A prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan
Abstract The COVID-19 pandemic has highlighted the global need for reliable models of disease spread. We propose an AI-augmented forecast modeling framework that provides daily predictions of the expected number of confirmed COVID-19 deaths, cases, and hospitalizations during the following 4 weeks....
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/5a7e3925daed42c8b7a7024387fa5045 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:5a7e3925daed42c8b7a7024387fa5045 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:5a7e3925daed42c8b7a7024387fa50452021-12-02T18:01:45ZA prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan10.1038/s41746-021-00511-72398-6352https://doaj.org/article/5a7e3925daed42c8b7a7024387fa50452021-10-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00511-7https://doaj.org/toc/2398-6352Abstract The COVID-19 pandemic has highlighted the global need for reliable models of disease spread. We propose an AI-augmented forecast modeling framework that provides daily predictions of the expected number of confirmed COVID-19 deaths, cases, and hospitalizations during the following 4 weeks. We present an international, prospective evaluation of our models’ performance across all states and counties in the USA and prefectures in Japan. Nationally, incident mean absolute percentage error (MAPE) for predicting COVID-19 associated deaths during prospective deployment remained consistently <8% (US) and <29% (Japan), while cumulative MAPE remained <2% (US) and <10% (Japan). We show that our models perform well even during periods of considerable change in population behavior, and are robust to demographic differences across different geographic locations. We further demonstrate that our framework provides meaningful explanatory insights with the models accurately adapting to local and national policy interventions. Our framework enables counterfactual simulations, which indicate continuing Non-Pharmaceutical Interventions alongside vaccinations is essential for faster recovery from the pandemic, delaying the application of interventions has a detrimental effect, and allow exploration of the consequences of different vaccination strategies. The COVID-19 pandemic remains a global emergency. In the face of substantial challenges ahead, the approach presented here has the potential to inform critical decisions.Sercan Ö. ArıkJoel ShorRajarishi SinhaJinsung YoonJoseph R. LedsamLong T. LeMichael W. DusenberryNathanael C. YoderKris PopendorfArkady EpshteynJohan EuphrosineElli KanalIsaac JonesChun-Liang LiBeth LuanJoe MckennaVikas MenonShashank SinghMimi SunAshwin Sura RaviLeyou ZhangDario SavaKane CunninghamHiroki KayamaThomas TsaiDaisuke YoneokaShuhei NomuraHiroaki MiyataTomas PfisterNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-18 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Computer applications to medicine. Medical informatics R858-859.7 |
| spellingShingle |
Computer applications to medicine. Medical informatics R858-859.7 Sercan Ö. Arık Joel Shor Rajarishi Sinha Jinsung Yoon Joseph R. Ledsam Long T. Le Michael W. Dusenberry Nathanael C. Yoder Kris Popendorf Arkady Epshteyn Johan Euphrosine Elli Kanal Isaac Jones Chun-Liang Li Beth Luan Joe Mckenna Vikas Menon Shashank Singh Mimi Sun Ashwin Sura Ravi Leyou Zhang Dario Sava Kane Cunningham Hiroki Kayama Thomas Tsai Daisuke Yoneoka Shuhei Nomura Hiroaki Miyata Tomas Pfister A prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan |
| description |
Abstract The COVID-19 pandemic has highlighted the global need for reliable models of disease spread. We propose an AI-augmented forecast modeling framework that provides daily predictions of the expected number of confirmed COVID-19 deaths, cases, and hospitalizations during the following 4 weeks. We present an international, prospective evaluation of our models’ performance across all states and counties in the USA and prefectures in Japan. Nationally, incident mean absolute percentage error (MAPE) for predicting COVID-19 associated deaths during prospective deployment remained consistently <8% (US) and <29% (Japan), while cumulative MAPE remained <2% (US) and <10% (Japan). We show that our models perform well even during periods of considerable change in population behavior, and are robust to demographic differences across different geographic locations. We further demonstrate that our framework provides meaningful explanatory insights with the models accurately adapting to local and national policy interventions. Our framework enables counterfactual simulations, which indicate continuing Non-Pharmaceutical Interventions alongside vaccinations is essential for faster recovery from the pandemic, delaying the application of interventions has a detrimental effect, and allow exploration of the consequences of different vaccination strategies. The COVID-19 pandemic remains a global emergency. In the face of substantial challenges ahead, the approach presented here has the potential to inform critical decisions. |
| format |
article |
| author |
Sercan Ö. Arık Joel Shor Rajarishi Sinha Jinsung Yoon Joseph R. Ledsam Long T. Le Michael W. Dusenberry Nathanael C. Yoder Kris Popendorf Arkady Epshteyn Johan Euphrosine Elli Kanal Isaac Jones Chun-Liang Li Beth Luan Joe Mckenna Vikas Menon Shashank Singh Mimi Sun Ashwin Sura Ravi Leyou Zhang Dario Sava Kane Cunningham Hiroki Kayama Thomas Tsai Daisuke Yoneoka Shuhei Nomura Hiroaki Miyata Tomas Pfister |
| author_facet |
Sercan Ö. Arık Joel Shor Rajarishi Sinha Jinsung Yoon Joseph R. Ledsam Long T. Le Michael W. Dusenberry Nathanael C. Yoder Kris Popendorf Arkady Epshteyn Johan Euphrosine Elli Kanal Isaac Jones Chun-Liang Li Beth Luan Joe Mckenna Vikas Menon Shashank Singh Mimi Sun Ashwin Sura Ravi Leyou Zhang Dario Sava Kane Cunningham Hiroki Kayama Thomas Tsai Daisuke Yoneoka Shuhei Nomura Hiroaki Miyata Tomas Pfister |
| author_sort |
Sercan Ö. Arık |
| title |
A prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan |
| title_short |
A prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan |
| title_full |
A prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan |
| title_fullStr |
A prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan |
| title_full_unstemmed |
A prospective evaluation of AI-augmented epidemiology to forecast COVID-19 in the USA and Japan |
| title_sort |
prospective evaluation of ai-augmented epidemiology to forecast covid-19 in the usa and japan |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/5a7e3925daed42c8b7a7024387fa5045 |
| work_keys_str_mv |
AT sercanoarık aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT joelshor aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT rajarishisinha aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT jinsungyoon aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT josephrledsam aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT longtle aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT michaelwdusenberry aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT nathanaelcyoder aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT krispopendorf aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT arkadyepshteyn aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT johaneuphrosine aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT ellikanal aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT isaacjones aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT chunliangli aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT bethluan aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT joemckenna aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT vikasmenon aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT shashanksingh aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT mimisun aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT ashwinsuraravi aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT leyouzhang aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT dariosava aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT kanecunningham aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT hirokikayama aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT thomastsai aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT daisukeyoneoka aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT shuheinomura aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT hiroakimiyata aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT tomaspfister aprospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT sercanoarık prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT joelshor prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT rajarishisinha prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT jinsungyoon prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT josephrledsam prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT longtle prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT michaelwdusenberry prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT nathanaelcyoder prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT krispopendorf prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT arkadyepshteyn prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT johaneuphrosine prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT ellikanal prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT isaacjones prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT chunliangli prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT bethluan prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT joemckenna prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT vikasmenon prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT shashanksingh prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT mimisun prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT ashwinsuraravi prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT leyouzhang prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT dariosava prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT kanecunningham prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT hirokikayama prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT thomastsai prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT daisukeyoneoka prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT shuheinomura prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT hiroakimiyata prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan AT tomaspfister prospectiveevaluationofaiaugmentedepidemiologytoforecastcovid19intheusaandjapan |
| _version_ |
1718378928343613440 |