Application of PanDict System Based on EPSEIRV and SI3R Models in Epidemic Forecasting and Healthcare Resource Planning

Global epidemics, such as COVID-19, have had a significant impact on almost all countries in terms of economy, hospitalization, lifestyle, and other aspects. Part of the reason is their high infectivity, but more importantly, due to the speed of virus transmission, the probability of new varieties appearing, and the conditions under which they appear, we cannot predict, making it a major challenge for us to arrange resources reasonably when the virus appears. Due to the inability of previous epidemic models to solve these three most important problems, we have developed the PanDict system, which can help solve all three basic problems discussed above. For a detailed explanation, our model consists of three key components that address the above issues: predicting the spread of new viruses in each local community and using our newly designed EPSEIRV model to calculate its R0 value; Creating and using the SI3R model to simulate variant competition; Predict the insufficient hospitalization in each state and use our IHOV model to generate a visual representation of the predicted demand. Compared to other vague and incorrect predictions/models, our EPSEIRV model accurately predicted the transmission of the severe acute respiratory syndrome coronavirus type 2 Omicron variant in the United States and South Africa before reaching its peak. In addition, the high infection rate of viruses allows them to spread widely among the population before vaccines are fully developed. As a result, the number of patients will inevitably surge, which will make hospitals overwhelmed, making the IHOV model particularly necessary. The PanDict model can quickly and accurately predict the speed of disease transmission, whether the disease will successfully mutate, and how to arrange hospitalization resources to most effectively alleviate pain. In addition, the PanDict model enables the hospitalization system to be more prepared for the upcoming surge in patients, which will greatly reduce excess deaths and insufficient hospitalization.