Trainee Rounds: Wanjin Li and Yuxi Long
DATE: June 11, 2025 (Wed.)
TIME: 12pm to 1pm ET
PRESENTERS: Wanjin Li and Yuxi Long
Learn more about the presenters
Wanjin Li
Title of Talk
Development and external validation of machine learning models predicting iron recovery after blood donation.
Description
A stable blood supply is vital for healthcare, but donation-associated iron deficiency threatens both blood donors and availability. Machine learning models directly predicting iron biomarkers post-donation could improve donor safety and blood supply management. No such models have been developed or externally validated internationally. This study aimed to develop and externally validate machine learning models predicting returning blood donors’ hemoglobin and ferritin.
Yuxi Long
Title of Talk
Pre-trained Vision Transformers Enable Robust Thermal Imaging-Based Detection of Rheumatoid Arthritis
Description
Rheumatoid arthritis (RA) is a chronic autoimmune disorder where early detection and accurate diagnosis is essential for effective disease management. Thermal imaging offers a non-invasive modality to detect inflammation associated with RA, but extracting discriminative features from thermal images remains challenging, particularly with limited datasets. We hypothesize that pre-trained vision transformers can overcome these limitations by leveraging transfer learning to extract robust and interpretable thermal biomarkers, improving RA classification accuracy and clinical applicability.
Learn more about the presenters
