# Unsupervised Discovery of Clinical Disease Signatures Using Probabilistic Independence

arXiv: https://arxiv.org/abs/2402.05802 · HTML: https://mlsanity.com/paper/2402.05802/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 71 references that are in the map.
- First posted on arXiv 8 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning](https://mlsanity.com/paper/1805.08651/) (2018)
- [Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer](https://mlsanity.com/paper/1906.04716/) (2019)
- [Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data](https://mlsanity.com/paper/2001.05295/) (2020)
- [Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning](https://mlsanity.com/paper/2303.16535/) (2023)
- [Deep Representation Learning of Electronic Health Records to Unlock Patient Stratification at Scale](https://mlsanity.com/paper/2003.06516/) (2020)
- [Identifying Patient-Specific Root Causes with the Heteroscedastic Noise Model](https://mlsanity.com/paper/2205.13085/) (2022)
- [TAPER: Time-Aware Patient EHR Representation](https://mlsanity.com/paper/1908.03971/) (2019)
- [Distilling Knowledge from Deep Networks with Applications to Healthcare Domain](https://mlsanity.com/paper/1512.03542/) (2015)
- [Multimodal data matters: language model pre-training over structured and unstructured electronic health records](https://mlsanity.com/paper/2201.10113/) (2022)
- [Representation Learning for Electronic Health Records](https://mlsanity.com/paper/1909.09248/) (2019)
- [Identifying Patient-Specific Root Causes of Disease](https://mlsanity.com/paper/2205.11627/) (2022)
- [Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification](https://mlsanity.com/paper/2304.02836/) (2023)
- [Efficient Inference of Gaussian Process Modulated Renewal Processes with Application to Medical Event Data](https://mlsanity.com/paper/1402.4732/) (2014)
- [Sample-Specific Root Causal Inference with Latent Variables](https://mlsanity.com/paper/2210.15340/) (2022)
- [Generalized and Transferable Patient Language Representation for Phenotyping with Limited Data](https://mlsanity.com/paper/2103.00482/) (2021)

## Built on by (most cited first, 3 of 3)

- [Self-supervised learning of imaging and clinical signatures using a multimodal joint-embedding predictive architecture](https://mlsanity.com/paper/2509.15470/) (2025)
- [Cryptogenic stroke and migraine: using probabilistic independence and machine learning to uncover latent sources of disease from the electronic health record](https://mlsanity.com/paper/2505.04631/) (2025)
- [A tutorial on discovering and quantifying the effect of latent causal sources of multimodal EHR data](https://mlsanity.com/paper/2510.16026/) (2025)

## Abstract (arXiv)

Insufficiently precise diagnosis of clinical disease is likely responsible for many treatment failures, even for common conditions and treatments. With a large enough dataset, it may be possible to use unsupervised machine learning to define clinical disease patterns more precisely. We present an approach to learning these patterns by using probabilistic independence to disentangle the imprint on the medical record of causal latent sources of disease. We inferred a broad set of 2000 clinical signatures of latent sources from 9195 variables in 269,099 Electronic Health Records. The learned signatures produced better discrimination than the original variables in a lung cancer prediction task unknown to the inference algorithm, predicting 3-year malignancy in patients with no history of cancer before a solitary lung nodule was discovered. More importantly, the signatures' greater explanatory power identified pre-nodule signatures of apparently undiagnosed cancer in many of those patients.