Health AI Central
Peer-Reviewed Publication
Knee Surg Sports Traumatol Arthrosc2026;34(4):1524-1533.April 1, 2026Journal Article

Deep learning of wrist accelerometry from UK Biobank data identifies early movement signatures of knee osteoarthritis up to 5 years before diagnosis.

Ricardo Smits Serena1,2, Michael T Hirschmann3,4,5, Georg Matziolis6, Rüdiger von Eisenhart-Rothe1, Daniel Rueckert2,7, Florian Hinterwimmer1,2, Christina Valle1
1Department of Orthopaedics and Sports Orthopaedics, TUM University Hospital, Munich, Germany.
2Institute for AI and Informatics in Medicine, TUM University Hospital, Munich, Germany.
3Kantonsspital Baselland, Bruderholz, Switzerland.
4Kantonsspital Baselland, Liestal, Switzerland.
5Kantonsspital Baselland, Laufen, Switzerland.
6Waldkliniken Eisenberg GmbH, Eisenberg, Germany.
7Department of Computing, Imperial College London, London, UK.
PubMed PMC DOI PDF

Abstract

PURPOSE: This study aims to test whether week-long wrist accelerometry combined with deep learning can (i) distinguish healthy individuals from people with knee osteoarthritis (KOA), (ii) separate prodromal KOA from established KOA, and (iii) identify individuals who will receive a KOA diagnosis within 5 years. METHODS: We conducted a retrospective case-control study using the UK Biobank data set…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.