Machine Learning‐Based Predictive Modeling for the Development of Chronic Rhinosinusitis Using Longitudinal Health Records
KEY POINTS: Machine learning identifies reproducible pre-diagnostic CRS trajectories in large EHR cohorts. Models show stable external performance (AUC ∼ 0.81), supporting real-world generalizability. Predictors highlight evolving CRS workups and models may serve as future decision support tools.
Authors
- Michael T. Yim (ORCID: https://orcid.org/0000-0002-8599-1637)
- Renjie Hu
- Masayoshi Takashima (ORCID: https://orcid.org/0000-0001-9790-3529)
- Aatin K. Dhanda (ORCID: https://orcid.org/0000-0002-8926-7662)
- Richard A. Balbin
- O G Ahmed
- Akshay R. Prabhakar
- Sebastian Guadarrama‐Sistos‐Vazquez
- Justina Varghese (ORCID: https://orcid.org/0009-0001-8397-4155)
- Jason F. Zhang
- Xin Fu
- Sicong Chang
Institutions
- Methodist Hospital (US)
- University of Houston (US)
- Louisiana State University Health Sciences Center Shreveport (US)
Publication Details
- Journal
- International Forum of Allergy & Rhinology
- Published
- 2026-06-18
- DOI
- https://doi.org/10.1002/alr.70206
- Primary Topic
- Sinusitis and nasal conditions
- Type
- article
- Field-Weighted Citation Impact
- 0.00