Paper ID: 2208.10245

When BERT Fails -- The Limits of EHR Classification

Augusto Garcia-Agundez, Carsten Eickhoff

Transformers are powerful text representation learners, useful for all kinds of clinical decision support tasks. Although they outperform baselines on readmission prediction, they are not infallible. Here, we look into one such failure case, and report patterns that lead to inferior predictive performance.

Submitted: Jul 26, 2022