1
|
Nielsen RL, Monfeuga T, Kitchen RR, Egerod L, Leal LG, Schreyer ATH, Gade FS, Sun C, Helenius M, Simonsen L, Willert M, Tahrani AA, McVey Z, Gupta R. Data-driven identification of predictive risk biomarkers for subgroups of osteoarthritis using interpretable machine learning. Nat Commun 2024; 15:2817. [PMID: 38561399 PMCID: PMC10985086 DOI: 10.1038/s41467-024-46663-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2023] [Accepted: 03/04/2024] [Indexed: 04/04/2024] Open
Abstract
Osteoarthritis (OA) is increasing in prevalence and has a severe impact on patients' lives. However, our understanding of biomarkers driving OA risk remains limited. We developed a model predicting the five-year risk of OA diagnosis, integrating retrospective clinical, lifestyle and biomarker data from the UK Biobank (19,120 patients with OA, ROC-AUC: 0.72, 95%CI (0.71-0.73)). Higher age, BMI and prescription of non-steroidal anti-inflammatory drugs contributed most to increased OA risk prediction ahead of diagnosis. We identified 14 subgroups of OA risk profiles. These subgroups were validated in an independent set of patients evaluating the 11-year OA risk, with 88% of patients being uniquely assigned to one of the 14 subgroups. Individual OA risk profiles were characterised by personalised biomarkers. Omics integration demonstrated the predictive importance of key OA genes and pathways (e.g., GDF5 and TGF-β signalling) and OA-specific biomarkers (e.g., CRTAC1 and COL9A1). In summary, this work identifies opportunities for personalised OA prevention and insights into its underlying pathogenesis.
Collapse
Affiliation(s)
| | | | | | - Line Egerod
- Novo Nordisk Research Centre Oxford, Oxford, UK
| | - Luis G Leal
- Novo Nordisk Research Centre Oxford, Oxford, UK
| | | | | | - Carol Sun
- Novo Nordisk Research Centre Oxford, Oxford, UK
| | | | | | | | | | - Zahra McVey
- Novo Nordisk Research Centre Oxford, Oxford, UK
| | | |
Collapse
|
2
|
Ma J, Dhiman P, Qi C, Bullock G, van Smeden M, Riley RD, Collins GS. Poor handling of continuous predictors in clinical prediction models using logistic regression: a systematic review. J Clin Epidemiol 2023; 161:140-151. [PMID: 37536504 DOI: 10.1016/j.jclinepi.2023.07.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Revised: 07/20/2023] [Accepted: 07/26/2023] [Indexed: 08/05/2023]
Abstract
BACKGROUND AND OBJECTIVES When developing a clinical prediction model, assuming a linear relationship between the continuous predictors and outcome is not recommended. Incorrect specification of the functional form of continuous predictors could reduce predictive accuracy. We examine how continuous predictors are handled in studies developing a clinical prediction model. METHODS We searched PubMed for clinical prediction model studies developing a logistic regression model for a binary outcome, published between July 01, 2020, and July 30, 2020. RESULTS In total, 118 studies were included in the review (18 studies (15%) assessed the linearity assumption or used methods to handle nonlinearity, and 100 studies (85%) did not). Transformation and splines were commonly used to handle nonlinearity, used in 7 (n = 7/18, 39%) and 6 (n = 6/18, 33%) studies, respectively. Categorization was most often used method to handle continuous predictors (n = 67/118, 56.8%) where most studies used dichotomization (n = 40/67, 60%). Only ten models included nonlinear terms in the final model (n = 10/18, 56%). CONCLUSION Though widely recommended not to categorize continuous predictors or assume a linear relationship between outcome and continuous predictors, most studies categorize continuous predictors, few studies assess the linearity assumption, and even fewer use methodology to account for nonlinearity. Methodological guidance is provided to guide researchers on how to handle continuous predictors when developing a clinical prediction model.
