Deep learning–based clustering for endotyping and post-arthroplasty response classification using knee osteoarthritis multiomic data
Authors' conclusion
We developed a multimodal deep learning-based clustering model capable of integrating complex multifluid, multiomic data to assist in uncovering biologically distinct patient endotypes and enhance outcome classifications to TKA surgery
Study context
- Population
- Patients with primary knee OA with subject-matched plasma, synovial fluid and urine; 1-year post-TKA WOMAC pain/function responses
- Participants
- 414 patients
- Outcome
- Multimodal deep learning-based clustering across 4 multiomic domains (plasma metabolites; plasma, synovial fluid and urine microRNAs)
Methodological detailsmultimodal deep learning variational autoencoder with K-means clustering, integrative machine learning framework, multiomic (microRNA sequencing, metabolomics)
- Multimodal deep learning variational autoencoder with K-means clustering
- Integrative machine learning framework
- Multiomic (microRNA sequencing, metabolomics)
Main finding
As reported in the abstract
Distinct patient clusters (knee osteoarthritis (KOA) endotypes)
3
Features in signature associated with cluster 1
30
Features in signature associated with cluster 3
24
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Deep learning–based clustering for endotyping and post-arthroplasty response classification using knee osteoarthritis multiomic data. Ann Rheum Dis. Published 12 February 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →