ABSTRACT
BACKGROUND: According to previous reports, very high percentages of individuals in Saudi Arabia are undiagnosed for type 2 diabetes mellitus (T2DM). Despite conducting several screening and awareness campaigns, these efforts lacked full accessibility and consumed extensive human and material resources. Thus, developing machine learning (ML) models could enhance the population-based screening process. The study aims to compare a newly developed ML model's outcomes with the validated American Diabetes Association's (ADA) risk assessment regarding predicting people with high risk for T2DM. RESEARCH DESIGN AND METHODS: Patients' age, gender, and risk factors that were obtained from the National Health Information Center's dataset were used to build and train the ML model. To evaluate the developed ML model, an external validation study was conducted in three primary health care centers. A random sample (N = 3400) was selected from the non-diabetic individuals. RESULTS: The results showed the plotted data of sensitivity/100-specificity represented in the Receiver Operating Characteristic (ROC) curve with an AROC value of 0.803, 95% CI: 0.779-0.826. CONCLUSIONS: The current study reveals a new ML model proposed for population-level classification that can be an adequate tool for identifying those at high risk of T2DM or who already have T2DM but have not been diagnosed.
ABSTRACT
Recent national reports have indicated an increasing trend of dental decay among school-aged children. National school-based data are required to guide decision-making to ensure effective public health efforts to manage dental decay. This study aimed to assess the prevalence of dental decay among school-age children in Saudi Arabia and explore the possible link between dental decay and weight status. This was a cross-sectional analysis of a national sample including 1,134,317 Saudi children in the 1st, 4th, 7th, and 10th grades who participated in a national school screening program. Data for weight, height, body mass index (BMI), dental decay prevalence, and decayed, missing, and filled teeth (DMFT) index were analysed. An independent t-test, one-way analysis of variance, and chi-square test were used to compare the means, while Pearson's r correlation and multiple linear regression were used to examine the relationships between the study variables. The prevalence of dental decay was 24.20%, and dental decay was the highest among female students (26.5%), students in primary school (25.9%), students living in the eastern region (35.2%), in the administrative capital (27.6%), and in rural areas (23.4%). Dental decay was the highest among students who were underweight. Female sex and living in rural areas significantly predicted higher DMFT while being overweight/obese significantly predicted lower DMFT. Dental decay is highly prevalent among underweight students, female students, and students living in rural areas and the eastern regions of Saudi Arabia. To reduce the prevalence of dental decay and related health disparities, dental health screening programs should be designed to detect dental decay early among children at high risk due to abnormal BMIs and sociodemographic factors. In addition, dental health screening and management programs should utilize standardized dental decay assessment methods and ethnically representative growth charts.
ABSTRACT
Objectives: This paper aims to measure the impact of the implemented nonpharmaceutical interventions (NPIs) in the Kingdom of Saudi Arabia (KSA) during the pandemic using simulation modeling. Methods: To measure the impact of NPI, a hybrid agent-based and system dynamics simulation model was built and validated. Data were collected prospectively on a weekly basis. The core epidemiological model is based on a complex Susceptible-Exposed-Infectious-Recovered and Dead model of epidemic dynamics. Reverse engineering was performed on a weekly basis throughout the study period as a mean for model validation which reported on four outcomes: total cases, active cases, ICU cases, and deaths cases. To measure the impact of each NPI, the observed values of active and total cases were captured and compared to the projected values of active and total cases from the simulation. To measure the impact of each NPI, the study period was divided into rounds of incubation periods (cycles of 14 days each). The behavioral change of the spread of the disease was interpreted as the impact of NPIs that occurred at the beginning of the cycle. The behavioral change was measured by the change in the initial reproduction rate (R0). Results: After 18 weeks of the reverse engineering process, the model achieved a 0.4 % difference in total cases for prediction at the end of the study period. The results estimated that NPIs led to 64 % change in The R0. Our breakdown analysis of the impact of each NPI indicates that banning going to schools had the greatest impact on the infection reproduction rate (24 %). Conclusion: We used hybrid simulation modeling to measure the impact of NPIs taken by the KSA government. The finding further supports the notion that early NPIs adoption can effectively limit the spread of COVID-19. It also supports using simulation for building mathematical modeling for epidemiological scenarios.
