Unsupervised machine-learning algorithms for the identification of clinical phenotypes in the osteoarthritis initiative database.

Autor: Demanse D; Novartis Pharma AG, 4002, Basel, Switzerland. Electronic address: david.demanse@novartis.com., Saxer F; Novartis Institutes for Biomedical Research, Novartis Campus, 4002, Basel, Switzerland; Medical Faculty, University of Basel, 4002, Basel, Switzerland. Electronic address: franziska.saxer@novartis.com., Lustenberger P; IBM Switzerland AG, Vulkanstrasse 106, 8048, Zürich, Switzerland. Electronic address: patrick.lustenberger@ibm.com., Tankó LB; Bayer Pharmaceuticals, 4002, Basel Basel, Schweiz., Nikolaus P; IBM Switzerland AG, Vulkanstrasse 106, 8048, Zürich, Switzerland., Rasin I; IBM Switzerland AG, Vulkanstrasse 106, 8048, Zürich, Switzerland. Electronic address: ilja.rasin@ch.ibm.com., Brennan DF; IBM Switzerland AG, Vulkanstrasse 106, 8048, Zürich, Switzerland., Roubenoff R; Novartis Institutes for Biomedical Research, Novartis Campus, 4002, Basel, Switzerland. Electronic address: ronenn.roubenoff@novartis.com., Premji S; Novartis Pharma AG, 4002, Basel, Switzerland; IBM Switzerland AG, Vulkanstrasse 106, 8048, Zürich, Switzerland. Electronic address: sumehra.premji@novartis.com., Conaghan PG; Leeds Institute of Rheumatic & Musculoskeletal Medicine, University of Leeds and NIHR Leeds Biomedical Research Centre, UK. Electronic address: p.conaghan@leeds.ac.uk., Schieker M; Novartis Institutes for Biomedical Research, Novartis Campus, 4002, Basel, Switzerland. Electronic address: matthias.schieker@novartis.com.
Jazyk: angličtina
Zdroj: Seminars in arthritis and rheumatism [Semin Arthritis Rheum] 2023 Feb; Vol. 58, pp. 152140. Date of Electronic Publication: 2022 Nov 19.
DOI: 10.1016/j.semarthrit.2022.152140
Abstrakt: Objectives: Osteoarthritis (OA) is a complex disease comprising diverse underlying patho-mechanisms. To enable the development of effective therapies, segmentation of the heterogenous patient population is critical. This study aimed at identifying such patient clusters using two different machine learning algorithms.
Methods: Using the progression and incident cohorts of the Osteoarthritis Initiative (OAI) dataset, deep embedded clustering (DEC) and multiple factor analysis with clustering (MFAC) approaches, including 157 input-variables at baseline, were employed to differentiate specific patient profiles.
Results: DEC resulted in 5 and MFAC in 3 distinct patient phenotypes. Both identified a "comorbid" cluster with higher body mass index (BMI), relevant burden of comorbidity and low levels of physical activity. Both methods also identified a younger and physically more active cluster and an elderly cluster with functional limitations, but low disease impact. The additional two clusters identified with DEC were subgroups of the young/physically active and the elderly/physically inactive clusters. Overall pain trajectories over 9 years were stable, only the numeric rating scale (NRS) for pain showed distinct increase, while physical activity decreased in all clusters. Clusters showed different (though non-significant) trajectories of joint space changes over the follow-up period of 8 years.
Conclusion: Two different clustering approaches yielded similar patient allocations primarily separating complex "comorbid" patients from healthier subjects, the latter divided in young/physically active vs elderly/physically inactive subjects. The observed association to clinical (pain/physical activity) and structural progression could be helpful for early trial design as strategy to enrich for patients who may specifically benefit from disease-modifying treatments.
Competing Interests: Declaration of Competing Interest David Demanse is employee and shareholder of Novartis. Franziska Saxer is employee and shareholder of Novartis, she is affiliated to the University Basel and member of the European Union Medical Devices - Expert Panel section Orthopaedics, traumatology, rehabilitation, rheumatology. Patrick Lustenberger is employee of IBM, Switzerland and shareholder of Novartis. László B. Tankó was employee of Novartis and held shares, he is current employee of Bayer Pharmaceuticals. Philipp Nikolaus was employee of IBM, Switzerland, he is current employee of MSCI Inc. Ilja Rasin is employee of IBM, Switzerland. Damian F. Brennan is a former employee of IBM, Switzerland and in this employment consultant to Novartis. He currently is employee of the Macquarie Group, Australia. Ronenn Roubenoff is employee and shareholder of Novartis. Sumehra Premji is a former employee of IBM Switzerland and in this employment, consultant and account partner to Novartis. She is current employee and shareholder of Novartis. Philip G Conaghan reports fees for speaker’s bureaus (AbbVie, Novartis) and consultancies (AstraZeneca, BMS, Eli Lilly, Galapagos, Genascence, GSK, Merck, Novartis, Pfizer, Regeneron, Stryker and UCB). Matthias Schieker is employee and shareholder of Novartis and owner LivImplant GmbH.
(Copyright © 2022 Novartis Institutes of BioMedical Research. Published by Elsevier Inc. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: