existing Indonesian (4.2-4.3%) and international references (3.3-6.2%). Similarly, the proportion of female newborns with a birth weight <10th percentile was higher (6.5%) than the existing Indonesian references (3.6-4.4%) and the global reference (5.8%) but lower than the Intergrowth 21st project (7.2%). The differences suggest that relative birth weight will likely be underestimated (overestimated) if other percentile references are used for the local population. Conclusion: A local birth weight percentile reference for babies in South Kalimantan Province based on gestational age (36-40 weeks) and sex has been developed. Access to the local data, as baseline information, will allow the compilation and comparison of pregnancy-related outcomes across provinces in Indonesia. Consequently, reliable national perinatal data can be strengthened to establish the national references for newborns' anthropometric measurements.

Predicting age at onset of type 1 diabetes in children using regression, artificial neural network and Random Forest: A case study in Saudi Arabia.

The rising incidence of type 1 diabetes (T1D) among children is an increasing concern globally. A reliable estimate of the age at onset of T1D in children would facilitate intervention plans for medical practitioners to reduce the problems with delayed diagnosis of T1D. This paper has utilised Multiple Linear Regression (MLR), Artificial Neural Network (ANN) and Random Forest (RF) to model and predict the age at onset of T1D in children in Saudi Arabia (S.A.) which is ranked as the 7th for the highest number of T1D and 5th in the world for the incidence rate of T1D. De-identified data between (2010-2020) from three cities in S.A. were used to model and predict the age at onset of T1D. The best subset model selection criteria, coefficient of determination, and diagnostic tests were deployed to select the most significant variables. The efficacy of models for predicting the age at onset was assessed using multi-prediction accuracy measures. The average age at onset of T1D is 6.2 years and the most common age group for onset is (5-9) years. Most of the children in the sample (68%) are from urban areas of S.A., 75% were delivered after a full term pregnancy length and 31% were delivered through a cesarean section. The models of best fit were the MLR and RF models with R2 = (0.85 and 0.95), the root mean square error = (0.25 and 0.15) and mean absolute error = (0.19 and 0.11) respectively for logarithm of age at onset. This study for the first time has utilised MLR, ANN and RF models to predict the age at onset of T1D in children in S.A. These models can effectively aid health care providers to monitor and create intervention strategies to reduce the impact of T1D in children in S.A.

The development of an alternative growth chart for estimated fetal weight in the absence of ultrasound: Application in Indonesia.

A fetal growth chart is a vital tool for assessing fetal risk during pregnancy. Since fetal weight cannot be directly measured, its reliable estimation at different stages of pregnancy has become an essential issue in obstetrics and gynecology and one of the critical elements in developing a fetal growth chart for estimated fetal weight. In Indonesia, however, a reliable model and data for fetal weight estimation remain challenging, and this causes the absence of a standard fetal growth chart in antenatal care practices. This study has reviewed and evaluated the efficacy of the prediction models used to develop the most prominent growth charts for estimated fetal weight. The study also has discussed the potential challenges when such surveillance tools are utilized in low resource settings. The study, then, has proposed an alternative model based only on maternal fundal height to estimate fetal weight. Finally, the study has developed an alternative growth chart and assessed its capability in detecting abnormal patterns of fetal growth during pregnancy. Prospective data from twenty selected primary health centers in South Kalimantan, Indonesia, were used for the proposed model validation, the comparison task, and the alternative growth chart development using both descriptive and inferential statistics. Results show that limited access to individual fetal biometric characteristics and low-quality data on personal maternal and neonatal characteristics make the existing fetal growth charts less applicable in the local setting. The proposed model based only on maternal fundal height has a comparable ability in predicting fetal weight with less error than the existing models. The results have shown that the developed chart based on the proposed model can effectively detect signs of abnormality, between 20 and 41 weeks, among low birth weight babies in the absence of ultrasound. Consequently, the developed chart would improve the quality of fetal risk assessment during pregnancy and reduce the risk of adverse neonatal outcomes.

Optimal Profile Limits for Maternal Mortality Rates (MMR) Influenced by Haemorrhage and Unsafe Abortion in South Sudan.

