The explainable AI dilemma under knowledge imbalance in specialist AI for glaucoma referrals in primary care - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Navigating the Explainable AI Challenge Amid Knowledge Disparities in Specialist AI for Glaucoma Referrals in Primary Care Settings

  • By

  • Catalina Gomez

  • Ruolin Wang

  • Katharina Breininger

  • Corinne Casey

  • Chris Bradley

  • Mitchell Pavlak

  • Alex Pham

  • Jithin Yohannan

  • Mathias Unberath

  • November 20, 2025

Share

  • 1

    Primary eye care providers rely on clinical experience for glaucoma referrals, but specialized AI can enhance decision-making with data-driven insights.

  • 2

    AI models developed for glaucoma referrals achieved higher accuracy in identifying urgent cases, but human-AI teams still underperformed compared to AI alone.

  • 3

    Explanations provided by AI did not improve referral accuracy and introduced uncertainty, leading to over-reliance on incorrect AI recommendations.

  • 4

    Post-hoc explanations contributed to anchoring bias, causing participants to align more closely with AI referrals than their own clinical judgment.

  • 5

    Challenges remain in designing effective AI support mechanisms that enhance human decision-making while preserving clinician autonomy.

Original Source(s)

The explainable AI dilemma under knowledge imbalance in specialist AI for glaucoma referrals in primary care

  • by Catalina Gomez, Ruolin Wang, Katharina Breininger, Corinne Casey, Chris Bradley, Mitchell Pavlak, Alex Pham, Jithin Yohannan, Mathias Unberath

  • November 20, 2025

Related Content

HHS Seeks Public Input to Improve Access to Deceased Donor Islet Cell Treatments

Knee sepsis may be rare across tibial fracture care

Investigators documented acute knee sepsis after both intra- and extra-articular nailing of open tibial shaft fractures.

DEXIS Announces Updates Across Dental Imaging Portfolio

New capabilities span X-ray and CBCT systems, intraoral scanning, diagnostic software, cloud services and education.