Limits of Compartmental Models and New Opportunities for Machine Learning: A Case Study to Forecast the Second Wave of COVID-19 Hospitalizations in Lombardy, Italy
Compartmental models have long been used in epidemiological studies for predicting disease spread. However, a major issue when using compartmental mathematical models concerns the time-invariant formulation of hyper-parameters that prevent the model from following the evolution over time of the epid...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Informatics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9709/8/3/57 |
_version_ | 1797518807615406080 |
---|---|
author | Andrea Gatto Gabriele Accarino Valeria Aloisi Francesco Immorlano Francesco Donato Giovanni Aloisio |
author_facet | Andrea Gatto Gabriele Accarino Valeria Aloisi Francesco Immorlano Francesco Donato Giovanni Aloisio |
author_sort | Andrea Gatto |
collection | DOAJ |
description | Compartmental models have long been used in epidemiological studies for predicting disease spread. However, a major issue when using compartmental mathematical models concerns the time-invariant formulation of hyper-parameters that prevent the model from following the evolution over time of the epidemiological phenomenon under investigation. In order to cope with this problem, the present work suggests an alternative hybrid approach based on Machine Learning that avoids recalculation of hyper-parameters and only uses an initial set. This study shows that the proposed hybrid approach makes it possible to correct the expected loss of accuracy observed in the compartmental model when the considered time horizon increases. As a case study, a basic compartmental model has been designed and tested to forecast COVID-19 hospitalizations during the first and the second pandemic waves in Lombardy, Italy. The model is based on an extended formulation of the contact function that allows modelling of the trend of personal contacts throughout the reference period. Moreover, the scenario analysis proposed in this work can help policy-makers select the most appropriate containment measures to reduce hospitalizations and relieve pressure on the health system, but also to limit any negative impact on the economic and social systems. |
first_indexed | 2024-03-10T07:34:43Z |
format | Article |
id | doaj.art-4a95c4e10eff4925a1abd969783550ed |
institution | Directory Open Access Journal |
issn | 2227-9709 |
language | English |
last_indexed | 2024-03-10T07:34:43Z |
publishDate | 2021-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Informatics |
spelling | doaj.art-4a95c4e10eff4925a1abd969783550ed2023-11-22T13:34:52ZengMDPI AGInformatics2227-97092021-08-01835710.3390/informatics8030057Limits of Compartmental Models and New Opportunities for Machine Learning: A Case Study to Forecast the Second Wave of COVID-19 Hospitalizations in Lombardy, ItalyAndrea Gatto0Gabriele Accarino1Valeria Aloisi2Francesco Immorlano3Francesco Donato4Giovanni Aloisio5Euro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Augusto Imperatore, 16, 73100 Lecce, ItalyEuro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Augusto Imperatore, 16, 73100 Lecce, ItalyEuro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Augusto Imperatore, 16, 73100 Lecce, ItalyEuro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Augusto Imperatore, 16, 73100 Lecce, ItalyUnit of Hygiene, Epidemiology, and Public Health, Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Viale Europa 11, 25123 Brescia, ItalyEuro-Mediterranean Center on Climate Change (CMCC) Foundation, Via Augusto Imperatore, 16, 73100 Lecce, ItalyCompartmental models have long been used in epidemiological studies for predicting disease spread. However, a major issue when using compartmental mathematical models concerns the time-invariant formulation of hyper-parameters that prevent the model from following the evolution over time of the epidemiological phenomenon under investigation. In order to cope with this problem, the present work suggests an alternative hybrid approach based on Machine Learning that avoids recalculation of hyper-parameters and only uses an initial set. This study shows that the proposed hybrid approach makes it possible to correct the expected loss of accuracy observed in the compartmental model when the considered time horizon increases. As a case study, a basic compartmental model has been designed and tested to forecast COVID-19 hospitalizations during the first and the second pandemic waves in Lombardy, Italy. The model is based on an extended formulation of the contact function that allows modelling of the trend of personal contacts throughout the reference period. Moreover, the scenario analysis proposed in this work can help policy-makers select the most appropriate containment measures to reduce hospitalizations and relieve pressure on the health system, but also to limit any negative impact on the economic and social systems.https://www.mdpi.com/2227-9709/8/3/57accurate forecastscompartmental modelscontainment measureshealth emergencyhealth systemsMachine Learning |
spellingShingle | Andrea Gatto Gabriele Accarino Valeria Aloisi Francesco Immorlano Francesco Donato Giovanni Aloisio Limits of Compartmental Models and New Opportunities for Machine Learning: A Case Study to Forecast the Second Wave of COVID-19 Hospitalizations in Lombardy, Italy Informatics accurate forecasts compartmental models containment measures health emergency health systems Machine Learning |
title | Limits of Compartmental Models and New Opportunities for Machine Learning: A Case Study to Forecast the Second Wave of COVID-19 Hospitalizations in Lombardy, Italy |
title_full | Limits of Compartmental Models and New Opportunities for Machine Learning: A Case Study to Forecast the Second Wave of COVID-19 Hospitalizations in Lombardy, Italy |
title_fullStr | Limits of Compartmental Models and New Opportunities for Machine Learning: A Case Study to Forecast the Second Wave of COVID-19 Hospitalizations in Lombardy, Italy |
title_full_unstemmed | Limits of Compartmental Models and New Opportunities for Machine Learning: A Case Study to Forecast the Second Wave of COVID-19 Hospitalizations in Lombardy, Italy |
title_short | Limits of Compartmental Models and New Opportunities for Machine Learning: A Case Study to Forecast the Second Wave of COVID-19 Hospitalizations in Lombardy, Italy |
title_sort | limits of compartmental models and new opportunities for machine learning a case study to forecast the second wave of covid 19 hospitalizations in lombardy italy |
topic | accurate forecasts compartmental models containment measures health emergency health systems Machine Learning |
url | https://www.mdpi.com/2227-9709/8/3/57 |
work_keys_str_mv | AT andreagatto limitsofcompartmentalmodelsandnewopportunitiesformachinelearningacasestudytoforecastthesecondwaveofcovid19hospitalizationsinlombardyitaly AT gabrieleaccarino limitsofcompartmentalmodelsandnewopportunitiesformachinelearningacasestudytoforecastthesecondwaveofcovid19hospitalizationsinlombardyitaly AT valeriaaloisi limitsofcompartmentalmodelsandnewopportunitiesformachinelearningacasestudytoforecastthesecondwaveofcovid19hospitalizationsinlombardyitaly AT francescoimmorlano limitsofcompartmentalmodelsandnewopportunitiesformachinelearningacasestudytoforecastthesecondwaveofcovid19hospitalizationsinlombardyitaly AT francescodonato limitsofcompartmentalmodelsandnewopportunitiesformachinelearningacasestudytoforecastthesecondwaveofcovid19hospitalizationsinlombardyitaly AT giovannialoisio limitsofcompartmentalmodelsandnewopportunitiesformachinelearningacasestudytoforecastthesecondwaveofcovid19hospitalizationsinlombardyitaly |