Adhera Health Research Reveals Bias in AI Models for Chronic Disease Care

Findings Highlight Urgent Need for Equitable Digital Health Solutions

SANTA CRUZ, CA, UNITED STATES, March 10, 2025 /EINPresswire.com/ -- A new study from Adhera Health, set to be presented this week at the American Medical Informatics Association (AMIA) Informatics Summit in Pittsburg, PA, reveals significant disparities in machine learning (ML) models used for clinical decision support in diabetes and heart disease management. The research, Disparate Model Performance and Stability in Machine Learning Clinical Support for Diabetes and Heart Diseases, highlights age- and sex-related biases in predictive accuracy, emphasizing the urgent need for more inclusive and equitable digital health solutions.

Analyzing data from over 25,000 individuals with chronic diseases, the study found that ML models favor younger and male patients, while older patients – who often present higher data complexity – experience inconsistent model performance. This exposes a critical gap in healthcare AI: representative training data alone does not guarantee equitable outcomes. To address this, the research introduces a novel analytical framework to assess model fairness beyond traditional performance metrics, providing a blueprint for more reliable and unbiased AI-driven clinical tools.

As a leader in family-centered digital health, Adhera Health is committed to ensuring AI-powered healthcare solutions work equitably for all patients. The company’s digital companion for pediatric chronic conditions—including Type 1 diabetes, Type 2 diabetes, and childhood obesity—leverages AI-driven personalization while addressing the social, behavioral, and systemic factors that impact health outcomes.

“We are excited to see these important discussions take center stage at AMIA,” said Ricardo C. Berrios, CEO and Co-Founder of Adhera Health and contributor to the published research. “This study underscores the need for digital health companies to prioritize fairness and inclusivity in AI-driven tools. By leveraging new research and ethical AI principles and ensuring that predictive models are designed to serve diverse populations, we can develop more effective digital health solutions that truly improve outcomes for all family members, not just those who are most commonly represented in training data.”

Join the Discussion at AMIA 2025
The study will be presented at AMIA Informatics Summit 2025 in Pittsburg, PA, on March 12, during Session S25 | Toward Implementation: Addressing Real-World Deployments from 1:30 PM – 3:00 PM at the Omni William Penn Hotel. Ioannis Bilionis, Data Scientist at Adhera Health, will discuss these findings and the path forward for building more equitable AI-driven healthcare solutions.

About Adhera Health
Adhera Health delivers deeply personalized, AI-powered digital health solutions for families navigating pediatric chronic conditions. Our platform integrates behavioral science, machine learning, and real-time analytics to provide holistic, data-driven support for caregivers, patients, and healthcare teams. By incorporating Social Determinants of Health (SDOH), we address the social, environmental, and economic factors that impact pediatric health outcomes. Trusted by Fortune 500 companies and leading health systems, Adhera Health is revolutionizing pediatric healthcare with sustainable, family-focused solutions.

Shannon McGinley
Adhera Health, Inc.
email us here
Visit us on social media:
LinkedIn
Facebook
YouTube