A comprehensive analysis of alcohol-attributed mortality in the United States

Alcohol related mortality remains an important public health challenge in the United States (US), with patterns that vary substantially by demographics and geography. The objective of this study is to provide a thorough analysis using state-of-the-art data mining and machine learning techniques on alcohol attributable deaths in the U.S. from 2015–2019. Driven by the urgent need for specific interventions, we used regression models followed with ensemble techniques (XGBoost) to forecast mortality rates utilizing parameters such as age, geographic region of residence, manner of death and consumption patterns. Results in accordance with empirical CDC mortality data, XGBoost outperformed all other models in predicting age-based (R2 = 0.98) and cause-specific (R2 = 0.96). Geographic patterns show that California, Texas and Florida were particularly hot spots for alcohol versus suicide related deaths. The study also found demographic disparities, with older adults being more at risk. Major research contributions are the good predictability of news on general mortality and due to age, selected causes of death as well identification these regional patterns. These findings are invaluable in shaping targeted public health initiatives and policies to address alcohol-related harm. The adoption of sophisticated predictive modelling methodology in this study contributes significantly to the field by providing an empirically driven process for investigating and confronting alcohol-attributable death burden within the U.S.