Maternal mortality rate (MMR) is one of the main worldwide public health challenges. Presently, the high levels of MMR are a common problem in the world public health and especially, in developing countries. Half of these maternal deaths occur in Sub-Saharan Africa where little or nothing progress has been made. South Sudan is one of the developing countries which has the highest MMR. Thus, this paper deploys statistical analysis to identify the significant physiological causes of MMR in South Sudan. Prediction models based on Poisson Regression are then developed to predict MMR in terms of the significant physiological causes. Coefficients of determination and variance inflation factor are deployed to assess the influence of the individual causes on MMR. Efficacy of the models is assessed by analyzing their prediction errors. The paper for the first time has used optimization procedures to develop yearly lower and upper profile limits for MMR. Hemorrhaging and unsafe abortion are used to achieve UN 2030 lower and upper MMR targets. The statistical analysis indicates that reducing haemorrhaging by 1.91% per year would reduce MMR by 1.91% (95% CI (42.85-52.53)), reducing unsafe abortion by 0.49% per year would reduce MMR by 0.49% (95% CI (11.06-13.56)). The results indicate that the most influential predictors of MMR are; hemorrhaging (38%), sepsis (11.5%), obstructed labour (11.5%), unsafe abortion (10%), and indirect causes such as anaemia, malaria, and HIV/AIDs virus (29%). The results also show that to obtain the UN recommended MMR levels of minimum 21 and maximum 42 by 2030, the Government and other stakeholders should simultaneously, reduce haemorrhaging from the current value of 62 to 33.38 and 16.69, reduce unsafe abortion from the current value of 16 to 8.62 and 4.31. Thirty years of data is used to develop the optimal reduced Poisson Model based on hemorrhaging and unsafe abortion. The model with R 2 of 92.68% can predict MMR with mean error of -0.42329 and SE-mean of 0.02268. The yearly optimal level of hemorrhage, unsafe abortion, and MMR can aid the government and other stakeholders on resources allocation to reduce the risk of maternal death.

Improving the Information Availability and Accessibility of Antenatal Measurements to Ensure Safe Delivery: A Research-Based Policy Recommendation to Reduce Neonatal Mortality in Indonesia.

PURPOSE: Assessing 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 METHODS: Descriptive 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. RESULTS: To 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. CONCLUSION: Consistent 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.

The Impact of Scientific and Technical Training on Improving Databases' Adequacy for Fetal Growth Chart Development in Limited-Resource Settings: A Case Study in the Province of South Kalimantan, Indonesia.

OBJECTIVES: To assess the impact of scientific and technical training on midwives' abilities in collecting and recording the key performance indicators for fetal growth chart development in limited-resource settings. METHODS: A descriptive design was used to describe midwives' abilities in timely collecting and recording the minimum data required to estimate fetal weight and develop fetal growth chart. The study was conducted among 19 urban and rural midwives in South Kalimantan, Indonesia, between April 2016 and October 2017. The training provided access to antenatal care information on 4,946 women (retrospective cohort study) and 381 women (prospective cohort study). RESULTS: The average amount of recorded antenatal care data on the key performance indicators of fetal growth assessment has been significantly improved (from 33.4% to 89.1%, p-value < 0.0005) through scientific and technical training. CONCLUSIONS: Scientific knowledge and technical abilities have enabled midwives to timely record routine data of the key performance indicators for fetal growth surveillance. Access to this information is vital during different stages of pregnancy. The information can be utilised as evidence-based guidelines to assess fetal risks through fetal weight estimation and to develop fetal growth chart that is currently not available in Indonesian primary healthcare systems.

Foetal weight prediction models at a given gestational age in the absence of ultrasound facilities: application in Indonesia.

