Age-Related Changes in Clinical Presentation of Covid-19: the EPICOVID19 Web-Based Survey

Abstract

Background: The influence of aging and multimorbidity on Covid-19 clinical presentation is still unclear.

Objectives: We investigated whether the association between symptoms (or cluster of symptoms) and positive SARS-CoV-2 nasopharyngeal swab (NPS) was different according to patients' age and presence of multimorbidity.

Methods: The study included 6680 participants in the EPICOVID19 web-based survey, who reported information about symptoms from February to June 2020 and who underwent at least one NPS. Symptom clusters were identified through hierarchical cluster analysis. The associations between symptoms (and clusters of symptoms) and positive NPS were investigated through multivariable binary logistic regression in the sample stratified by age (<65 vs ≥65 years) and number of chronic diseases (0 vs 1 vs ≥2).

Results: The direct association between taste/smell disorders and positive NPS was weaker in older and multimorbid patients than in their younger and healthier counterparts. Having reported no symptoms reduced the chance of positive NPS by 86% in younger (95%CI: 0.11-0.18), and by 46% in older participants (95%CI: 0.37-0.79). Of the four symptom clusters identified (asymptomatic, generic, flu-like, and combined generic and flu-like symptoms), those associated with a higher probability of SARS-CoV-2 infection were the flu-like for older people, and the combined generic and flu-like for the younger ones.

Conclusions: Older age and pre-existing chronic diseases may influence the clinical presentation of Covid-19. Symptoms at disease onset tend to aggregate differently by age. New diagnostic algorithms considering age and chronic conditions may ease Covid-19 diagnosis and optimize health resources allocation.

Trial registration: NCT04471701 (ClinicalTrials.gov).

Keywords: 95% confidence intervals - CIs; Aged; COVID-19; Differential Diagnosis; European Union General Data Protection Regulation - EU GDPR; Multimorbidity Abbreviations SARS-CoV-2 nasopharyngeal swab - NPS; Odds ratios – OR; Symptom Cluster.

Fig. 1

Association between symptoms and positive nasopharyngeal swab test in young and older people. Notes. Odds ratios derive from a binary logistic regression adjusted for age, sex, smoking habit, number of chronic diseases (0 vs 1 vs 2+), cardiovascular diseases, respiratory diseases, diabetes, depressive/anxiety disorders, use of steroids, use of anti-inflammatory drugs, month at symptoms onset, and geographical area. Except for analysis on “no symptoms”, all symptoms were included in the model. The outcome was having had a positive nasopharyngeal swab test.

Fig. 2

Dendrogram of symptom clusters reported among the 6680 respondents. Notes. Fever, smell or taste disorders, cough, sore throat/rhinorrhea, myalgia, headache, and gastrointestinal disturbances defined the flu-like symptoms cluster. Shortness of breath, chest pain, heart palpitations, and conjunctivitis defined the generic symptoms cluster.

Fig. 3

Frequency of positive SARS-CoV-2 nasopharyngeal swab test in young and older individuals stratified by symptom cluster. Abbreviations: NPS, nasopharyngeal swab.

Fig. 4

Logistic regression for the association between symptom clusters and positive nasopharyngeal swab test. Notes. Odds ratios derive from an unadjusted binary logistic regression. Symptom clusters (vs all the others) were considered separately as exposure. The outcome was having had a positive nasopharyngeal swab test.