Duke Center for Health Informatics: Machine Learning-Based Analytics of the Impact of the Covid-19 Pandemic on Alcohol Consumption Habit Changes Among United States Healthcare Workers
In this presentation, we explore the impact of the COVID-19 pandemic on changes in alcohol consumption habits among healthcare workers in the United States during the first wave of the pandemic. Using a variety of supervised and unsupervised machine learning methods and models, including decision trees, logistic regression, support vector machines, multilayer perceptrons, XGBoost, CatBoost, LightGBM, AdaBoost, Chi-Squared Test, mutual information, KModes clustering, and the synthetic minority oversampling technique, we analyzed mental health survey data from the University of Michigan Inter-University Consortium for Political and Social Research. Our objective was to investigate the connections between COVID-19-related adverse effects and shifts in alcohol consumption habits among healthcare workers. Our analysis of the supervised and unsupervised methods revealed that healthcare workers who had children at home during the first wave of the pandemic in the US consumed more alcohol. We also found that changes in work schedules due to the COVID-19 pandemic were linked to alterations in alcohol use habits. Additional factors, such as changes in food consumption, age, gender, geographical characteristics, changes in sleep habits, news consumption volume, and screen time, also significantly predicted increased alcohol use among healthcare workers in the United States.
Dr. Mostafa Rezapour is currently a Research Fellow at the Center for Biomedical Informatics at Wake Forest University School of Medicine. Under the mentorship of Dr. Metin Nafi Gurcan, as a Biomedical Informatics Research Fellow, he is employing innovative machine learning and statistical methods to address various health-related issues. Since September 2022, he has collaborated with Dr. Metin Nafi Gurcan on twelve health-related research articles.
Zoom Meeting link:
Meeting number (access code) 920 0552 7024, Meeting password: 128631