Using a Multilingual AI Care Agent to Reduce Disparities in Colorectal Cancer Screening for Higher Fecal Immunochemical Test Adoption Among Spanish-Speaking Patients: Retrospective Analysis
Journal of Medical Internet Research · 2025-06-25 · 27 · e71211
DOI: 10.2196/71211 ↗At a glance
Journal article in Journal of Medical Internet Research, published online on 2025-06-25. Written by Meenesh Bhimani and 11 co-authors. Institution: Hippocratic AI, Palo Alto, CA, United States. Major MEDLINE topics: Artificial Intelligence, Colorectal Neoplasms, Early Detection of Cancer, Healthcare Disparities. Cited 9 times so far (Crossref); 35 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Colorectal cancer (CRC) screening rates remain disproportionately low among Hispanic and Latino populations compared to non-Hispanic White populations. While artificial intelligence (AI) shows promise in health care delivery, concerns exist that AI-based interventions may disadvantage non–English-speaking populations due to biases in development and deployment.
Objective
This study aimed to evaluate the effectiveness of a multilingual AI care agent in engaging Spanish-speaking patients for CRC screening compared to that with English-speaking patients.
Methods
This retrospective analysis examined an AI-powered outreach initiative at WellSpan Health in Pennsylvania and Maryland during September 2024. The study included 1878 patients (517 Spanish-speaking, 1361 English-speaking) eligible for CRC screening who lacked active web-based health profiles. A multilingual AI conversational agent conducted personalized telephone calls in the patient’s preferred language to provide education about CRC screening and facilitate fecal immunochemical test (FIT) kit requests. The primary outcome was the FIT test opt-in rate, with secondary outcomes including connect rates and call duration. Statistical analysis included descriptive statistics, bivariate comparisons, and multivariate logistic regression.
Results
Spanish-speaking patients demonstrated significantly higher engagement across all measures than English-speaking patients with respect to FIT test opt-in rates (18.2% vs 7.1%, P
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Hippocratic AI, Palo Alto, CA, United States.
- WellSpan Health, York, PA, United States.
- School of Population and Public Health, University of British Columbia, Vancouver, BC, Canada.
- University of California Davis Health, Davis, CA, United States.
ORCID profiles: Meenesh Bhimani, R Hal Baker, Markel Sanz Ausin, Gerald Meixiong, Rae Lasko, Mariska Raglow-Defranco, Alex Miller, Subhabrata Mukherjee, Saad Godil, Anderson Cook, Jonathan D Agnew, Ashish Atreja
Cite
APA
Bhimani, M., Baker, R. H., Ausin, M. S., Meixiong, G., Lasko, R., Raglow-Defranco, M., Miller, A., Mukherjee, S., Godil, S., Cook, A., Agnew, J. D., & Atreja, A. (2025). Using a Multilingual AI Care Agent to Reduce Disparities in Colorectal Cancer Screening for Higher Fecal Immunochemical Test Adoption Among Spanish-Speaking Patients: Retrospective Analysis. Journal of Medical Internet Research, 27, e71211. https://doi.org/10.2196/71211
Vancouver
Bhimani M, Baker RH, Ausin MS, Meixiong G, Lasko R, Raglow-Defranco M, et al. Using a Multilingual AI Care Agent to Reduce Disparities in Colorectal Cancer Screening for Higher Fecal Immunochemical Test Adoption Among Spanish-Speaking Patients: Retrospective Analysis. Journal of Medical Internet Research. 2025;27:e71211. doi:10.2196/71211
BibTeX
@article{Bhimani2025,
author = {Bhimani, Meenesh and Baker, R Hal and Ausin, Markel Sanz and Meixiong, Gerald and Lasko, Rae and Raglow-Defranco, Mariska and Miller, Alex and Mukherjee, Subhabrata and Godil, Saad and Cook, Anderson and Agnew, Jonathan D and Atreja, Ashish},
title = {Using a Multilingual AI Care Agent to Reduce Disparities in Colorectal Cancer Screening for Higher Fecal Immunochemical Test Adoption Among Spanish-Speaking Patients: Retrospective Analysis},
journal = {Journal of Medical Internet Research},
year = {2025},
volume = {27},
pages = {e71211},
doi = {10.2196/71211}
}
EUVIMED