Collapse
Affiliation(s)
- Jie Ma
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, United Kingdom.
| | - Paula Dhiman
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, United Kingdom
| | - Cathy Qi
- Population Data Science, Swansea University Medical School, Faculty of Medicine, Health and Life Science, Swansea University, Singleton Park Swansea, SA2 8PP, Swansea, United Kingdom
| | - Garrett Bullock
- Department of Orthopaedic Surgery, Wake Forest School of Medicine, Winston-Salem, NC, USA; Centre for Sport, Exercise and Osteoarthritis Research Versus Arthritis, University of Oxford, Oxford, United Kingdom
| | - Maarten van Smeden
- Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Richard D Riley
- Institute of Applied Health Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham B15 2TT, United Kingdom
| | - Gary S Collins
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, United Kingdom
| |
Collapse
|
3
|
De Baets L, Runge N, Labie C, Mairesse O, Malfliet A, Verschueren S, Van Assche D, de Vlam K, Luyten FP, Coppieters I, Babiloni AH, Martel MO, Lavigne GJ, Nijs J. The interplay between symptoms of insomnia and pain in people with osteoarthritis: A narrative review of the current evidence. Sleep Med Rev 2023; 70:101793. [PMID: 37269784 DOI: 10.1016/j.smrv.2023.101793] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2022] [Revised: 04/28/2023] [Accepted: 05/10/2023] [Indexed: 06/05/2023]
Abstract
Osteoarthritis (OA) is a leading cause of disability worldwide and clinical pain is the major symptom of OA. This clinical OA-related pain is firmly associated with symptoms of insomnia, which are reported in up to 81% of people with OA. Since understanding the association between both symptoms is critical for their appropriate management, this narrative review synthesizes the existing evidence in people with OA on i) the mechanisms underlying the association between insomnia symptoms and clinical OA-related pain, and ii) the effectiveness of conservative non-pharmacological treatments on insomnia symptoms and clinical OA-related pain. The evidence available identifies depressive symptoms, pain catastrophizing and pain self-efficacy as mechanisms partially explaining the cross-sectional association between insomnia symptoms and pain in people with OA. Furthermore, in comparison to treatments without a specific insomnia intervention, the ones including an insomnia intervention appear more effective for improving insomnia symptoms, but not for reducing clinical OA-related pain. However, at a within-person level, treatment-related positive effects on insomnia symptoms are associated with a long-term pain reduction. Future longitudinal prospective studies offering fundamental insights into neurobiological and psychosocial mechanisms explaining the association between insomnia symptoms and clinical OA-related pain will enable the development of effective treatments targeting both symptoms.
Collapse
Affiliation(s)
- Liesbet De Baets
- Pain in Motion Research Group (PAIN), Department of Physiotherapy, Human Physiology and Anatomy, Faculty of Physical Education & Physiotherapy, Vrije Universiteit Brussel, Belgium.
