Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach
During the COVID-19 pandemic, West Virginia developed an aggressive SARS-CoV-2 testing strategy which included utilizing pop-up mobile testing in locations anticipated to have near-term increases in SARS-CoV-2 infections. This study describes and compares two methods for predicting near-term SARS-Co...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2021-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8565789/?tool=EBI |
| _version_ | 1818916366818738176 |
|---|---|
| author | Bradley S. Price Maryam Khodaverdi Adam Halasz Brian Hendricks Wesley Kimble Gordon S. Smith Sally L. Hodder |
| author_facet | Bradley S. Price Maryam Khodaverdi Adam Halasz Brian Hendricks Wesley Kimble Gordon S. Smith Sally L. Hodder |
| author_sort | Bradley S. Price |
| collection | DOAJ |
| description | During the COVID-19 pandemic, West Virginia developed an aggressive SARS-CoV-2 testing strategy which included utilizing pop-up mobile testing in locations anticipated to have near-term increases in SARS-CoV-2 infections. This study describes and compares two methods for predicting near-term SARS-CoV-2 incidence in West Virginia counties. The first method, Rt Only, is solely based on producing forecasts for each county using the daily instantaneous reproductive numbers, Rt. The second method, ML+Rt, is a machine learning approach that uses a Long Short-Term Memory network to predict the near-term number of cases for each county using epidemiological statistics such as Rt, county population information, and time series trends including information on major holidays, as well as leveraging statewide COVID-19 trends across counties and county population size. Both approaches used daily county-level SARS-CoV-2 incidence data provided by the West Virginia Department Health and Human Resources beginning April 2020. The methods are compared on the accuracy of near-term SARS-CoV-2 increases predictions by county over 17 weeks from January 1, 2021- April 30, 2021. Both methods performed well (correlation between forecasted number of cases and the actual number of cases week over week is 0.872 for the ML+Rt method and 0.867 for the Rt Only method) but differ in performance at various time points. Over the 17-week assessment period, the ML+Rt method outperforms the Rt Only method in identifying larger spikes. Results show that both methods perform adequately in both rural and non-rural predictions. Finally, a detailed discussion on practical issues regarding implementing forecasting models for public health action based on Rt is provided, and the potential for further development of machine learning methods that are enhanced by Rt. |
| first_indexed | 2024-12-20T00:17:02Z |
| format | Article |
| id | doaj.art-6e5b4a28a76e4c1c8caf8dad30f84e41 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-20T00:17:02Z |
| publishDate | 2021-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-6e5b4a28a76e4c1c8caf8dad30f84e412022-12-21T20:00:19ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-011611Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approachBradley S. PriceMaryam KhodaverdiAdam HalaszBrian HendricksWesley KimbleGordon S. SmithSally L. HodderDuring the COVID-19 pandemic, West Virginia developed an aggressive SARS-CoV-2 testing strategy which included utilizing pop-up mobile testing in locations anticipated to have near-term increases in SARS-CoV-2 infections. This study describes and compares two methods for predicting near-term SARS-CoV-2 incidence in West Virginia counties. The first method, Rt Only, is solely based on producing forecasts for each county using the daily instantaneous reproductive numbers, Rt. The second method, ML+Rt, is a machine learning approach that uses a Long Short-Term Memory network to predict the near-term number of cases for each county using epidemiological statistics such as Rt, county population information, and time series trends including information on major holidays, as well as leveraging statewide COVID-19 trends across counties and county population size. Both approaches used daily county-level SARS-CoV-2 incidence data provided by the West Virginia Department Health and Human Resources beginning April 2020. The methods are compared on the accuracy of near-term SARS-CoV-2 increases predictions by county over 17 weeks from January 1, 2021- April 30, 2021. Both methods performed well (correlation between forecasted number of cases and the actual number of cases week over week is 0.872 for the ML+Rt method and 0.867 for the Rt Only method) but differ in performance at various time points. Over the 17-week assessment period, the ML+Rt method outperforms the Rt Only method in identifying larger spikes. Results show that both methods perform adequately in both rural and non-rural predictions. Finally, a detailed discussion on practical issues regarding implementing forecasting models for public health action based on Rt is provided, and the potential for further development of machine learning methods that are enhanced by Rt.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8565789/?tool=EBI |
| spellingShingle | Bradley S. Price Maryam Khodaverdi Adam Halasz Brian Hendricks Wesley Kimble Gordon S. Smith Sally L. Hodder Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach PLoS ONE |
| title | Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach |
| title_full | Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach |
| title_fullStr | Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach |
| title_full_unstemmed | Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach |
| title_short | Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach |
| title_sort | predicting increases in covid 19 incidence to identify locations for targeted testing in west virginia a machine learning enhanced approach |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8565789/?tool=EBI |
| work_keys_str_mv | AT bradleysprice predictingincreasesincovid19incidencetoidentifylocationsfortargetedtestinginwestvirginiaamachinelearningenhancedapproach AT maryamkhodaverdi predictingincreasesincovid19incidencetoidentifylocationsfortargetedtestinginwestvirginiaamachinelearningenhancedapproach AT adamhalasz predictingincreasesincovid19incidencetoidentifylocationsfortargetedtestinginwestvirginiaamachinelearningenhancedapproach AT brianhendricks predictingincreasesincovid19incidencetoidentifylocationsfortargetedtestinginwestvirginiaamachinelearningenhancedapproach AT wesleykimble predictingincreasesincovid19incidencetoidentifylocationsfortargetedtestinginwestvirginiaamachinelearningenhancedapproach AT gordonssmith predictingincreasesincovid19incidencetoidentifylocationsfortargetedtestinginwestvirginiaamachinelearningenhancedapproach AT sallylhodder predictingincreasesincovid19incidencetoidentifylocationsfortargetedtestinginwestvirginiaamachinelearningenhancedapproach |