Abstract: Artificial Intelligence And Disparities In Pediatric Type 1 Diabetes Care: Predictive Model Performance Varies By Age And Sex

Mother and son having fun in public park, eating ice cream

Authors: Diana Ferro, David D. Williams, Susana R. Patton, Ryan McDonough, Mark A. Clements

We can use predictive models to intensify care among youth with type 1 diabetes (T1D) who are predicted to experience a rise in hemoglobin A1c (HbA1c), yet little is known about the impact of age and sex on the performance of machine learning-based models. We evaluated the performance of a model to predict 90-day change in HbA1c by sex and age. Method: We applied supervised machine learning (random forest + natural language processing with 305 data features) to electronic health record data from May 2013 to December 2018 for 1725 youth aged 1-20 years with T1D seen at a Midwest US diabetes center with 11 sites. Eligible encounters included those with an HbA1c measurement >70 days (median 106 days; IQR 94,132) after baseline, with resampling of youth who had multiple eligible encounters. We evaluated model performance characteristics (sensitivity, positive predicted values [PPV]) by age and sex to evaluate for disparities in performance. Results: Median youth age was 14.3 years (IQR=10.9, 16.5), with 50.9% female and 17% non-Hispanic, non- white. Sensitivity and PPV of the model for predicting HbA1c rise of ≥0.3% were 12.4% and 47.2%, in the overall cohort, 13.8% and 51.4% in males, and 10.9% and 0.4% (p<0.05) in females, respectively. Across age strata, sensitivity for males vs females was 12.7% vs 13% and 14.9% vs 10.9% in youth 0-9 and 9-18 years old, respectively. PPV for males vs females was 41% vs 36% (p<0.05), 54% vs 43%, and 33.3% vs 57.1% (p<0.05) in youth 0-9 and 9-18 respectively. Conclusions: Predictive models used in clinical practice should be examined for disparities in performance across groups. Our present predictive model exhibits disparities in performance characteristics by sex and age. Whether the model performs differently among groups defined by race, ethnicity, socioeconomic status, and treatment modalities remains to be determined; such disparities have the potential to exacerbate disparities in healthcare delivery.

Subscribe To Our Newsletter

Subscribe to receive news and updates.

Share This Research

Share on facebook
Share on twitter
Share on linkedin
Share on email

More To Explore

February 2022

Background: where we started In 2020, we launched a new effort called the Rising T1DE Alliance (formerly known as the Rapid Learning Lab), funded by

Do You Want To Join the Alliance?

Get exclusive access by joining our newsletter

business partners in a circle with wrists held
Skip to content