No abstract

COVID‐19 vaccines have a limited supply, and there is a huge gap between supply and demand, leading to disproportionate administration. One of the main conditions on which balanced and optimal vaccine distribution depends are the health conditions of the vaccine recipients. Vaccine administration of front‐line workers, the elderly, and those with diseases should be prioritized. To solve this problem, we proposed a novel architecture called CovidXAI, which is trained with a self‐collected dataset with 24 parameters influencing the risk group of the vaccine recipient. Then, Random Forest and XGBoost classifiers have been used to train the model—having training accuracies of 0.85 and 0.87 respectively, to predict the risk factor, classified as low, medium, and high risk. The optimal vaccine distribution can be done using the derived from the predicted risk class. A web application is developed as a user interface, and Explainable AI (XAI) has been used to demonstrate the varying dependence of the various factors used in the dataset, on the output by CovidXAI.

No abstract

In December 2021, we published statistical research on Administrative Data Based Population Estimates (ABPEs) for Scotland’s population in 2016, 2017 and 2018.  This work was developed as part of a project to consider how administrative data could be used to support Scotland’s Census. Following the governance process, administrative datasets were processed and de-identified, before being transferred to Scotland’s National Safe Haven for linking and analysis.  The datasets used include data from health, the electoral register, vital events registrations, and education.  The methodology used several linking variables so data could be linked, even without exact agreement between records.  Records from across the data sources were resolved into individuals using these links.  Business rules then indicated which individuals to include in Scotland’s Integrated Demographic Dataset (SIDD).  The ABPEs were then produced from this and compared with the official mid-year population estimates (MYEs) to determine success. On aggregate, the population estimates from the ABPEs are very similar to the MYEs, differing by less than 0.5 per cent in each year.  When broken down further, larger differences occur with ABPEs having more males and fewer people aged over 65 when compared with the official statistics. A notable difference between the two is for males aged between 30 and 65 in deprived areas, with ABPEs up to 20% higher than the MYEs. These differences by deprivation are smaller for other age ranges and for females. The ABPEs tend to be higher than official estimates for urban areas, and lower for rural areas.  Differences for each local authority area range from 5 per cent below to 4 per cent above official estimates. It is therefore possible to produce Scottish population estimates purely from administrative sources that roughly agree with MYEs. Further investigation will help understand the differences for particular groups, and will be explored in future years by comparing ABPEs with the 2022 Census.

No abstract