ABSTRACT
Objectives: This study investigated the risk factors of developing COVID Syndrome and identified potential disease profiles that may exist among those who have contracted COVID-19. Method(s): Data on 13,953 adults who had experienced COVID-19 at any time were analyzed from the 2022 US National Health and Wellness Survey. XGBoost binary classification with 10-fold cross-validation was used to predict long COVID among those who reported experiencing COVID-19 and to extract feature importance. Synthetic minority oversampling technique (SMOTE) was used to address class imbalance in the outcome variable. Variable selection was conducted based on SHAP values. Fifty variables including demographic characteristics, COVID-19 symptoms, comorbidities, and health characteristics were used in the final model. Parameters were tuned using AUC. Among the 2,665 respondents who were diagnosed with long COVID, k-medoids clustering with t-SNE dimensionality reduction was implemented to determine whether distinct symptom profiles exist. Average silhouette score was used to determine the optimal number of clusters. Result(s): The XGBoost binary classification for predicting long COVID among those with COVID-19 had an AUC of 0.9145, accuracy of 0.9072, sensitivity of 0.9630, specificity of 0.8328, and Brier score of 0.0928. The most important features in predicting long COVID were age, smoking habits, COVID-19 vaccination status, certain COVID-19 symptoms experienced, and certain comorbidities. Among those diagnosed with long COVID, the clustering analysis found nine unique clusters of symptoms. The cluster that experienced the most severe symptoms was older, female, lower income, lower vaccination rate, and had more comorbidities like asthma, chronic bronchitis, and allergies. Conclusion(s): In a broadly representative US adult population, XGBoost model identified a selection of risk factors for developing long COVID. K-medoids clustering identified clusters of patients that were at risk for developing severe symptoms.Copyright © 2023
ABSTRACT
Objectives: Health is distributed unequally by occupation (Ravesteijn,2013). This research aims to explore patient-reported outcomes by occupation profiles using the National Health and Wellness Survey (NHWS). Method(s): Data from the 2022 US NHWS included employed respondents at least 18 years of age with information on occupation profile, defined as 22 categories from the Bureau of Labor Statistics. Descriptive statistics were used to analyze respondent characteristics and outcomes such as COVID-19 diagnoses, healthcare resource use over the past six months, and work impairment as measured by the Work Productivity and Activity Impairment Questionnaire (WPAI). Result(s): A total of 35,789 respondents were employed and had occupation information. Respondents were predominantly white (62.0%) and male (53.9%). Sales and Related occupations had the greatest proportion of respondents reporting a COVID-19 diagnosis (16.1%) while Building and Grounds Cleaning and Maintenance had the lowest proportion (3.8%). Educational Instruction and Library had the most respondents reporting that they had received at least one dose of the COVID-19 vaccine (79.2%) while Farming, Fishing, and Forestry had the least respondents (52.9%). Life, Physical, and Social Science had the greatest COVID-19 vaccination rate over the past year (66.5%) while Farming, Fishing, and Forestry had the lowest (45.0%). Office and Administrative Support had the greatest proportion of respondents with a traditional healthcare provider visit (79.8%), but the lowest proportion with an emergency room (ER) visit (12.7%) or a hospitalization (8.1%). Farming, Fishing, and Forestry had the greatest proportion of respondents with an ER visit (41.6%) or hospitalization (41.6%). The greatest proportion of respondents with any overall work impairment or activity impairment was in Farming, Fishing, and Forestry (work: 91.1%, activity: 87.4%) while the lowest proportion was in Office and Administrative Support (work: 50.0%, activity: 53.3%). Conclusion(s): Certain occupation profiles consistently show higher impairment while others consistently show lower impairment.Copyright © 2023