Predicting New Daily COVID-19 Cases and Deaths Using Search Engine Query Data in South Korea From 2020 to 2021: Infodemiology Study

Abstract

Background Given the ongoing COVID-19 pandemic situation, accurate predictions could greatly help in the health resource management for future waves. However, as a new entity, COVID-19’s disease dynamics seemed difficult to predict. External factors, such as internet search data, need to be included in the models to increase their accuracy. However, it remains unclear whether incorporating online search volumes into models leads to better predictive performances for long-term prediction. Objective The aim of this study was to analyze whether search engine query data are important variables that should be included in the models predicting new daily COVID-19 cases and deaths in short- and long-term periods. Methods We used country-level case-related data, NAVER search volumes, and mobility data obtained from Google and Apple for the period of January 20, 2020, to July 31, 2021, in South Korea. Data were aggregated into four subsets: 3, 6, 12, and 18 months after the first case was reported. The first 80% of the data in all subsets were used as the training set, and the remaining data served as the test set. Generalized linear models (GLMs) with normal, Poisson, and negative binomial distribution were developed, along with linear regression (LR) models with lasso, adaptive lasso, and elastic net regularization. Root mean square error values were defined as a loss function and were used to assess the performance of the models. All analyses and visualizations were conducted in SAS Studio, which is part of the SAS OnDemand for Academics. Results GLMs with different types of distribution functions may have been beneficial in predicting new daily COVID-19 cases and deaths in the early stages of the outbreak. Over longer periods, as the distribution of cases and deaths became more normally distributed, LR models with regularization may have outperformed the GLMs. This study also found that models performed better when predicting new daily deaths compared to new daily cases. In addition, an evaluation of feature effects in the models showed that NAVER search volumes were useful variables in predicting new daily COVID-19 cases, particularly in the first 6 months of the outbreak. Searches related to logistical needs, particularly for “thermometer” and “mask strap,” showed higher feature effects in that period. For longer prediction periods, NAVER search volumes were still found to constitute an important variable, although with a lower feature effect. This finding suggests that search term use should be considered to maintain the predictive performance of models. Conclusions NAVER search volumes were important variables in short- and long-term prediction, with higher feature effects for predicting new daily COVID-19 cases in the first 6 months of the outbreak. Similar results were also found for death predictions.

The Apple Mobility Trends Data in Human Mobility Patterns during Restrictions and Prediction of COVID-19: A Systematic Review and Meta-Analysis

“…Several studies found that lockdowns led to a significant decrease in the number of new cases. The lockdowns were most effective when combined with other measures, such as temperature checks, mask-wearing, and contact tracing [ 74 ]. It is important to note that the lockdowns were lifted after some time, and the number of new cases began to rise again.…”

Explanation of hand, foot, and mouth disease cases in Japan using Google Trends before and during the COVID-19: infodemiology study

“…Researchers have also investigated public interest and information-seeking behaviors in chronic obstructive pulmonary disease (COPD) [ 28 ], cancer [ 29 , 30 ], bariatric surgery [ 31 ], kidney stone surgery [ 32 ], and suicide [ 33 ]. During the COVID-19 pandemic, similar studies using Google Trends search data were conducted to predict COVID-19 infectious cases [ 34 , 35 ], explore public attitudes toward vaccination [ 36 – 38 ], identify symptoms caused by pandemics [ 39 – 41 ], and assess affected medical services [ 42 – 44 ]. The above studies indicate that Google Trends can assist in gaining a better understanding and analysis of health information-seeking behavior.…”

Explanation of Hand, Foot, and Mouth Disease Cases in Japan Using Google Trends Before and During the COVID-19: Infodemiology Study

“…Researchers have also investigated public interest and information-seeking behavior in chronic obstructive pulmonary disease (COPD) (Boehm et al, 2019), cancer (Schootman et al, 2015; Phillips et al, 2018), bariatric surgery (Linkov et al, 2014), kidney stone surgery (Dreher et al, 2018), and suicide (Taira et al, 2021). During the COVID-19 pandemic, similar studies using Internet search data were conducted to predict COVID-19 infectious cases (Husnayain et al, 2021; Higgins et al, 2020), explore public attitudes toward vaccination (Pullan and Dey, 2021; Diaz et al, 2021; An et al, 2021), identify symptoms caused by pandemics (Han et al, 2022; Kardeş et al, 2022; Knipe et al, 2021), and assess affected medical services (Cohen et al, 2021; Akpan et al, 2021; Adelhoefer et al, 2021). The above studies indicate that Google Trends could assist in gaining a better understanding and analysis of health information-seeking behavior.…”

“…Researchers have also investigated public interest and information-seeking behavior in chronic obstructive pulmonary disease (COPD) [28], cancer [29,30], bariatric surgery [31], kidney stone surgery [32], and suicide [33]. During the COVID-19 pandemic, similar studies using Google Trends search data were conducted to predict COVID-19 infectious cases [34,35], explore public attitudes toward vaccination [36][37][38], identify symptoms caused by pandemics [39][40][41], and assess affected medical services [42][43][44]. The above studies indicate that Google Trends could assist in gaining a better understanding and analysis of health information-seeking behavior.…”