SPLENDID incorporates continuous genetic ancestry in biobank-scale data to improve polygenic risk prediction across diverse populations.

SPLENDID improves polygenic risk prediction accuracy across diverse populations by modeling genetic ancestry as a continuum without requiring ancestry labels, outperforming existing methods.

• Why it matters: Accurate disease risk prediction is essential for personalized medicine, but current polygenic risk scores often perform poorly in non-European and admixed populations, contributing to health disparities.
• What they did: The authors developed SPLENDID, a penalized regression framework that uses large-scale individual-level data to incorporate continuous genetic ancestry, tested on datasets with over 224,000 and 340,000 participants.
• The result: SPLENDID significantly enhanced prediction accuracy, especially for underrepresented and admixed groups, enabling fairer clinical application and reducing disparities in genetic risk assessment.