What is the clinical evidence from this study?

Study design: Observational. Population: Colorectal cancer screening disparities (n=1500191). Intervention: Machine learning models to infer nativity and country of birth vs. Known foreign-born status. Primary outcome: Odds of colorectal cancer screening for US-born vs. foreign-born Latinos (OR 0.55, 95% CI 0.50-0.617).

What question did this study set out to answer?

This research aims to develop machine learning models to better understand Latino nativity and its implications for colorectal cancer screening disparities.

April 5, 2026

Abstract 7604: Disaggregating Latino nativity using machine learning on electronic health records: Insights for colorectal cancer screening disparities.

Resultado clave

Machine learning models accurately predicted Latino nativity (AUC 0.90), revealing that US-born Latinos had lower odds of colorectal cancer screening than foreign-born Latinos (OR 0.55; 95% CI 0.50-0.617).

Puntos clave

This research aims to develop machine learning models to better understand Latino nativity and its implications for colorectal cancer screening disparities.
Analyzed electronic health record data from over 1.5 million Latino patients.
Developed models to predict nativity using supervised learning algorithms.
Evaluated model performance with area under the receiver operating curve (AUC).
Used predicted nativity data to assess colorectal cancer screening disparities.
Only 11.6% of Latino patients self-reported their country of birth.
Prediction models achieved high AUC scores for nativity classification (up to 0.90).
US-born Latinos had lower odds of colorectal cancer screening compared to foreign-born counterparts (OR=0.55).
High concordance was observed between known and model-predicted screening odds ratios.

Diseño del estudio

Tipo

Observational (n=1,500,191)

Multicéntrico

Sí

PICO estructurado

Can machine learning models using electronic health records accurately infer Latino nativity and country of birth to evaluate colorectal cancer screening disparities?

Población

1,500,191 Latino patients receiving care at 1,876 community health centers across 28 states

Intervención

Machine learning models using electronic health record data, geocoded census-tract-level neighborhood composition data, and surname-based data to predict nativity and country of birth

Comparador

Known (self-reported) foreign-born status/nativity

Resultado

Model predictive performance (AUC) for nativity and country of birth, and colorectal cancer screening disparities (odds ratios)

Machine learning models can accurately infer Latino nativity and country of birth from electronic health records, providing a novel method to evaluate cancer disparities when self-reported data is missing.

Resultado numérico

Estimación del efecto: OR 0.55 (95% CI 0.50-0.617)

Resumen

Abstract Background: Advancements in colorectal cancer (CRC) prevention have not been equitable with studies showing reduced CRC screening rates and later-stage diagnoses among Latino patients. Latino subgroups vary in their cancer-related risk factors but also differ widely in their sociodemographic characteristics, migration histories, insurance coverage, and health care access patterns that may impact cancer prevention. However, large-scale datasets seldom contain granular data needed to study Latino subgroup-specific differences in cancer risk and outcomes. This study evaluated a machine learning approach designed to infer nativity and country of birth and advance cancer prevention research to better evaluate health equity among Latinos. Methods: We used comprehensive electronic health record data from 1,500,191 Latino patients receiving care at 1,876 community health centers across 28 states, along with geocoded census-tract-level neighborhood composition data, and surname-based data to develop machine learning models of Latino subgroups. Multiple supervised learning algorithms were trained and tested to predict nativity and country of birth. Model predictive performance was evaluated using area under the receiver operating curve (AUC). As a case example, we used model-predicted probabilities of Latino subgroups and nativity to evaluate CRC screening disparities by foreign-born status, both known and predicted. Results: Among 1,500,191 Latinos in the network, country of birth was self-reported by Latino patients for only 173,278 (11.6%), underscoring the challenges of using existing EHR data for studying Latino heterogeneity. Prediction models for nativity showed excellent discriminatory prediction performance across all groups (US-born vs. foreign-born: AUC=0.90; Mexican vs. non-Mexican: AUC=0.87; Guatemalan vs. non-Guatemalan: AUC=0.84; Cuban vs. non-Cuban: AUC=0.84). In our case example, using known foreign-born status of Latino patients, we observed that US-born Latinos had lower odds of CRC screening compared to foreign-born Latinos (OR=0.55, 95% CI=0.50-0.617). We observed high concordance between known and model-predicted estimates of CRC screening odds ratios. Conclusion: National calls for data disaggregation, including among Latinos, have numerous challenges. We developed and validated novel prediction models to infer Latino nativity and country of birth for use in population-based cancer disparities research. These methods present an opportunity to evaluate cancer disparities in data where Latino nativity is not collected. Citation Format: Miguel Marino, Jun Hwang, Jennifer A. Lucas, Wyatt Bensken, Matthew P. Banegas, John D. Heintzman. Disaggregating Latino nativity using machine learning on electronic health records: Insights for colorectal cancer screening disparities abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 7604.

Preguntar a la IA

Me gusta

Guardar