Unsupervised machine learning models reveal two distinct post-operative physical activity profiles among joint arthroplasty patients: a United Kingdom biobank cohort study
Unsupervised learning of accelerometer-derived physical activity data revealed two clinically meaningful recovery profiles following joint arthroplasty. These findings underscore the multifactorial nature of post-operative recovery and support the development of personalised rehabilitation strategies to improve outcomes in lower limb arthroplasty patients. Video Abstract.
Authors
- Sara Sousi (ORCID: https://orcid.org/0000-0002-0494-5138)
- Gareth G. Jones (ORCID: https://orcid.org/0000-0002-3428-8765)
- Omar Musbahi (ORCID: https://orcid.org/0000-0002-4095-0989)
- Alex Bottle (ORCID: https://orcid.org/0000-0001-9978-2011)
- Justin Peter Cobb (ORCID: https://orcid.org/0000-0002-6095-8822)
- Ahmed Al-Saadawi (ORCID: https://orcid.org/0009-0000-5105-0903)
- Sevasti Panagiota Glynou (ORCID: https://orcid.org/0000-0001-5132-3967)
Institutions
- Queen Mary University of London (GB)
- Imperial College London (GB)
Publication Details
- Journal
- Arthroplasty
- Published
- 2025-11-12
- DOI
- https://doi.org/10.1186/s42836-025-00339-6
- Citations
- 1
- Primary Topic
- Total Knee Arthroplasty Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 2.01
Funders
- National Institute for Health and Care Research