| | - Nils Runge
- Pain in Motion Research Group (PAIN), Department of Physiotherapy, Human Physiology and Anatomy, Faculty of Physical Education & Physiotherapy, Vrije Universiteit Brussel, Belgium; Musculoskeletal Rehabilitation Research Group, Department of Rehabilitation Sciences, Faculty of Movement and Rehabilitation Sciences, KU Leuven, Belgium
| | - Céline Labie
- Pain in Motion Research Group (PAIN), Department of Physiotherapy, Human Physiology and Anatomy, Faculty of Physical Education & Physiotherapy, Vrije Universiteit Brussel, Belgium; Musculoskeletal Rehabilitation Research Group, Department of Rehabilitation Sciences, Faculty of Movement and Rehabilitation Sciences, KU Leuven, Belgium; Division of Rheumatology, University Hospitals Leuven, Belgium
| | - Olivier Mairesse
- Department of Brain Body and Cognition (BBCO), Vrije Universiteit Brussel (VUB), Brussels, Belgium; Sleep Laboratory and Unit for Chronobiology U78, Department of Psychiatry, Brugmann University Hospital, Université Libre de Bruxelles (ULB) and Vrije Universiteit Brussel (VUB), Brussels, Belgium
| | - Anneleen Malfliet
- Pain in Motion Research Group (PAIN), Department of Physiotherapy, Human Physiology and Anatomy, Faculty of Physical Education & Physiotherapy, Vrije Universiteit Brussel, Belgium; Research Foundation Flanders (FWO), Brussels, Belgium
| | - Sabine Verschueren
- Musculoskeletal Rehabilitation Research Group, Department of Rehabilitation Sciences, Faculty of Movement and Rehabilitation Sciences, KU Leuven, Belgium
| | - Dieter Van Assche
- Musculoskeletal Rehabilitation Research Group, Department of Rehabilitation Sciences, Faculty of Movement and Rehabilitation Sciences, KU Leuven, Belgium; Division of Rheumatology, University Hospitals Leuven, Belgium
| | - Kurt de Vlam
- Division of Rheumatology, University Hospitals Leuven, Belgium; Skeletal Biology & Engineering Research Center, Dept. of Development & Regeneration, KU Leuven, Belgium
| | - Frank P Luyten
- Skeletal Biology & Engineering Research Center, Dept. of Development & Regeneration, KU Leuven, Belgium
| | - Iris Coppieters
- Pain in Motion Research Group (PAIN), Department of Physiotherapy, Human Physiology and Anatomy, Faculty of Physical Education & Physiotherapy, Vrije Universiteit Brussel, Belgium; The Laboratory for Brain-Gut Axis Studies (LaBGAS), Translational Research Center for Gastrointestinal Disorders (TARGID), KU Leuven, Leuven, Belgium
| | - Alberto Herrero Babiloni
- Division of Experimental Medicine, McGill University, Montreal, Québec, Canada; Center for Advanced Research in Sleep Medicine, Research Centre, Hôpital du Sacré-Coeur de Montréal (CIUSSS du Nord de-l'Île-de-Montréal) and University of Québec, Canada; Faculty of Dental Medicine, Université de Montréal, Québec, Canada
| | - Marc O Martel
- Division of Experimental Medicine, McGill University, Montreal, Québec, Canada; Faculty of Dentistry & Department of Anesthesia, McGill University, Canada
| | - Gilles J Lavigne
- Division of Experimental Medicine, McGill University, Montreal, Québec, Canada; Center for Advanced Research in Sleep Medicine, Research Centre, Hôpital du Sacré-Coeur de Montréal (CIUSSS du Nord de-l'Île-de-Montréal) and University of Québec, Canada; Faculty of Dental Medicine, Université de Montréal, Québec, Canada
| | - Jo Nijs
- Pain in Motion Research Group (PAIN), Department of Physiotherapy, Human Physiology and Anatomy, Faculty of Physical Education & Physiotherapy, Vrije Universiteit Brussel, Belgium; Department of Health and Rehabilitation, Unit of Physiotherapy, Institute of Neuroscience and Physiology, Sahlgrenska Academy, University of Gothenburg, Sweden; University of Gothenburg Center for Person-Centred Care (GPCC), Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden; Chronic Pain Rehabilitation, Department of Physical Medicine and Physiotherapy, University Hospital Brussels, Belgium
| |
Collapse
|
4
|
Magni N, Rice D, McNair P. Development of a prediction model to determine responders to conservative treatment in people with symptomatic hand osteoarthritis: A secondary analysis of a single-centre, randomised feasibility trial. Musculoskelet Sci Pract 2022; 62:102659. [PMID: 36088783 DOI: 10.1016/j.msksp.2022.102659] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/25/2022] [Revised: 08/15/2022] [Accepted: 08/21/2022] [Indexed: 12/14/2022]
Abstract
BACKGROUND Conservative treatments are beneficial for people with hand osteoarthritis (OA). OBJECTIVE It was the purpose of this study to develop and internally validate both a basic model and a more complex model that could predict responders to conservative treatments in people with hand OA. DESIGN This was a secondary analysis of a single-centre, randomised feasibility study. METHODS Fifty-nine participants (34 responders) with hand osteoarthritis were recruited from the general population. Participants were randomised to receive either advice alone, or advice in combination with blood flow restriction training (BFRT), or traditional high intensity training (HIT). Participants underwent supervised hand exercises three times per week for six weeks. The OMERACT-OARSI criteria were utilised to determine responders vs non responders to treatment at the end of six weeks. A basic logistic regression model (treatment type, expectations, adherence) and a more complex logistic regression model (basic model variables plus pain catastrophising and neuropathic pain features) were created. Discrimination ability, and calibration were assessed. Internal model validation through bootstrapping (200 repetitions) was utilised to calculate the prediction model optimism. RESULTS The results showed that the basic model presented with acceptable discrimination (optimism corrected c-statistic: 0.72, 95% CI 0.71-0.73) and calibration (slope = 1.41; intercept = 0.68). The more complex model had better discrimination but poorer calibration. CONCLUSION A prediction tool was created to provide an individualised estimate of treatment response in people with hand OA. Future studies will need to validate this model in other groups of patients. TRIAL REGISTRATION https://www.anzctr.org.au/- ACTRN12617001270303.
