EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Deep learning–based clustering for endotyping and post-arthroplasty response classification using knee osteoarthritis multiomic data

Jason S Rockel, Divya Sharma, Osvaldo Espin-Garcia, Katrina Hueniken, Amit Sandhu, Chiara Pastrello, Kala Sundararajan, Pratibha Potla, Noah Fine, Starlee S Lively, Kim Perry, Nizar N Mahomed und 6 weitere

Annals of the Rheumatic Diseases · 2025

DOI: 10.1016/j.ard.2025.01.012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of the Rheumatic Diseases, 2025. Verfasst von Jason S Rockel und 17 weiteren Autor:innen. Beteiligte Einrichtung: Division of Orthopaedics, Osteoarthritis Research Program, Schroeder Arthritis Institute, University Health Network, Toronto, ON, Canada; Krembil Res…. Hauptthemen laut MEDLINE: Osteoarthritis, Knee, Deep Learning, Arthroplasty, Replacement, Knee. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Canada Foundation for Innovation, Race and Difference Initiative, Emory University, University Health Network Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES: Primary knee osteoarthritis (KOA) is a heterogeneous disease with clinical and molecular contributors. Biofluids contain microRNAs and metabolites that can be measured by omic technologies. Multimodal deep learning is adept at uncovering complex relationships within multidomain data. We developed a novel multimodal deep learning framework for clustering of multiomic data from 3 subject-matched biofluids to identify distinct KOA endotypes and classify 1-year post-total knee arthroplasty (TKA) pain/function responses. METHODS: In 414 patients with KOA, subject-matched plasma, synovial fluid, and urine were analysed using microRNA sequencing or metabolomics. Integrating 4 high-dimensional datasets comprising metabolites from plasma and microRNAs from plasma, synovial fluid, or urine, a multimodal deep learning variational autoencoder architecture with K-means clustering was employed. Features influencing cluster assignment were identified and pathway analyses conducted. An integrative machine learning framework combining 4 molecular domains and a clinical domain was then used to classify Western Ontario and McMaster Universities Arthritis Index (WOMAC) pain/function responses after TKA within each cluster. RESULTS: Multimodal deep learning-based clustering of subjects across 4 domains yielded 3 distinct patient clusters. Feature signatures comprising microRNAs and metabolites across biofluids included 30, 16, and 24 features associated with clusters 1 to 3, respectively. Pathway analyses revealed distinct pathways associated with each cluster. Integration of 4 multiomic domains along with clinical data improved response classification performance, surpassing individual domain classifications alone. CONCLUSIONS: 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, which may aid in future precision medicine approaches.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Osteoarthritis, KneeDeep LearningArthroplasty, Replacement, KneeHumansMaleFemaleMiddle AgedAgedMicroRNAsCluster AnalysisSynovial FluidMetabolomicsTreatment Outcome

Substanzen

MicroRNAs

Autor:innen und Institutionen

  • Division of Orthopaedics, Osteoarthritis Research Program, Schroeder Arthritis Institute, University Health Network, Toronto, ON, Canada; Krembil Research Institute, University Health Network, Toronto, ON, Canada.
  • Division of Orthopaedics, Osteoarthritis Research Program, Schroeder Arthritis Institute, University Health Network, Toronto, ON, Canada; Department of Biostatistics, Dalla Lana School of Public Health, University of To…
  • Division of Orthopaedics, Osteoarthritis Research Program, Schroeder Arthritis Institute, University Health Network, Toronto, ON, Canada; Krembil Research Institute, University Health Network, Toronto, ON, Canada; Depar…
  • Division of Orthopaedics, Osteoarthritis Research Program, Schroeder Arthritis Institute, University Health Network, Toronto, ON, Canada; Krembil Research Institute, University Health Network, Toronto, ON, Canada; Princ…

Förderung

  • Canada Foundation for Innovation
  • Race and Difference Initiative, Emory University
  • University Health Network Foundation
  • Arthritis Society
  • Natural Sciences and Engineering Research Council of Canada
  • Canada Research Chairs Program
  • Arthritis Society Canada

Zitieren

APA

Rockel, J. S., Sharma, D., Espin-Garcia, O., Hueniken, K., Sandhu, A., Pastrello, C., Sundararajan, K., Potla, P., Fine, N., Lively, S. S., Perry, K., Mahomed, N. N., Syed, K., Jurisica, I., Perruccio, A. V., Rampersaud, Y. R., Gandhi, R., & Kapoor, M. (2025). Deep learning–based clustering for endotyping and post-arthroplasty response classification using knee osteoarthritis multiomic data. Annals of the Rheumatic Diseases. https://doi.org/10.1016/j.ard.2025.01.012

Vancouver

Rockel JS, Sharma D, Espin-Garcia O, Hueniken K, Sandhu A, Pastrello C, et al. Deep learning–based clustering for endotyping and post-arthroplasty response classification using knee osteoarthritis multiomic data. Annals of the Rheumatic Diseases. 2025. doi:10.1016/j.ard.2025.01.012

BibTeX
@article{Rockel2025,
  author = {Rockel, Jason S and Sharma, Divya and Espin-Garcia, Osvaldo and Hueniken, Katrina and Sandhu, Amit and Pastrello, Chiara and Sundararajan, Kala and Potla, Pratibha and Fine, Noah and Lively, Starlee S and Perry, Kim and Mahomed, Nizar N and Syed, Khalid and Jurisica, Igor and Perruccio, Anthony V and Rampersaud, Y Raja and Gandhi, Rajiv and Kapoor, Mohit},
  title = {Deep learning–based clustering for endotyping and post-arthroplasty response classification using knee osteoarthritis multiomic data},
  journal = {Annals of the Rheumatic Diseases},
  year = {2025},
  doi = {10.1016/j.ard.2025.01.012}
}
Kostenlos starten →