Predicting pediatric diagnostic imaging patient no-show and extended wait-times using LLMs, regression, and tree based models
Our results surveyed multiple algorithms and data balancing methods to propose the greatest performing models on our tasks, implemented a unique methodology to use LLMs on heterogeneous data within this domain, and demonstrated the greater importance of contextual appointment data over patient demographic features for a more equitable prediction algorithm. Going forward, the predictive output (calibrated probabilities of events) can be used as stochastic input for risk-based optimized scheduling to provide accommodation for patients less likely to receive quality access to healthcare.
Authors
- Manohar Shroff
- Farzad Khalvati (ORCID: https://orcid.org/0000-0001-5616-8660)
- Kim Fung Tsang (ORCID: https://orcid.org/0000-0002-8332-227X)
- Melissa D. McCradden (ORCID: https://orcid.org/0000-0002-6476-2165)
- Wayne Lee (ORCID: https://orcid.org/0000-0002-0486-360X)
- Mjaye Mazwi (ORCID: https://orcid.org/0000-0003-1345-5429)
- Birgit Betina Ertl-Wagner (ORCID: https://orcid.org/0000-0001-5306-7549)
- Xuan Liu (ORCID: https://orcid.org/0000-0002-7966-4488)
- Bo Gong (ORCID: https://orcid.org/0000-0003-2763-6829)
- Daniel Rafique
- Laura Belsito
- Graham Ohanlon
Institutions
- University of Toronto (CA)
- Hospital for Sick Children (CA)
- Women's and Children's Health Network (AU)
- Seattle Children's Hospital (US)
- Vector Institute (CA)
- Australian Centre for Robotic Vision (AU)
- The University of Adelaide (AU)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-09-03
- DOI
- https://doi.org/10.3389/frai.2025.1652397
- Citations
- 1
- Primary Topic
- Healthcare Operations and Scheduling Optimization
- Type
- article
- Field-Weighted Citation Impact
- 2.52
Funders
- Hospital Research Foundation
- Government of Canada
- Hospital for Sick Children