Early Stage Machine Learning–Based Prediction of US County Vulnerability to the COVID-19 Pandemic: Machine Learning Approach

Abstract

Background The rapid spread of COVID-19 means that government and health services providers have little time to plan and design effective response policies. It is therefore important to quickly provide accurate predictions of how vulnerable geographic regions such as counties are to the spread of this virus. Objective The aim of this study is to develop county-level prediction around near future disease movement for COVID-19 occurrences using publicly available data. Methods We estimated county-level COVID-19 occurrences for the period March 14 to 31, 2020, based on data fused from multiple publicly available sources inclusive of health statistics, demographics, and geographical features. We developed a three-stage model using XGBoost, a machine learning algorithm, to quantify the probability of COVID-19 occurrence and estimate the number of potential occurrences for unaffected counties. Finally, these results were combined to predict the county-level risk. This risk was then used as an estimated after-five-day-vulnerability of the county. Results The model predictions showed a sensitivity over 71% and specificity over 94% for models built using data from March 14 to 31, 2020. We found that population, population density, percentage of people aged >70 years, and prevalence of comorbidities play an important role in predicting COVID-19 occurrences. We observed a positive association at the county level between urbanicity and vulnerability to COVID-19. Conclusions The developed model can be used for identification of vulnerable counties and potential data discrepancies. Limited testing facilities and delayed results introduce significant variation in reported cases, which produces a bias in the model.

Leveraging artificial intelligence for pandemic preparedness and response: a scoping review to identify key use cases

“…The most common techniques were variations of neural networks (Supplementary Table 2 ). These models forecasted various short- (e.g., 10 days 15 ) or longer-term (e.g., 24 days 16 ) outcomes including infections, deaths, and effects of non-pharmaceutical interventions; spread of COVID-19 across the globe 17 ; and regional vulnerability to COVID-19 18 . Although many studies compared the relative performance of various ML techniques, these models were rarely evaluated against traditional approaches.…”

Adaptive Susceptible-Infectious-Removed Model for Continuous Estimation of the COVID-19 Infection Rate and Reproduction Number in the United States: Modeling Study

“…Moreover, a single value of R t estimated for a large population does not reflect differences in subpopulations, such as age groups, which is especially relevant for COVID-19 [46][47][48]. The generation of a bank of aSIR models for each subpopulation or region can provide a more realistic insight into the dynamics of the pandemic across a larger population [49,50]. Another critical assumption is that once an individual is infected and recovers, he/she is no longer susceptible to repeated infection; however, this assumption does not appear strongly violated.…”

Machine Learning in Healthcare Communication

“…It is important to quickly obtain an accurate prediction of the vulnerability of geographic regions, such as countries that are vulnerable to this virus' spread. AI was used to make that prediction by developing a three-stage model using XGBoost, a machine learning algorithm that can estimate potential occurrences in unaffected countries and quantify the COVID-19 occurrence probability [89].…”