What If…? Pandemic policy-decision-support to guide a cost-benefit-optimised, country-specific response.
<h4>Background</h4>After 18 months of responding to the COVID-19 pandemic, there is still no agreement on the optimal combination of mitigation strategies. The efficacy and collateral damage of pandemic policies are dependent on constantly evolving viral epidemiology as well as the volat...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2022-01-01
|
Series: | PLOS Global Public Health |
Online Access: | https://doi.org/10.1371/journal.pgph.0000721 |
_version_ | 1797695408653205504 |
---|---|
author | Giorgio Mannarini Francesco Posa Thierry Bossy Lucas Massemin Javier Fernandez-Castanon Tatjana Chavdarova Pablo Cañas Prakhar Gupta Martin Jaggi Mary-Anne Hartley |
author_facet | Giorgio Mannarini Francesco Posa Thierry Bossy Lucas Massemin Javier Fernandez-Castanon Tatjana Chavdarova Pablo Cañas Prakhar Gupta Martin Jaggi Mary-Anne Hartley |
author_sort | Giorgio Mannarini |
collection | DOAJ |
description | <h4>Background</h4>After 18 months of responding to the COVID-19 pandemic, there is still no agreement on the optimal combination of mitigation strategies. The efficacy and collateral damage of pandemic policies are dependent on constantly evolving viral epidemiology as well as the volatile distribution of socioeconomic and cultural factors. This study proposes a data-driven approach to quantify the efficacy of the type, duration, and stringency of COVID-19 mitigation policies in terms of transmission control and economic loss, personalised to individual countries.<h4>Methods</h4>We present What If…?, a deep learning pandemic-policy-decision-support algorithm simulating pandemic scenarios to guide and evaluate policy impact in real time. It leverages a uniquely diverse live global data-stream of socioeconomic, demographic, climatic, and epidemic trends on over a year of data (04/2020-06/2021) from 116 countries. The economic damage of the policies is also evaluated on the 29 higher income countries for which data is available. The efficacy and economic damage estimates are derived from two neural networks that infer respectively the daily R-value (RE) and unemployment rate (UER). Reinforcement learning then pits these models against each other to find the optimal policies minimising both RE and UER.<h4>Findings</h4>The models made high accuracy predictions of RE and UER (average mean squared errors of 0.043 [CI95: 0.042-0.044] and 4.473% [CI95: 2.619-6.326] respectively), which allow the computation of country-specific policy efficacy in terms of cost and benefit. In the 29 countries where economic information was available, the reinforcement learning agent suggested a policy mix that is predicted to outperform those implemented in reality by over 10-fold for RE reduction (0.250 versus 0.025) and at 28-fold less cost in terms of UER (1.595% versus 0.057%).<h4>Conclusion</h4>These results show that deep learning has the potential to guide evidence-based understanding and implementation of public health policies. |
first_indexed | 2024-03-12T03:12:00Z |
format | Article |
id | doaj.art-2ebe4bdacfe9448ebe7606f59a90f2f4 |
institution | Directory Open Access Journal |
issn | 2767-3375 |
language | English |
last_indexed | 2024-03-12T03:12:00Z |
publishDate | 2022-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLOS Global Public Health |
spelling | doaj.art-2ebe4bdacfe9448ebe7606f59a90f2f42023-09-03T14:21:31ZengPublic Library of Science (PLoS)PLOS Global Public Health2767-33752022-01-0128e000072110.1371/journal.pgph.0000721What If…? Pandemic policy-decision-support to guide a cost-benefit-optimised, country-specific response.Giorgio MannariniFrancesco PosaThierry BossyLucas MasseminJavier Fernandez-CastanonTatjana ChavdarovaPablo CañasPrakhar GuptaMartin JaggiMary-Anne Hartley<h4>Background</h4>After 18 months of responding to the COVID-19 pandemic, there is still no agreement on the optimal combination of mitigation strategies. The efficacy and collateral damage of pandemic policies are dependent on constantly evolving viral epidemiology as well as the volatile distribution of socioeconomic and cultural factors. This study proposes a data-driven approach to quantify the efficacy of the type, duration, and stringency of COVID-19 mitigation policies in terms of transmission control and economic loss, personalised to individual countries.<h4>Methods</h4>We present What If…?, a deep learning pandemic-policy-decision-support algorithm simulating pandemic scenarios to guide and evaluate policy impact in real time. It leverages a uniquely diverse live global data-stream of socioeconomic, demographic, climatic, and epidemic trends on over a year of data (04/2020-06/2021) from 116 countries. The economic damage of the policies is also evaluated on the 29 higher income countries for which data is available. The efficacy and economic damage estimates are derived from two neural networks that infer respectively the daily R-value (RE) and unemployment rate (UER). Reinforcement learning then pits these models against each other to find the optimal policies minimising both RE and UER.<h4>Findings</h4>The models made high accuracy predictions of RE and UER (average mean squared errors of 0.043 [CI95: 0.042-0.044] and 4.473% [CI95: 2.619-6.326] respectively), which allow the computation of country-specific policy efficacy in terms of cost and benefit. In the 29 countries where economic information was available, the reinforcement learning agent suggested a policy mix that is predicted to outperform those implemented in reality by over 10-fold for RE reduction (0.250 versus 0.025) and at 28-fold less cost in terms of UER (1.595% versus 0.057%).<h4>Conclusion</h4>These results show that deep learning has the potential to guide evidence-based understanding and implementation of public health policies.https://doi.org/10.1371/journal.pgph.0000721 |
spellingShingle | Giorgio Mannarini Francesco Posa Thierry Bossy Lucas Massemin Javier Fernandez-Castanon Tatjana Chavdarova Pablo Cañas Prakhar Gupta Martin Jaggi Mary-Anne Hartley What If…? Pandemic policy-decision-support to guide a cost-benefit-optimised, country-specific response. PLOS Global Public Health |
title | What If…? Pandemic policy-decision-support to guide a cost-benefit-optimised, country-specific response. |
title_full | What If…? Pandemic policy-decision-support to guide a cost-benefit-optimised, country-specific response. |
title_fullStr | What If…? Pandemic policy-decision-support to guide a cost-benefit-optimised, country-specific response. |
title_full_unstemmed | What If…? Pandemic policy-decision-support to guide a cost-benefit-optimised, country-specific response. |
title_short | What If…? Pandemic policy-decision-support to guide a cost-benefit-optimised, country-specific response. |
title_sort | what if pandemic policy decision support to guide a cost benefit optimised country specific response |
url | https://doi.org/10.1371/journal.pgph.0000721 |
work_keys_str_mv | AT giorgiomannarini whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse AT francescoposa whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse AT thierrybossy whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse AT lucasmassemin whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse AT javierfernandezcastanon whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse AT tatjanachavdarova whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse AT pablocanas whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse AT prakhargupta whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse AT martinjaggi whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse AT maryannehartley whatifpandemicpolicydecisionsupporttoguideacostbenefitoptimisedcountryspecificresponse |