Cluster Analysis of US COVID-19 Infected States for Vaccine Distribution.

Since December 2019, COVID-19 has been raging worldwide. To prevent the spread of COVID-19 infection, many countries have proposed epidemic prevention policies and quickly administered vaccines, However, under facing a shortage of vaccines, the United States did not put forward effective epidemic prevention policies in time to prevent the infection from expanding, resulting in the epidemic in the United States becoming more and more serious. Through "The COVID Tracking Project", this study collects medical indicators for each state in the United States from 2020 to 2021, and through feature selection, each state is clustered according to the epidemic's severity. Furthermore, through the confusion matrix of the classifier to verify the accuracy of the cluster analysis, the study results show that the Cascade K-means cluster analysis has the highest accuracy. This study also labeled the three clusters of the cluster analysis results as high, medium, and low infection levels. Policymakers could more objectively decide which states should prioritize vaccine allocation in a vaccine shortage to prevent the epidemic from continuing to expand. It is hoped that if there is a similar epidemic in the future, relevant policymakers can use the analysis procedure of this study to determine the allocation of relevant medical resources for epidemic prevention according to the severity of infection in each state to prevent the spread of infection.