Magnitude and Impact of Hallucinations in Tabular Synthetic Health Data on Prognostic Machine Learning Models: Validation Study
These findings suggest that while hallucinations may be very common in synthetic tabular health data, they do not necessarily impair its utility for prognostic modeling.
Authors
- Samer El Kababji (ORCID: https://orcid.org/0000-0002-7642-2280)
- Khaled El Emam (ORCID: https://orcid.org/0000-0003-3325-4149)
- Dan Liu (ORCID: https://orcid.org/0000-0003-2131-6322)
- Lisa Pilgram (ORCID: https://orcid.org/0000-0002-1020-0650)
Institutions
- University of Ottawa (CA)
- Children's Hospital of Eastern Ontario (CA)
- Charité - Universitätsmedizin Berlin (DE)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-07-21
- DOI
- https://doi.org/10.2196/77893
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00