Unsupervised Discovery of Clinical Disease Signatures Using Probabilistic Independence
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917585143988224 |
|---|---|
| author | Lasko, Thomas A. Still, John M. Li, Thomas Z. Mota, Marco Barbero Stead, William W. Strobl, Eric V. Landman, Bennett A. Maldonado, Fabien |
| author_facet | Lasko, Thomas A. Still, John M. Li, Thomas Z. Mota, Marco Barbero Stead, William W. Strobl, Eric V. Landman, Bennett A. Maldonado, Fabien |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05802 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unsupervised Discovery of Clinical Disease Signatures Using Probabilistic Independence Lasko, Thomas A. Still, John M. Li, Thomas Z. Mota, Marco Barbero Stead, William W. Strobl, Eric V. Landman, Bennett A. Maldonado, Fabien Machine Learning Applications I.2.6; I.2.1; J.3 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. |
| title | Unsupervised Discovery of Clinical Disease Signatures Using Probabilistic Independence |
| topic | Machine Learning Applications I.2.6; I.2.1; J.3 |
| url | https://arxiv.org/abs/2402.05802 |