Optimizing COVID-19 vaccine distribution across the United States using deterministic and stochastic recurrent neural networks

• Published in: PloS one Vol. 16; no. 7; p. e0253925
• Main Authors: Davahli, Mohammad Reza, Karwowski, Waldemar, Fiok, Krzysztof
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 06.07.2021; Public Library of Science (PLoS)
• Subjects: Artificial intelligence; Biology and Life Sciences; Computer and Information Sciences; Coronaviruses; COVID-19; COVID-19 - prevention & control; COVID-19 - virology; COVID-19 vaccines; COVID-19 Vaccines - administration & dosage; Datasets; Evaluation; Geographical distribution; Long short-term memory; Medicine and Health Sciences; Neural networks; Neural Networks, Computer; Pandemics; People and places; Physical Sciences; Predictions; Recurrent neural networks; Regression analysis; Regression models; Reproduction; Research and Analysis Methods; SARS-CoV-2 - isolation & purification; Seasonal variations; Self organizing maps; Similarity; Stochasticity; United States; Vaccination; Vaccination - statistics & numerical data; Vaccines; Viral diseases; Viruses; United States; Canada; United Kingdom > UK; United States > US; China; Italy; Florida; India
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0253925

Optimizing COVID-19 vaccine distribution can help plan around the limited production and distribution of vaccination, particularly in early stages. One of the main criteria for equitable vaccine distribution is predicting the geographic distribution of active virus at the time of vaccination. This research developed sequence-learning models to predict the behavior of the COVID-19 pandemic across the US, based on previously reported information. For this objective, we used two time-series datasets of confirmed COVID-19 cases and COVID-19 effective reproduction numbers from January 22, 2020 to November 26, 2020 for all states in the US. The datasets have 310 time-steps (days) and 50 features (US states). To avoid training the models for all states, we categorized US states on the basis of their similarity to previously reported COVID-19 behavior. For this purpose, we used an unsupervised self-organizing map to categorize all states of the US into four groups on the basis of the similarity of their effective reproduction numbers. After selecting a leading state (the state with earliest outbreaks) in each group, we developed deterministic and stochastic Long Short Term Memory (LSTM) and Mixture Density Network (MDN) models. We trained the models with data from each leading state to make predictions, then compared the models with a baseline linear regression model. We also remove seasonality and trends from a dataset of non-stationary COVID-19 cases to determine the effects on prediction. We showed that the deterministic LSTM model trained on the COVID-19 effective reproduction numbers outperforms other prediction methods.