JMIR Publications

ABSTRACT

Background:

Surveillance data are essential for public health initiatives; however, missing data is often a challenge, potentially introducing bias and impacting the accuracy of vaccine coverage assessments, particularly in addressing disparities.

Objective:

To evaluate the effectiveness of machine learning-based imputation methods, including Iterative Imputer and miceforest, in reconciling missing demographic data within large immunization datasets and compare their computational efficiency to multiple imputation by chained equations (MICE).

Methods:

We analyzed 2021-2022 flu vaccination and demographic data from the West Virginia Immunization Information System (N=2,302,036), where race (15%) and ethnicity (34%) were missing. MICE, Iterative Imputer, and miceforest were used to impute missing variables, generating 15 datasets each. Computational efficiency and the ability to preserve demographic distributions were assessed.

Results:

After imputation, an additional 780,339 observations were obtained compared to complete case analysis. MICE and miceforest best preserved the proportional distribution of demographics. Computational time varied, with MICE requiring 14 hours, Iterative Imputer 2 minutes, and miceforest 10 minutes for 15 imputations. Post-imputation estimates indicated a 0.87-18% reduction in flu vaccination coverage rates.

Conclusions:

Miceforest offers a flexible, fast, and iterative approach for imputing missing demographic data while preserving underlying distributions and mitigating bias. Cloud-based computing further enhances efficiency by offloading resource-intensive tasks, enabling parallel execution, and minimizing processing delays. These advancements support timely analyses, facilitate culturally responsive decision-making, and optimize public health performance.