BACKGROUND: Birth weight is one of the most important indicators of neonatal survival. A reliable estimate of foetal weight at different stages of pregnancy would facilitate intervention plans for medical practitioners to prevent the risk of low birth weight delivery. This study has developed reliable models to more accurately predict estimated foetal weight at a given gestation age in the absence of ultrasound facilities. METHODS: A primary health care centre was involved in collecting retrospective non-identified Indonesian data. The best subset model selection criteria, coefficient of determination, standard deviation, variance inflation factor, Mallows Cp, and diagnostic tests of residuals were deployed to select the most significant independent variables. Simple and multivariate linear regressions were used to develop the proposed models. The efficacy of models for predicting foetal weight at a given gestational age was assessed using multi-prediction accuracy measures. RESULTS: Four weight prediction models based on fundal height and its combinations with gestational age (between 32 and 41 weeks) and ultrasonic estimates of foetal head circumference and foetal abdominal circumference have been developed. Multiple comparison criteria show that the proposed models were more accurate than the existing models (mean prediction errors between - 0.2 and 2.4 g and median absolute percentage errors between 4.1 and 4.2%) in predicting foetal weight at a given gestational age (between 35 and 41 weeks). CONCLUSIONS: This research has developed models to more accurately predict estimated foetal weight at a given gestational age in the absence of ultrasound machines and trained ultra-sonographers. The efficacy of the models was assessed using retrospective data. The results show that the proposed models produced less error than the existing clinical and ultrasonic models. This research has resulted in the development of models where ultrasound facilities do not exist, to predict the estimated foetal weight at varying gestational age. This would promote the development of foetal inter growth charts, which are currently unavailable in Indonesian primary health care systems. Consistent monitoring of foetal growth would alleviate the risk of having inter growth abnormalities, such as low birth weight that is the most leading factor of neonatal mortality.

The Impact of Scientific and Technical Training on Improving Routine Collection of Antenatal Care Data for Maternal and Foetal Risk Assessment: A Case Study in the Province of South Kalimantan, Indonesia.

OBJECTIVES: First, to assess the impact of scientific and technical training on midwives' abilities in collecting and recording the results of routine antenatal care examinations. Second, to explore midwives' views with regard to factors affecting their abilities to successfully complete the data documentation tasks. METHODS: The study was conducted in South Kalimantan, Indonesia (April 2016-October 2017). Nineteen urban and rural midwives were selected. Access to antenatal care information on 4,946 women (retrospective cohort study) and 381 women (prospective cohort study) was granted. A descriptive and exploratory design was used to describe midwives' abilities and challenges pertaining to timely collection and recording of results concerning antenatal care examinations. RESULTS: Scientific and technical training has significantly improved the average amount of recorded antenatal care data (from 17.5% to 62.1%, p-value < 0.0005). Lack of awareness, high workload, and insufficient skills and facilities are the main reasons for the database gaps. CONCLUSIONS: The training has equipped midwives with scientific knowledge and technical abilities to allow routine collection of antenatal care data. Provision and adequate use of this information during different stages of pregnancy is crucial as an evidence-based guideline to assess maternal and foetal risk factors to ending preventable mortality.

Optimal profile limits for maternal mortality rate (MMR) in South Sudan.

BACKGROUND: Reducing Maternal Mortality Rate (MMR) is considered by the international community as one of the eight Millennium Development Goals. Based on previous studies, Skilled Assistant at Birth (SAB), General Fertility Rate (GFR) and Gross Domestic Product (GDP) have been identified as the most significant predictors of MMR in South Sudan. This paper aims for the first time to develop profile limits for the MMR in terms of significant predictors SAB, GFR, and GDP. The paper provides the optimal values of SAB and GFR for a given MMR level. METHODS: Logarithmic multi- regression model is used to model MMR in terms of SAB, GFR and GDP. Data from 1986 to 2015 collected from Juba Teaching Hospital was used to develop the model for predicting MMR. Optimization procedures are deployed to attain the optimal level of SAB and GFR for a given MMR level. MATLAB was used to conduct the optimization procedures. The optimized values were then used to develop lower and upper profile limits for yearly MMR, SAB and GFR. RESULTS: The statistical analysis shows that increasing SAB by 1.22% per year would decrease MMR by 1.4% (95% CI (0.4-5%)) decreasing GFR by 1.22% per year would decrease MMR by 1.8% (95% CI (0.5-6.26%)). The results also indicate that to achieve the UN recommended MMR levels of minimum 70 and maximum 140 by 2030, the government should simultaneously reduce GFR from the current value of 175 to 97 and 75, increase SAB from the current value of 19 to 50 and 76. CONCLUSIONS: This study for the first time has deployed optimization procedures to develop lower and upper yearly profile limits for maternal mortality rate targeting the UN recommended lower and upper MMR levels by 2030. The MMR profile limits have been accompanied by the profile limits for optimal yearly values of SAB and GFR levels. Having the optimal level of predictors that significantly influence the maternal mortality rate can effectively aid the government and international organizations to make informed evidence-based decisions on resources allocation and intervention plans to reduce the risk of maternal death.