Characterizing and Understanding Temporal Effects in COVID-19 Data

Bruno Barbosa Miranda Paiva, Polianna Delfino Pereira, Virginia Mara Reis Gomes, Maira Viana Rego Souza Silva, Cláudio Valiense, Milena Soriano Marcolino, Marcos André Gonçalves
Proceedings of the 1st Workshop on Healthcare AI and COVID-19, ICML 2022, PMLR 184:33-40, 2022.

Abstract

Since the global outbreak of the coronavirus 2019 pandemic, hundreds of works have been published, analyzing and modeling multiple aspects of the disease. Several of them venture into predictive and modeling tasks, such as mortality prediction and patient severity scoring, using machine-learning (ML) algorithms. An important limitation for most of these works is the fact that they do not consider the multiple temporal aspects of this pandemic, especially regarding disease profile and distributional changes over the months. Such temporal effects are mostly due to multiple interactions between different and novel viral strains, combined with mass vaccination campaigns targeting different groups or patterns (e.g., prioritizing older individuals and those with comorbidity first) and availability of different vaccines. These temporal effects result in impaired model effectiveness and classification errors. In this paper, using a large dataset with over 10,000 patients from 39 hospitals in Brazil admitted during a period of more than 20 months, we provide an overview of the multiple forms of temporal drift that happened during the pandemic and the magnitude of their effects on model effectiveness. Our analyses encompass changes in the severely ill patients’ profile as well as how mortality rates have changed over time. We also investigate how the importance of different predictive variables change and shift over time.

Cite this Paper


BibTeX
@InProceedings{pmlr-v184-paiva22a, title = {Characterizing and Understanding Temporal Effects in COVID-19 Data}, author = {Paiva, Bruno Barbosa Miranda and Pereira, Polianna Delfino and Gomes, Virginia Mara Reis and Silva, Maira Viana Rego Souza and Valiense, Cl\'audio and Marcolino, Milena Soriano and Gon\c{c}alves, Marcos Andr\'e}, booktitle = {Proceedings of the 1st Workshop on Healthcare AI and COVID-19, ICML 2022}, pages = {33--40}, year = {2022}, editor = {Xu, Peng and Zhu, Tingting and Zhu, Pengkai and Clifton, David A. and Belgrave, Danielle and Zhang, Yuanting}, volume = {184}, series = {Proceedings of Machine Learning Research}, month = {22 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v184/paiva22a/paiva22a.pdf}, url = {https://proceedings.mlr.press/v184/paiva22a.html}, abstract = {Since the global outbreak of the coronavirus 2019 pandemic, hundreds of works have been published, analyzing and modeling multiple aspects of the disease. Several of them venture into predictive and modeling tasks, such as mortality prediction and patient severity scoring, using machine-learning (ML) algorithms. An important limitation for most of these works is the fact that they do not consider the multiple temporal aspects of this pandemic, especially regarding disease profile and distributional changes over the months. Such temporal effects are mostly due to multiple interactions between different and novel viral strains, combined with mass vaccination campaigns targeting different groups or patterns (e.g., prioritizing older individuals and those with comorbidity first) and availability of different vaccines. These temporal effects result in impaired model effectiveness and classification errors. In this paper, using a large dataset with over 10,000 patients from 39 hospitals in Brazil admitted during a period of more than 20 months, we provide an overview of the multiple forms of temporal drift that happened during the pandemic and the magnitude of their effects on model effectiveness. Our analyses encompass changes in the severely ill patients’ profile as well as how mortality rates have changed over time. We also investigate how the importance of different predictive variables change and shift over time.} }
Endnote
%0 Conference Paper %T Characterizing and Understanding Temporal Effects in COVID-19 Data %A Bruno Barbosa Miranda Paiva %A Polianna Delfino Pereira %A Virginia Mara Reis Gomes %A Maira Viana Rego Souza Silva %A Cláudio Valiense %A Milena Soriano Marcolino %A Marcos André Gonçalves %B Proceedings of the 1st Workshop on Healthcare AI and COVID-19, ICML 2022 %C Proceedings of Machine Learning Research %D 2022 %E Peng Xu %E Tingting Zhu %E Pengkai Zhu %E David A. Clifton %E Danielle Belgrave %E Yuanting Zhang %F pmlr-v184-paiva22a %I PMLR %P 33--40 %U https://proceedings.mlr.press/v184/paiva22a.html %V 184 %X Since the global outbreak of the coronavirus 2019 pandemic, hundreds of works have been published, analyzing and modeling multiple aspects of the disease. Several of them venture into predictive and modeling tasks, such as mortality prediction and patient severity scoring, using machine-learning (ML) algorithms. An important limitation for most of these works is the fact that they do not consider the multiple temporal aspects of this pandemic, especially regarding disease profile and distributional changes over the months. Such temporal effects are mostly due to multiple interactions between different and novel viral strains, combined with mass vaccination campaigns targeting different groups or patterns (e.g., prioritizing older individuals and those with comorbidity first) and availability of different vaccines. These temporal effects result in impaired model effectiveness and classification errors. In this paper, using a large dataset with over 10,000 patients from 39 hospitals in Brazil admitted during a period of more than 20 months, we provide an overview of the multiple forms of temporal drift that happened during the pandemic and the magnitude of their effects on model effectiveness. Our analyses encompass changes in the severely ill patients’ profile as well as how mortality rates have changed over time. We also investigate how the importance of different predictive variables change and shift over time.
APA
Paiva, B.B.M., Pereira, P.D., Gomes, V.M.R., Silva, M.V.R.S., Valiense, C., Marcolino, M.S. & Gonçalves, M.A.. (2022). Characterizing and Understanding Temporal Effects in COVID-19 Data. Proceedings of the 1st Workshop on Healthcare AI and COVID-19, ICML 2022, in Proceedings of Machine Learning Research 184:33-40 Available from https://proceedings.mlr.press/v184/paiva22a.html.

Related Material