Estimating the adjusted fatality rate of COVID-19 in Iran using the fused lasso approach in distributed lag models

Document Type : Original article

Authors

1 PhD Candidate in Biostatistics, Department of Epidemiology and Biostatistics, School of Health, Mashhad University of Medical Sciences, Mashhad, Iran.

2 Associate Professor of Biostatistics, Department of Epidemiology and Biostatistics, School of Health, Mashhad University of Medical Sciences, Mashhad, Iran.

3 Associate Professor of Biostatistics, Department of Medical Informatics, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.

10.22038/nnj.2024.80983.1455

Abstract

Background and Aims: Distributed lag models can estimate disease fatality in long-term epidemics by adjusting the delayed effect of the number of daily cases. The fused lasso approach is a regularization method that considers the inherent order between features, such as the time order between the number of daily hospitalizations, and can remove the effect of collinearity between features by placing a penalty in the estimation of the parameters of the distributed lag model. Therefore, this study has been carried out by estimating the adjusted mortality of COVID-19 using the lasso regularization approach in distributed lag models.
Materials and Methods: The data relating to the COVID-19 disease (the number of deaths and the number of people identified daily) in Iran from the middle of February 1398 to the middle of May 1402 was prepared from the OurWorldinData database and using R4. 3.3 the distributed lag model was fitted with the fused lasso method.
Results: The adjusted fatality rate of COVID-19 in Iran is 1.72%, with five days delay between new cases diagnosis and deaths. The highest fractions were on the first day and the fifth day after detection.
Conclusion: Using the fused lasso method improved the significance of the coefficients in the distributed lag model. The short time from detection to death in Iran compared to other countries is a sign of poor screening and a lack of adequate equipment and services for the emergency treatment of patients.

Keywords

References

 
[1].    Hasanzadeh J, Amiresmaili M, Moosazadeh M, Najafi F, Moradinazar M. Implementing a weather-based early warning system to prevent traffic accidents fatalities. World Appl Sci J. 2013;24(1):113-7.
[2].    Hasanzadeh J, Najafi F, Moradinazar M. How to choose an appropriate model for time series data. Iranian Journal of Epidemiology. 2015;11(1):94-102.
[3].    Schwartz J. The distributed lag between air pollution and daily deaths. Epidemiology. 2000;11(3):320-6.
[4].    Almon S. The distributed lag between capital appropriations and expenditures. Econometrica: Journal of the Econometric Society. 1965:178-96.
[5].    Rastaghi S, Shark NA, Saki A. Application of distribution-delay models to estimating the hospitalized mortality rate of covid-19 according to delay effect of hospitalizations counts. Journal of Biostatistics and Epidemiology. 2021.
[6].    Hadianfar A, Rastaghi S, Tabesh H, Saki A. Application of distributed lag models and spatial analysis for comparing the performance of the COVID-19 control decisions in European countries. Scientific Reports. 2023;13(1):17466.
[7].    Gasparrini A, Armstrong B, Kenward MG. Distributed lag non‐linear models. Statistics in medicine. 2010;29(21):2224-34.
[8].    Shadrokh A, Khadembashiri Z, Yarmohammadi M. Regression Modeling Via T-Lasso Bayesian Method. Journal of Advanced Mathematical Modeling. 2021;11(2):365-81.
[9].    Hoerl AE, Kennard RW. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics. 1970;12(1):55-67.
[10].  Ranstam J, Cook J. LASSO regression. Journal of British Surgery. 2018;105(10):1348-.
[11].  Lange KL, Little RJ, Taylor JM. Robust statistical modeling using the t distribution. Journal of the American Statistical Association. 1989;84(408):881-96.
[12].  Tang L, Song PX. Fused lasso approach in regression coefficients clustering: learning parameter heterogeneity in data integration. The Journal of Machine Learning Research. 2016;17(1):3915-37.
[13].  Leek JT, Storey JD. Capturing heterogeneity in gene expression studies by surrogate variable analysis. PLoS genetics. 2007;3(9):e161.
[14].  Liu D, Liu RY, Xie M. Multivariate meta-analysis of heterogeneous studies using only summary statistics: efficiency and robustness. Journal of the American Statistical Association. 2015;110(509):326-40.
[15].  Shekelle PG, Hardy ML, Morton SC, Maglione M, Mojica WA, Suttorp MJ, et al. Efficacy and safety of ephedra and ephedrine for weight loss and athletic performance: a meta-analysis. Jama. 2003;289(12):1537-45.
[16].  Jang W, Lim J, Lazar NA, Loh JM, Yu D. Some properties of generalized fused lasso and its applications to high dimensional data. Journal of the Korean Statistical Society. 2015;44(3):352-65.
[17].  Tibshirani R, Wang P. Spatial smoothing and hot spot detection for CGH data using the fused lasso. Biostatistics. 2008;9(1):18-29.
[18].  Hadianfar A, Rastaghi S, Saki A. Evaluation of the Relative Risk of Covid-19 Mortality Based on the Number of Hospitalizations in Iran using a Log-Linear Distributed Lag Model. Iranian Journal of Epidemiology. 2021;16(5):20-8.
[19].  Jung J, Roh J, Park C-S. Abstract PO-079: Fused LASSO application for gastric cancer image segmentation. Clinical Cancer Research. 2021;27(5_Supplement):PO-079-PO-.
[20].  Guglielmi N, Iacomini E, Viguerie A. Identification of time delays in COVID-19 data. Epidemiologic Methods. 2023;12(1):20220117.
[21].  Cobre AdF, Böger B, Fachi MM, Vilhena RdO, Domingos EL, Tonin FS, Pontarolo R. Risk factors associated with delay in diagnosis and mortality in patients with COVID-19 in the city of Rio de Janeiro, Brazil. Ciencia & saude coletiva. 2020;25:4131-40.

Files

Share

How to cite

Statistics