# CONAN: Complementary Pattern Augmentation for Rare Disease Detection

arXiv: https://arxiv.org/abs/1911.13232 · HTML: https://mlsanity.com/paper/1911.13232/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 9 of 9)

- [PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning](https://mlsanity.com/paper/2211.01761/) (2022)
- [Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model](https://mlsanity.com/paper/2304.02169/) (2023)
- [Artificial Intelligence for In Silico Clinical Trials: A Review](https://mlsanity.com/paper/2209.09023/) (2022)
- [Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference](https://mlsanity.com/paper/2312.14646/) (2023)
- [Generating Clinically Realistic EHR Data via a Hierarchy- and Semantics-Guided Transformer](https://mlsanity.com/paper/2502.20719/) (2025)
- [CEHR-XGPT: A Scalable Multi-Task Foundation Model for Electronic Health Records](https://mlsanity.com/paper/2509.03643/) (2025)
- [Machine Learning Applications for Therapeutic Tasks with Genomics Data](https://mlsanity.com/paper/2105.01171/) (2021)
- [Fairness-Optimized Synthetic EHR Generation for Arbitrary Downstream Predictive Tasks](https://mlsanity.com/paper/2406.02510/) (2024)
- [Knowledge Graph Sparsification for GNN-based Rare Disease Diagnosis](https://mlsanity.com/paper/2510.08655/) (2025)

## Abstract (arXiv)

Rare diseases affect hundreds of millions of people worldwide but are hard to detect since they have extremely low prevalence rates (varying from 1/1,000 to 1/200,000 patients) and are massively underdiagnosed. How do we reliably detect rare diseases with such low prevalence rates? How to further leverage patients with possibly uncertain diagnosis to improve detection? In this paper, we propose a Complementary pattern Augmentation (CONAN) framework for rare disease detection. CONAN combines ideas from both adversarial training and max-margin classification. It first learns self-attentive and hierarchical embedding for patient pattern characterization. Then, we develop a complementary generative adversarial networks (GAN) model to generate candidate positive and negative samples from the uncertain patients by encouraging a max-margin between classes. In addition, CONAN has a disease detector that serves as the discriminator during the adversarial training for identifying rare diseases. We evaluated CONAN on two disease detection tasks. For low prevalence inflammatory bowel disease (IBD) detection, CONAN achieved .96 precision recall area under the curve (PR-AUC) and 50.1% relative improvement over best baseline. For rare disease idiopathic pulmonary fibrosis (IPF) detection, CONAN achieves .22 PR-AUC with 41.3% relative improvement over the best baseline.