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
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.
