Forecasting Model Based on Lifestyle Risk and Health Factors to Predict COVID-19 Severity
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Design and Settings
2.2. Study Area
2.3. Data Collection
2.3.1. Machine Learning Approach
2.3.2. Generalized Linear Model
- A random component that specifies the conditional distribution of the dependent variable composed by n independent observations in relation to the values of the independent variables of the model.
- A linear function of regressors
- A linearizing link function that converts the expectation of , in
2.3.3. Random Forest
- They are ease to tune;
- There are only two different parameters to set: the number of trees n and m the number of features sampled to grow each leaf within a tree;
- They are little affected by the overfitting problem;
- They can evaluate the importance of each feature in the model during the training phase;
- By means of out-of-bag procedure, the Random Forest algorithm computes an unbiased estimate of the generalization error.
2.3.4. Support Vector Machine
2.3.5. Feature Importance Procedure and Performance Metrics
3. Results
3.1. Regression Performances
3.2. Feature Importance
4. Discussion
Limitations and Strengths
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Promislow, D.E.L. A Geroscience Perspective on COVID-19 Mortality. J. Gerontol. Ser. A 2020, 75, e30–e33. [Google Scholar] [CrossRef] [Green Version]
- Leffler, C.T.; Ing, E.; Lykins, J.D.; Hogan, M.C.; McKeown, C.A.; Grzybowski, A. Association of Country-wide Coronavirus Mortality with Demographics, Testing, Lockdowns, and Public Wearing of Masks. Am. J. Trop. Med. Hyg. 2020, 103, 2400–2411. [Google Scholar] [CrossRef] [PubMed]
- Remuzzi, A.; Remuzzi, G. COVID-19 and Italy: What next? Lancet 2020, 395, 1225–1228. [Google Scholar] [CrossRef]
- Casti, E.; Consolandi, E. Italy into three parts: The space–time spread of contagion. Vaccines 2021, 9, 29–39. [Google Scholar] [CrossRef]
- Casti, E. Conclusions: Towards spatial vulnerability management for a new “happy” living. Mod. Cartogr. Ser. 2021, 9, 217–225. [Google Scholar] [CrossRef]
- Apolone, G.; Montomoli, E.; Manenti, A.; Boeri, M.; Sabia, F.; Hyseni, I.; Mazzini, L.; Martinuzzi, D.; Cantone, L.; Milanese, G.; et al. Unexpected detection of SARS-CoV-2 antibodies in the prepandemic period in Italy. Tumori J. 2021, 107, 446–451. [Google Scholar] [CrossRef] [PubMed]
- Amato, M.; Werba, J.P.; Frigerio, B.; Coggi, D.; Sansaro, D.; Ravani, A.; Ferrante, P.; Veglia, F.; Tremoli, E.; Baldassarre, D. Relationship between Influenza Vaccination Coverage Rate and COVID-19 Outbreak: An Italian Ecological Study. Vaccines 2020, 8, 535. [Google Scholar] [CrossRef] [PubMed]
- Zanettini, C.; Omar, M.; Dinalankara, W.; Imada, E.L.; Colantuoni, E.; Parmigiani, G.; Marchionni, L. Influenza Vaccination and COVID-19 Mortality in the USA: An Ecological Study. Vaccines 2021, 9, 427. [Google Scholar] [CrossRef] [PubMed]
- Conlon, A.; Ashur, C.; Washer, L.; Eagle, K.A.; Bowman, M.A.H. Impact of the influenza vaccine on COVID-19 infection rates and severity. Am. J. Infect. Control 2021, 49, 694–700. [Google Scholar] [CrossRef]
- Wilcox, C.R.; Islam, N.; Dambha-Miller, H. Association between influenza vaccination and hospitalisation or all-cause mortality in people with COVID-19: A retrospective cohort study. BMJ Open Respir. Res. 2021, 8, e000857. [Google Scholar] [CrossRef]
- Gao, C.; Zhao, Z.; Li, F.; Liu, J.-L.; Xu, H.; Zeng, Y.; Yang, L.; Chen, J.; Lu, X.; Wang, C.; et al. The impact of individual lifestyle and status on the acquisition of COVID-19: A case—Control study. PLoS ONE 2020, 15, e0241540. [Google Scholar] [CrossRef] [PubMed]
- Muhammad, S.J.; Siddiqui, R.; Khan, R.A. COVID-19: Is There a Link between Alcohol Abuse and SARS-CoV-2-Induced Severe Neurological Manifestations? ACS Pharmacol. Transl. Sci. 2021, 4, 1024–1025. [Google Scholar] [CrossRef]
- Yang, J.M.; Koh, H.Y.; Moon, S.Y.; Yoo, I.K.; Ha, E.K.; You, S.; Kim, S.Y.; Yon, D.K.; Lee, S.W. Allergic disorders and susceptibility to and severity of COVID-19: A nationwide cohort study. J. Allergy Clin. Immunol. 2020, 146, 790–798. [Google Scholar] [CrossRef]
- The Italian Civil Protection’s Data Repository. 2020. Available online: https://github.com/pcm-dpc/COVID-19/tree/master/dati-regioni (accessed on 23 November 2020).
