An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number <i>R<sub>t</sub></i> in Italy
Since December 2019, the novel coronavirus disease (COVID-19) has had a considerable impact on the health and socio-economic fabric of Italy. The effective reproduction number <i>R<sub>t</sub></i> is one of the most representative indicators of the contagion status as it repo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/3/1/9 |
| _version_ | 1827650267274805248 |
|---|---|
| author | Andrea Gatto Valeria Aloisi Gabriele Accarino Francesco Immorlano Marco Chiarelli Giovanni Aloisio |
| author_facet | Andrea Gatto Valeria Aloisi Gabriele Accarino Francesco Immorlano Marco Chiarelli Giovanni Aloisio |
| author_sort | Andrea Gatto |
| collection | DOAJ |
| description | Since December 2019, the novel coronavirus disease (COVID-19) has had a considerable impact on the health and socio-economic fabric of Italy. The effective reproduction number <i>R<sub>t</sub></i> is one of the most representative indicators of the contagion status as it reports the number of new infections caused by an infected subject in a partially immunized population. The task of predicting <i>R<sub>t</sub></i> values forward in time is challenging and, historically, it has been addressed by exploiting compartmental models or statistical frameworks. The present study proposes an Artificial Neural Networks-based approach to predict the <i>R<sub>t</sub></i> temporal trend at a daily resolution. For each Italian region and autonomous province, 21 daily COVID-19 indicators were exploited for the 7-day ahead prediction of the <i>R<sub>t</sub></i> trend by means of different neural network architectures, i.e., Feed Forward, Mono-Dimensional Convolutional, and Long Short-Term Memory. Focusing on Lombardy, which is one of the most affected regions, the predictions proved to be very accurate, with a minimum Root Mean Squared Error (<i>RMSE</i>) ranging from 0.035 at day <i>t</i> + 1 to 0.106 at day <i>t</i> + 7. Overall, the results show that it is possible to obtain accurate forecasts in Italy at a daily temporal resolution instead of the weekly resolution characterizing the official <i>R<sub>t</sub></i> data. |
| first_indexed | 2024-03-09T20:12:59Z |
| format | Article |
| id | doaj.art-d1b356ca2ac44262b886efed57e47ba1 |
| institution | Directory Open Access Journal |
| issn | 2673-2688 |
| language | English |
| last_indexed | 2024-03-09T20:12:59Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AI |
| spelling | doaj.art-d1b356ca2ac44262b886efed57e47ba12023-11-24T00:08:40ZengMDPI AGAI2673-26882022-02-013114616310.3390/ai3010009An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number <i>R<sub>t</sub></i> in ItalyAndrea Gatto0Valeria Aloisi1Gabriele Accarino2Francesco Immorlano3Marco Chiarelli4Giovanni Aloisio5Euro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Marco Biagi, 5, 73100 Lecce, ItalyEuro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Marco Biagi, 5, 73100 Lecce, ItalyEuro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Marco Biagi, 5, 73100 Lecce, ItalyEuro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Marco Biagi, 5, 73100 Lecce, ItalyEuro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Marco Biagi, 5, 73100 Lecce, ItalyEuro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Marco Biagi, 5, 73100 Lecce, ItalySince December 2019, the novel coronavirus disease (COVID-19) has had a considerable impact on the health and socio-economic fabric of Italy. The effective reproduction number <i>R<sub>t</sub></i> is one of the most representative indicators of the contagion status as it reports the number of new infections caused by an infected subject in a partially immunized population. The task of predicting <i>R<sub>t</sub></i> values forward in time is challenging and, historically, it has been addressed by exploiting compartmental models or statistical frameworks. The present study proposes an Artificial Neural Networks-based approach to predict the <i>R<sub>t</sub></i> temporal trend at a daily resolution. For each Italian region and autonomous province, 21 daily COVID-19 indicators were exploited for the 7-day ahead prediction of the <i>R<sub>t</sub></i> trend by means of different neural network architectures, i.e., Feed Forward, Mono-Dimensional Convolutional, and Long Short-Term Memory. Focusing on Lombardy, which is one of the most affected regions, the predictions proved to be very accurate, with a minimum Root Mean Squared Error (<i>RMSE</i>) ranging from 0.035 at day <i>t</i> + 1 to 0.106 at day <i>t</i> + 7. Overall, the results show that it is possible to obtain accurate forecasts in Italy at a daily temporal resolution instead of the weekly resolution characterizing the official <i>R<sub>t</sub></i> data.https://www.mdpi.com/2673-2688/3/1/9accurate daily forecastsartificial neural networksCOVID-19effective reproduction number <i>R<sub>t</sub></i>epidemiological factorsItalian regions |
| spellingShingle | Andrea Gatto Valeria Aloisi Gabriele Accarino Francesco Immorlano Marco Chiarelli Giovanni Aloisio An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number <i>R<sub>t</sub></i> in Italy AI accurate daily forecasts artificial neural networks COVID-19 effective reproduction number <i>R<sub>t</sub></i> epidemiological factors Italian regions |
| title | An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number <i>R<sub>t</sub></i> in Italy |
| title_full | An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number <i>R<sub>t</sub></i> in Italy |
| title_fullStr | An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number <i>R<sub>t</sub></i> in Italy |
| title_full_unstemmed | An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number <i>R<sub>t</sub></i> in Italy |
| title_short | An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number <i>R<sub>t</sub></i> in Italy |
| title_sort | artificial neural network based approach for predicting the covid 19 daily effective reproduction number i r sub t sub i in italy |
| topic | accurate daily forecasts artificial neural networks COVID-19 effective reproduction number <i>R<sub>t</sub></i> epidemiological factors Italian regions |
| url | https://www.mdpi.com/2673-2688/3/1/9 |
| work_keys_str_mv | AT andreagatto anartificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT valeriaaloisi anartificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT gabrieleaccarino anartificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT francescoimmorlano anartificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT marcochiarelli anartificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT giovannialoisio anartificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT andreagatto artificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT valeriaaloisi artificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT gabrieleaccarino artificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT francescoimmorlano artificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT marcochiarelli artificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly AT giovannialoisio artificialneuralnetworkbasedapproachforpredictingthecovid19dailyeffectivereproductionnumberirsubtsubiinitaly |