Abstract
During 2020, the infection rate of COVID-19 has been investigated by many scholars from different research fields. In this context, reliable and interpretable forecasts of disease incidents are a vital tool for policymakers to manage healthcare resources. In this context, several experts have called for the necessity to account for human mobility to explain the spread of COVID-19. Existing approaches often apply standard models of the respective research field, frequently restricting modeling possibilities. For instance, most statistical or epidemiological models cannot directly incorporate unstructured data sources, including relational data that may encode human mobility. In contrast, machine learning approaches may yield better predictions by exploiting these data structures yet lack intuitive interpretability as they are often categorized as black-box models. We propose a combination of both research directions and present a multimodal learning framework that amalgamates statistical regression and machine learning models for predicting local COVID-19 cases in Germany. Results and implications: the novel approach introduced enables the use of a richer collection of data types, including mobility flows and colocation probabilities, and yields the lowest mean squared error scores throughout the observational period in the reported benchmark study. The results corroborate that during most of the observational period more dispersed meeting patterns and a lower percentage of people staying put are associated with higher infection rates. Moreover, the analysis underpins the necessity of including mobility data and showcases the flexibility and interpretability of the proposed approach.
Highlights
During 2020, the infection rate of COVID-19 has been investigated by many scholars from different research fields
We argue that data science and machine learning can provide urgently needed tools to doctors and policymakers in various applications
Allowing for the inclusion of novel data modalities in some of the more traditional approaches may further improve models. This was highlighted in previous works[16] that included non-standard data sources, e.g., aggregated contact patterns obtained from mobile phones or behavioral data, into the analysis to help in understanding and fighting COVID-19
Summary
The results indicate a notable improvement over existing approaches, which we achieved by incorporating the network data. The provided findings highlight the need for regularization and showcase how common ML approaches can not adequately capture the autoregressive term, which, in turn, proved to be essential for the forecast. Working only with mobility data from one source, i.e., Facebook, might affect the findings due to an unknown selection bias. To minimize such a bias, we restricted the analysis to the younger and mid-aged cohorts. [19], investigate the representativeness of the Facebook data and compare the information with the mobility data from other providers, such as Google and Apple, and conclude that the data source adequately represents the spatial distribution of people and is consistent with the other data sources. Additional data sources could be used, possibly of higher granularity, e.g., daily instead of weekly infection count, to provide faster and more accurate insights into the pandemic
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