- What Do We Know about the Risk of Dying from COVID-19? 2020. Available online: https://ourworldindata.org/covid-mortality-risk (accessed on 23 November 2020).
- Quanti Allergici ci Sono in Italia? Un po’ di Statistiche. 2016. Available online: https://www.allergipedia.it/2017/11/30/quanti-allergici-ci-sono-in-italia/ (accessed on 20 September 2020).
- Coperture della Vaccinazione Antinfluenzale in Italia. 2019. Available online: https://www.epicentro.iss.it/influenza/coperture-vaccinali (accessed on 10 September 2020).
- I dati per l’Italia Attività Fisica. 2018. Available online: https://www.epicentro.iss.it/passi/dati/attivita (accessed on 10 September 2020).
- Annuario Statistico Italiano 2019. Available online: https://www.istat.it/it/files/2019/12/Asi-2019.pdf (accessed on 1 September 2020).
- McCullagh, P.; Nelder, J.A. Generalized Linear Models, 2nd ed.; Chapman and Hall: London, UK, 1998. [Google Scholar]
- Hoffman, J.P. Generalized Linear Models: An Applied Approach; Pearson, Allyn, and Bacon: Boston, MA, USA, 2003. [Google Scholar]
- Müller, M. Generalized Linear Models; Gentle, J., Härdle, W., Mori, Y., Eds.; Handbook of Computational Statistics; Springer: Berlin/Heidelberg, Germany, 2012. [Google Scholar]
- Hardin, J.W.; Hilbe, J.M. Generalized Linear Models and Extensions; StataCorp LP.: College Station, TX, USA, 2007. [Google Scholar]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef] [Green Version]
- Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar] [CrossRef]
- Parveen, N.; Zaidi, S.; Danish, M. Support vector regression model for predicting the sorption capacity of lead (II). Perspect. Sci. 2016, 8, 629–631. [Google Scholar] [CrossRef] [Green Version]
- Vapnik, V.N.; Golowich, S.; Smola, A.J. Support vector method for function approximation, regression estimation and signal processing. Adv. Neural Inform. Process. Syst. 1996, 9, 281–287. [Google Scholar]
- Kuhn, H.W.; Tucker, A.W. Nonlinear programming. In Proceedings of the 2nd Berkeley Symposium, Berkeley, CA, USA, 31 July–12 August 1950; University of California Press: Berkeley, CA, USA, 1951; pp. 481–492. [Google Scholar]
- de Myttenaere, A.; Golden, B.; Le Grand, B.; Rossi, F. Mean Absolute Percentage Error for regression models. Neurocomputing 2016, 92, 38–48. [Google Scholar] [CrossRef] [Green Version]
- R Core Team. R: A Language and Environment for Statistical Computing; R Foundation for Statistical Computing: Vienna, Austria, 2020. [Google Scholar]
- Nicewander, R. Thirteen ways to look at the correlation coefficient. Am. Stat. 1988, 42, 59–66. [Google Scholar] [CrossRef]
- Casti, E.; Riggio, A. Atlante COVID-19 Geografie del Contago in Italia; A.Ge.I.: Roma, Italy, 2022. [Google Scholar]
- Marín-Hernández, D.; Schwartz, R.E.; Nixon, D.F. Epidemiological evidence for association between higher influenza vaccine uptake in the elderly and lower COVID-19 deaths in Italy. J. Med. Virol. 2021, 93, 64–65. [Google Scholar] [CrossRef]
- Tayar, E.; Abdeen, S.; Alah, M.A.; Chemaitelly, H.; Bougmiza, I.; Ayoub, H.H.; Kaleeckal, A.H.; Latif, A.N.; Shaik, R.M.; Al-Romaihi, H.E.; et al. Effectiveness of influenza vaccination against SARS-CoV-2 infection among healthcare workers in Qatar. medRxiv 2022. [Google Scholar] [CrossRef]
- Huang, K.; Lin, S.W.; Sheng, W.H.; Wang, C. Influenza vaccination and the risk of COVID-19 infection and severe illness in older adults in the United States. Sci. Rep. 2021, 11, 11025. [Google Scholar] [CrossRef] [PubMed]
- Bailey, K.L.; Samuelson, D.R.; Wyatt, T.A. Alcohol use disorder: A pre-existing condition for COVID-19? Alcohol 2020, 90, 11–17. [Google Scholar] [CrossRef] [PubMed]
