RESUMO
BACKGROUND: To address the current COVID-19 and any future pandemic, we need robust, real-time, and population-scale collection and analysis of data. Rapid and comprehensive knowledge on the trends in reported symptoms in populations provides an earlier window into the progression of viral spread, and helps to predict the needs and timing of professional health care. OBJECTIVE: The objective of this study was to use a Conformité Européenne (CE)-marked medical online symptom checker service, Omaolo, and validate the data against the national demand for COVID-19-related care to predict the pandemic progression in Finland. METHODS: Our data comprised real-time Omaolo COVID-19 symptom checker responses (414,477 in total) and daily admission counts in nationwide inpatient and outpatient registers provided by the Finnish Institute for Health and Welfare from March 16 to June 15, 2020 (the first wave of the pandemic in Finland). The symptom checker responses provide self-triage information input to a medically qualified algorithm that produces a personalized probability of having COVID-19, and provides graded recommendations for further actions. We trained linear regression and extreme gradient boosting (XGBoost) models together with F-score and mutual information feature preselectors to predict the admissions once a week, 1 week in advance. RESULTS: Our models reached a mean absolute percentage error between 24.2% and 36.4% in predicting the national daily patient admissions. The best result was achieved by combining both Omaolo and historical patient admission counts. Our best predictor was linear regression with mutual information as the feature preselector. CONCLUSIONS: Accurate short-term predictions of COVID-19 patient admissions can be made, and both symptom check questionnaires and daily admissions data contribute to the accuracy of the predictions. Thus, symptom checkers can be used to estimate the progression of the pandemic, which can be considered when predicting the health care burden in a future pandemic.
RESUMO
Research on health inequalities shows considerable variation in health by socioeconomic position regardless of measurement. Income level is among the most commonly used indicators to measure the social gradient in health. The income gradient in health may, however, vary according to what aspect of health is studied but equally it may depend on how income is measured. The traditional approach of measuring income is to use household income and to modify it with consumption needs and size of the household. Our hypothesis was that the traditional picture of the income-health gradient becomes more nuanced when we use different equalization scales for household incomes than the most often used modified OECD equalization scale. More technically, we expected the steepness of the income-health gradient to change when the equivalence scale for adjusting household size and composition is altered. The data were Finnish cross-sectional 2017 data from EU-SILC (N = 9406). The primary measures were perceived health status and total household disposable annual income by household type. Ordered probit estimation using Stata package was applied to solving the function between health and income controlling for age, age-squared and gender. Respondents' health status associated with their household type similarly to the association between personal income and household type. Those living in a single household tend to report poorer health but also tend to have lower personal income. Our main finding was that the health-income gradient becomes steeper with the larger equivalence scales, i.e., larger scale relativities, which assume bigger consumption needs for additional household members. One should be more aware of the fact that when household consumption is adjusted with conventional equivalence scales, other income-related aspects beyond consumption potential - such as social status, economic security - are also adjusted for.