In the article “Identifying Predictors of Opioid Overdose Death at a Neighborhood-Level With Machine Learning” by Schell et al. (1), a reference to an article by Goin et al. (2) was mistakenly omitted from the Methods. The paper by Goin et al. provided an important model for the predictive modeling approach we took, which included a LASSO screening algorithm to reduce the variable set, followed by a random forest algorithm to rank the strength of predictors. In the Statistical analysis section on page 528, the first sentence of the second paragraph should read, “We next used the random forest algorithm for its ability to handle high-dimensional data with complex interactions and to rank covariates by variable importance, following the work of Goin et al.”
The authors regret the oversight and thank the American Journal of Epidemiology for giving us the opportunity to both cite and give proper credit to the study by Goin et al.
REFERENCES
- 1. Schell RC, Allen B, Goedel WC, et al. Identifying predictors of opioid overdose death at a neighborhood-level with machine learning. Am J Epidemiol. 2022;191(3):526–533. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 2. Goin DE, Rudolph KE, Ahern J. Predictors of firearm violence in urban communities: a machine-learning approach. Health Place. 2018;51:61–67. [DOI] [PMC free article] [PubMed] [Google Scholar]