Unsupervised discovery of clinical disease signatures using probabilistic independence
These promising results demonstrate the potential of using probabilistic independence to disentangle complex clinical signatures from noisy, asynchronous, and incomplete EHR data that represent the confluence of multiple simultaneous conditions, and to identify patient-specific causes that support precise treatment decisions.
Authors
- Michael N. Kammer (ORCID: https://orcid.org/0000-0001-7912-8450)
- John M. Still
- Fabien Maldonado (ORCID: https://orcid.org/0000-0002-6504-2063)
- William W. Stead (ORCID: https://orcid.org/0000-0002-5048-9540)
- Bennett A. Landman (ORCID: https://orcid.org/0000-0001-5733-2127)
- Thomas A. Lasko (ORCID: https://orcid.org/0000-0003-2300-9529)
- Thomas Li (ORCID: https://orcid.org/0000-0001-9950-4679)
- Eric V Strobl (ORCID: https://orcid.org/0009-0003-9894-9694)
- Marco Barbero-Mota
Institutions
- Vanderbilt University (US)
- University of Pittsburgh Medical Center (US)
- Vanderbilt University Medical Center (US)
Publication Details
- Journal
- Journal of Biomedical Informatics
- Published
- 2025-04-23
- DOI
- https://doi.org/10.1016/j.jbi.2025.104837
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Fundación Bancaria Caixa d'Estalvis i Pensions de Barcelona
- National Cancer Institute