ABSTRACT
Background: Recent reports indicated an increasing prevalence of obesity among children and adolescents in Saudi Arabia, making it an impending national epidemic. However, obesity prevalence data in children and adolescents in Saudi Arabia are largely inconsistent. Objectives: This study analyzed and compared the prevalence of obesity among a national sample of children and adolescents across sexes, school grades, regions, and city types in Saudi Arabia using the Growth Charts for Saudi Children and Adolescents. Methods: Weight, height, and body mass index (BMI) data from 1 134 317 children in first, fourth, seventh, and tenth school grades who participated in the national school screening program were analyzed cross-sectionally. BMI values were classified using the Growth Charts for Saudi Children and Adolescents. Results: Nearly 10.4% of students were overweight, 10.7 % were obese, and 4.50% were severely obese. Male students had a higher prevalence of overweight and obesity than their female counterparts. The prevalence of overweight and obesity was the highest among students in intermediate school, the Central region, and administrative capitals. Conclusion: Managing childhood obesity is challenging due to its multifaceted nature Therefore, utilizing clinical and community-based participatory approaches is essential to develop nationwide obesity prevention and management program that is effective and sustainable. This program must utilize dynamic BMI surveillance systems using ethnically representative growth references, conduct national pediatric obesity research with careful consideration for demographic and regional differences, lead targeted pediatric obesity awareness campaigns, provide obesity management interventions in a pediatric multi-disciplinary clinic, and evaluate the program outcomes periodically.
ABSTRACT
Background: During the COVID-19 pandemic, Saudi Arabia witnessed hesitancy from a proportion of the population toward taking the vaccine; thus, it was necessary to nudge them to uptake it. This study was conducted to assess the impact of using different types of messages to nudge the public to increase the proportion of vaccinated individuals. Methods: This study is a multi-arm randomized controlled trial aiming to assess the efficacy of using differently framed messages that appear as pop-notifications in Sehatty application. Of those who preregistered to receive a COVID-19 vaccine but didn't take it according to the Saudi national vaccine registry (n = 1,291,686), 12,000 individuals were randomly recruited and randomly assigned to one of five intervention groups (commitment, loss aversion, salience, social norms, and ego) or a control group. To ensure the exposure occurred in the intervention groups, we included only those who received the notification, which was confirmed by checking the information technology system. We used the Chi-square test to compare each intervention group against the control group separately. Also, we used the same test to investigate whether sex and age influenced the percentage of booked appointments in the intervention groups. Results: Social norms, ego, salience and loss aversion groups had higher percentages of booked appointments when compared to the control group (21.0%, p = 0.001; 19.1%, p = 0.011; 19.0%, p = 0.013; 18.4%, p = 0.034, respectively). Moreover, when combining the intervention groups, the percentage was higher than the control group (p < 0.001). The percentages of booked appointments made by Young adults (18-35 years old) were higher than that of adults over 35 years old in the social norms (22.6%, p = 0.016) and ego groups (21.0%, p = 0.010). At the same time, sex didn't affect the percentages of booked appointments in any group. Conclusion: Using different framings of messages to nudge the public to take vaccines can help increase the percentage of immunized individuals in a community. Nudges can boost the public health of a population during an unusual spread of vaccine-preventable diseases. Findings might also inspire governmental responses to other public health situations.
ABSTRACT
OBJECTIVES: Patient readmission is a costly and preventable burden on healthcare systems. The main objective of this study was to develop a machine-learning classification model to identify cardiovascular patients with a high risk of readmission. METHODS: Inpatient data were collected from 48 Ministry of Health hospitals (MOH) in Saudi Arabia from 2016 to 2019. Cardiovascular disease (CVD)-related diagnoses were defined as congestive heart failure (HF), ischemic heart disease (IHD), cardiac arrhythmias (CA), and valvular diseases (VD). Hospitalization days, daily hospitalization price, and the price of each basic and medical service provided were used to calculate the healthcare utilization cost. We employed a Python machine-learning model to identify all-cause 30-day CVD-related readmissions using the International Classification of Diseases, Revision 10 classification system (ICD10) as the gold standard. Demographics, comorbidities, and healthcare utilization were used as the independent variables. RESULTS: From 2016 to 2019, we identified 403,032 hospitalized patients from 48 hospitals in 13 administrative regions of Saudi Arabia. Out of these patients, 17,461 had a history of hospital admission for cardiovascular reasons. The total direct cost of overall hospitalizations was 1.6 B international dollars (I$) with an average of I$ 3,156 per hospitalization, whereas CVD-related readmission costs were estimated to be I$ 14.9 M, with an average of I$ 7,600 per readmission. Finally, an empirical approach was followed to test several algorithms to identify patients at high risk of readmission. The comparison indicated that the decision-tree algorithm correctly classified 2,336 instances (926 readmitted and 1,410 not readmitted) and showed a higher F1 score than other models (64%), with a recall of 71% and precision of 57%. CONCLUSION: This study identified IHD as the most prevalent CVD, and hypertension and diabetes were found to be the most common comorbidities among hospitalized CVD patients. Compared to general encounters, readmission encounters were nearly two times higher on average among the study population. Furthermore, we concluded that a machine-learning model can be used to identify CVD patients at a high risk of readmission. Further research is required to develop more accurate models based on clinical notes and laboratory results.