Machine learning models show stable predictors of healthcare financial vulnerability post-COVID-19

A new study analyzed Medical Expenditure Panel Survey data from 2019 and 2021 to assess healthcare financial vulnerability before and after the COVID-19 pandemic in the United States. Researchers defined high financial burden as out-of-pocket healthcare costs exceeding 10% of family income. The analysis, which employed logistic regression, random forest, and gradient boosting models, found that poverty status, insurance coverage, and prescription drug spending were key predictors of financial vulnerability. While disparities persisted, models trained on pre-pandemic data retained significant predictive power for post-pandemic data, indicating stable core predictors of financial strain. AI

RANK_REASON The item is an academic paper detailing a machine learning analysis of population health data. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• alphaXiv
• CatalyzeX Code Finder for Papers
• COVID-19
• DagsHub
• Gotit.pub
• gradient boosting
• Hugging Face
• logistic regression model
• Medical Expenditure Panel Survey
• random forest
• ScienceCast
• United States

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →