# Open Set Medical Diagnosis

arXiv: https://arxiv.org/abs/1910.02830 · HTML: https://mlsanity.com/paper/1910.02830/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets](https://mlsanity.com/paper/2109.05554/) (2021)
- [CheXseen: Unseen Disease Detection for Deep Learning Interpretation of Chest X-rays](https://mlsanity.com/paper/2103.04590/) (2021)
- [Injecting knowledge into language generation: a case study in auto-charting after-visit care instructions from medical dialogue](https://mlsanity.com/paper/2306.03652/) (2023)
- [Open-Set Recognition of Breast Cancer Treatments](https://mlsanity.com/paper/2201.02923/) (2022)
- [Latent Space Energy-based Model for Fine-grained Open Set Recognition](https://mlsanity.com/paper/2309.10711/) (2023)
- [OSLAT: Open Set Label Attention Transformer for Medical Entity Retrieval and Span Extraction](https://mlsanity.com/paper/2207.05817/) (2022)

## Abstract (arXiv)

Machine-learned diagnosis models have shown promise as medical aides but are trained under a closed-set assumption, i.e. that models will only encounter conditions on which they have been trained. However, it is practically infeasible to obtain sufficient training data for every human condition, and once deployed such models will invariably face previously unseen conditions. We frame machine-learned diagnosis as an open-set learning problem, and study how state-of-the-art approaches compare. Further, we extend our study to a setting where training data is distributed across several healthcare sites that do not allow data pooling, and experiment with different strategies of building open-set diagnostic ensembles. Across both settings, we observe consistent gains from explicitly modeling unseen conditions, but find the optimal training strategy to vary across settings.