# Making Conformal Predictors Robust in Healthcare Settings: a Case Study on EEG Classification

arXiv: https://arxiv.org/abs/2602.19483 · HTML: https://mlsanity.com/paper/2602.19483/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Conformal Prediction Under Covariate Shift](https://mlsanity.com/paper/1904.06019/) (2019)
- [The Temple University Hospital Seizure Detection Corpus](https://mlsanity.com/paper/1801.08085/) (2018)
- [Improved EEG Event Classification Using Differential Energy](https://mlsanity.com/paper/1801.02477/) (2018)
- [ManyDG: Many-domain Generalization for Healthcare Applications](https://mlsanity.com/paper/2301.08834/) (2023)
- [Tokenizing Single-Channel EEG with Time-Frequency Motif Learning](https://mlsanity.com/paper/2502.16060/) (2025)
- [Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis](https://mlsanity.com/paper/2303.10694/) (2023)
- [Conformal Drug Property Prediction with Density Estimation under Covariate Shift](https://mlsanity.com/paper/2310.12033/) (2023)

## Abstract (arXiv)

Quantifying uncertainty in clinical predictions is critical for high-stakes diagnosis tasks. Conformal prediction offers a principled approach by providing prediction sets with theoretical coverage guarantees. However, in practice, patient distribution shifts violate the i.i.d. assumptions underlying standard conformal methods, leading to poor coverage in healthcare settings. In this work, we evaluate several conformal prediction approaches on EEG seizure classification, a task with known distribution shift challenges and label uncertainty. We demonstrate that personalized calibration strategies can improve coverage by over 20 percentage points while maintaining comparable prediction set sizes. Our implementation is available via PyHealth, an open-source healthcare AI framework: https://github.com/sunlabuiuc/PyHealth.