Collapse
Affiliation(s)
- N Magni
- Department of Physiotherapy, School of Clinical Sciences, Auckland University of Technology, Auckland, New Zealand.
| | - D Rice
- Department of Physiotherapy, School of Clinical Sciences, Auckland University of Technology, Auckland, New Zealand; Waitemata Pain Services, Department of Anaesthesiology and Perioperative Medicine, Waitemata District Health Board, Auckland, New Zealand
| | - P McNair
- Department of Physiotherapy, School of Clinical Sciences, Auckland University of Technology, Auckland, New Zealand
| |
Collapse
|
5
|
Appleyard T, Thomas MJ, Antcliff D, Peat G. Prediction Models to Estimate the Future Risk of Osteoarthritis in the General Population: A Systematic Review. Arthritis Care Res (Hoboken) 2022. [PMID: 36205228 DOI: 10.1002/acr.25035] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2022] [Revised: 09/06/2022] [Accepted: 10/04/2022] [Indexed: 01/27/2023]
Abstract
OBJECTIVE To evaluate the performance and applicability of multivariable prediction models for osteoarthritis (OA). METHODS This was a systematic review and narrative synthesis using 3 databases (EMBASE, PubMed, and Web of Science) from inception to December 2021. We included general population longitudinal studies reporting derivation, comparison, or validation of multivariable models to predict individual risk of OA incidence, defined by recognized clinical or imaging criteria. We excluded studies reporting prevalent OA and joint arthroplasty outcome. Paired reviewers independently performed article selection, data extraction, and risk-of-bias assessment. Model performance, calibration, and retained predictors were summarized. RESULTS A total of 26 studies were included, reporting 31 final multivariable prediction models for incident knee (23), hip (4), hand (3) and any-site OA (1), with a median of 121.5 (range 27-12,803) outcome events, a median prediction horizon of 8 years (range 2-41), and a median of 6 predictors (range 3-24). Age, body mass index, previous injury, and occupational exposures were among the most commonly included predictors. Model discrimination after validation was generally acceptable to excellent (area under the curve = 0.70-0.85). Either internal or external validation processes were used in most models, although the risk of bias was often judged to be high with limited applicability to mass application in diverse populations. CONCLUSION Despite growing interest in multivariable prediction models for incident OA, focus remains predominantly on the knee, with reliance on data from a small pool of appropriate cohort data sets, and concerns over general population applicability.