- Zhang, J.J.; Dong, X.; Cao, Y.Y.; Yuan, Y.-D.; Yang, Y.-B.; Yan, Y.-Q.; Akdis, C.A.; Gao, Y. Clinical characteristics of 140 patients infected with SARS-CoV-2 in Wuhan, Chine. Allergy 2020, 75, 1730–1741. [Google Scholar] [CrossRef] [PubMed]
- Skevaki, C.; Karsonova, A.; Karaulov, A.; Xie, M.; Renz, H. Asthma-associated risk for COVID-19 development. J. Allergy Clin. Immunol. 2020, 146, 1295–1301. [Google Scholar] [CrossRef]
- Lee, S.C.; Son, K.J.; Han, C.H.; Jung, J.Y.; Park, S.C. Impact of comorbid asthma on severity of coronavirus disease (COVID-19). Sci. Rep. 2020, 10, 21805. [Google Scholar] [CrossRef]
- Susanna, C.; Gill, D.L. Genetic predisposition to allergic diseases is inversely associated with risk of COVID-19. Allergy 2021, 76, 1911–1913. [Google Scholar] [CrossRef]
- Wu, X.; Xu, Y.; Jin, L.; Wang, X.; Zhu, H.; Xie, Y. Association of Preexisting Asthma and Other Allergic Diseases with Mortality in COVID-19 Patients: A Systematic Review and Meta-Analysis. Front. Med. 2021, 8, 670744. [Google Scholar] [CrossRef]
Independent Feature | Explanation |
---|---|
Allergic subjects | percentage of people affected by chronic allergic diseases in 2016 in each Italian region [16]. |
Flu vaccinated | percentage of people over 65 years old vaccinated against the seasonal flu in each Italian region in 2019 [17]. |
Sedentary subjects | percentage of subjects, in each Italian region, that do not engage in any physical activity in their free time, nor do they do heavy work calculated from 2015 to 2018 [18]. |
Deaths respiratory system | number of deaths due to diseases of the respiratory system per inhabitants in each Italian region in 2016 [19]. |
Asthmatics | percentage of subjects suffering from chronic bronchitis and bronchial asthma in each Italian region in 2019 [19]. |
Alcohol consumers | percentage of subjects who claim they have a high daily alcohol consumption in each Italian region calculated from 2015 to 2018 [19]. |
Old-age index | ratio between the population aged 65 years and over and that under 15 in each Italian region in 2019 [19]. |
Population density | population density expressed in inhabitants per square kilometer in each Italian region in 2019. |
Passenger | data collected by each Italian national airport about the passengers who departed from or landed at that airport in 2018. |
Independent Feature | Mean | Standard Deviation | Median | 25th Percentile | 75th Percentile |
---|---|---|---|---|---|
Allergic subjects | |||||
Flu vaccinated | |||||
Sedentary subjects | |||||
Deaths respiratory system | |||||
Asthmatics | |||||
Alcohol consumers | |||||
Old-age index | |||||
Population density | |||||
Passenger | 8,841,969 | 1,412,266 | 3,193,386 | 223,436 | 8,893,672 |
Predicted Values | Regression Models | MAPE (±SD) | Adjusted (±SD) |
---|---|---|---|
Crude Positivity Rate | Random Forest | ||
Support Vector Machine | |||
Generalized Linear Model | |||
Crude Mortality Rate | Random Forest | ||
Support Vector Machine | |||
Generalized Linear Model |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Firza, N.; Monaco, A. Forecasting Model Based on Lifestyle Risk and Health Factors to Predict COVID-19 Severity. Int. J. Environ. Res. Public Health 2022, 19, 12538. https://doi.org/10.3390/ijerph191912538
Firza N, Monaco A. Forecasting Model Based on Lifestyle Risk and Health Factors to Predict COVID-19 Severity. International Journal of Environmental Research and Public Health. 2022; 19(19):12538. https://doi.org/10.3390/ijerph191912538
Chicago/Turabian StyleFirza, Najada, and Alfonso Monaco. 2022. "Forecasting Model Based on Lifestyle Risk and Health Factors to Predict COVID-19 Severity" International Journal of Environmental Research and Public Health 19, no. 19: 12538. https://doi.org/10.3390/ijerph191912538