This paper seeks to find correlations between Air Pollution (AP) and COVID-19 hospital admissions as the basis for a conceptual personalised monitoring system for people at risk of Acute Respiratory Infections. A review of related work was carried out on the link between pollution and COVID-19 hospital admissions. Furthermore, machine learning models were examined to determine the most appropriate models for the prediction of pollution levels and COVID-19. The research objectives were the creation of a Machine Learning Algorithm that will predict a Daily Air Quality Index (DAQI). Literature suggested that short and long-term exposure to Particulate Matter is associated with a large set of adverse health complications, this includes more hospital admissions and in-turn, fatalities. It was derived from the Exploratory Data Analysis that the Air Quality in Cardiff is, on average, low and only a few outlying days contribute to just under a months’ worth of Air Quality in a DAQI band that isn’t low. Statistical analysis of three machine learning algorithms indicated the most accurate being Random Forest with performance metrics of both Cross Validation and Percentage split showing a Mean Absolute Error of 0.07–0.09, which is very low. This paper suggests that further research should be conducted surrounding statistical machine learning to find correlations between AP and COVID-19 Hospitalisations within Cardiff. Furthermore, improvements in accuracy and predictive capability would be enhanced by the expanding the dataset used.