Collapse
Affiliation(s)
| | - Martin J Thomas
- Keele University and Midlands Partnership NHS Foundation Trust, Staffordshire, and Haywood Hospital, Burslem, UK
| | - Deborah Antcliff
- Keele University, Staffordshire, Northern Care Alliance NHS Foundation Trust, Bury Care Organisation, Manchester, and University of Leeds, Leeds, UK
| | - George Peat
- Keele University, Staffordshire, and Sheffield Hallam University, Sheffield, UK
| |
Collapse
|
6
|
Johnsen MB, Magnusson K, Børte S, Gabrielsen ME, Winsvold BS, Skogholt AH, Thomas L, Storheim K, Hveem K, Zwart JA. Response to Letter to the Editor: 'Comments on the paper presenting prediction models for incident hand OA in the HUNT study'. Osteoarthritis Cartilage 2021; 29:292-293. [PMID: 33279719 DOI: 10.1016/j.joca.2020.10.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/28/2020] [Accepted: 10/06/2020] [Indexed: 02/02/2023]
Affiliation(s)
- M B Johnsen
- Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Research, Innovation and Education, Division of Clinical Neuroscience, Oslo University Hospital, Oslo, Norway; K. G. Jebsen Center for Genetic Epidemiology, Department of Public Health and Nursing, Faculty of Medicine and Health, Norwegian University of Science and Technology, Trondheim, Norway.
| | - K Magnusson
- Lund University, Faculty of Medicine, Department of Clinical Sciences, Lund, Sweden; Orthopaedics, Clinical Epidemiology Unit, Lund, Sweden; National Advisory Unit on Rehabilitation in Rheumatology, Department of Rheumatology, Diakonhjemmet Hospital, Oslo, Norway.
| | - S Børte
- Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Research, Innovation and Education, Division of Clinical Neuroscience, Oslo University Hospital, Oslo, Norway; K. G. Jebsen Center for Genetic Epidemiology, Department of Public Health and Nursing, Faculty of Medicine and Health, Norwegian University of Science and Technology, Trondheim, Norway.
| | - M E Gabrielsen
- K. G. Jebsen Center for Genetic Epidemiology, Department of Public Health and Nursing, Faculty of Medicine and Health, Norwegian University of Science and Technology, Trondheim, Norway.
| | - B S Winsvold
- Department of Research, Innovation and Education, Division of Clinical Neuroscience, Oslo University Hospital, Oslo, Norway; K. G. Jebsen Center for Genetic Epidemiology, Department of Public Health and Nursing, Faculty of Medicine and Health, Norwegian University of Science and Technology, Trondheim, Norway.
| | - A H Skogholt
- K. G. Jebsen Center for Genetic Epidemiology, Department of Public Health and Nursing, Faculty of Medicine and Health, Norwegian University of Science and Technology, Trondheim, Norway.
| | - L Thomas
- K. G. Jebsen Center for Genetic Epidemiology, Department of Public Health and Nursing, Faculty of Medicine and Health, Norwegian University of Science and Technology, Trondheim, Norway; Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Trondheim, Norway.
| | - K Storheim
- Research and Communication Unit for Musculoskeletal Health, Oslo University Hospital, Oslo, Norway.
| | - K Hveem
- K. G. Jebsen Center for Genetic Epidemiology, Department of Public Health and Nursing, Faculty of Medicine and Health, Norwegian University of Science and Technology, Trondheim, Norway.
| | - J-A Zwart
- Institute of Clinical Medicine, University of Oslo, Oslo, Norway; Department of Research, Innovation and Education, Division of Clinical Neuroscience, Oslo University Hospital, Oslo, Norway; K. G. Jebsen Center for Genetic Epidemiology, Department of Public Health and Nursing, Faculty of Medicine and Health, Norwegian University of Science and Technology, Trondheim, Norway.
| |
Collapse
|
7
|
Choudary R, Wang Q, Runhaar J. Comments on the paper presenting prediction models for incident hand OA in the HUNT study. Osteoarthritis Cartilage 2021; 29:290-291. [PMID: 33278603 DOI: 10.1016/j.joca.2020.07.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/22/2020] [Accepted: 07/22/2020] [Indexed: 02/02/2023]
Affiliation(s)
- R Choudary
- Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Q Wang
- Department of General Practice, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - J Runhaar
- Department of General Practice, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands.
| |
Collapse
|