O08 Developing a DNA methylation signature for predicting rheumatoid arthritis using a machine learning pipeline

Abstract Background/Aims Early diagnosis and intervention improves outcomes of immune mediated rheumatic and musculoskeletal diseases (RMDs) but may be hampered by diagnostic uncertainty. The extent to which rationally selected molecular parameters add value to clinical characteristics for diagnostic prediction in undifferentiated disease states warrants investigation. B lymphocytes play an increasingly recognised role in rheumatoid arthritis (RA) pathogenesis, and cell-specific methylation patterns link environmental exposures to genetic risk. We derived and tested the practical utility of a B lymphocyte-derived DNA methylation signature for predicting RA in an early arthritis clinic cohort. Methods CD19+ B cell and peripheral blood mononuclear cell (PBMC) whole genome DNA methylation array data were available, respectively, from 109 inflammatory arthritis patients naïve to immunomodulatory drugs (Newcastle, UK; 38% confirmed to have a diagnosis of RA within 1 year) and 50 untreated undifferentiated arthritis (UA) patients (Leiden, The Netherlands; 68% classifiable RA within 1 year by 1987 ACR criteria versus alternate diagnoses). A bespoke machine learning pipeline employed a sequential model-based optimisation (SMBO) procedure for selecting, tuning and applying methods amongst ten feature-selection, six data-sampling and two classification algorithms in the Newcastle “training cohort.” The predictive performance of the resultant optimised molecular classifier was assessed in the independent Leiden “test cohort” alongside a previously described clinical prediction rule, using comparative area under receiver operating characteristic (AUROC) curves. A modification to the clinical prediction rule that incorporated a single parameter to reflect molecular classification was also assessed. The pipeline was implemented using the R machine learning package mlr. Results Using the SMBO approach, 27 CpGs maximally discriminatory for RA were selected from B lymphocyte DNA methylome training data, and a molecular classifier was derived using the random forest algorithm. Applied to the independent PBMC methylome in UA patients, the classifier and the validated Leiden prediction rule performed similarly in predicting RA (AUROC [95% CI] = 0.8 [0.66-0.94] versus 0.78 [0.64-0.92]). Interestingly, incorporating a molecular risk score based on the 27-CpG signature into the validated Leiden clinical prediction rule significantly improved its performance (AUROC [95% CI] = 0.89 [0.79-0.98] versus 0.78 [0.64-0.92]; p = 0.048). When applied to the sub-cohort of 25 patients in the Leiden cohort who were negative for anti-citrullinated peptide autoantibodies (ACPA), enhanced performance of the modified over the un-modified clinical prediction rule was maintained (AUROC [95% CI] = 0.82 [0.65-1] versus 0.70 [0.45-0.95], respectively), although the difference did not reach statistical significance in this smaller cohort. Conclusion We provide a proof of principle for the application of a B lymphocyte-derived epigenetic signature to enhance prediction of RA in UA patients using stored PBMCs. Further refinement of our pipeline represents a plausible means to expedite the diagnosis in undifferentiated RMDs and could offer pathophysiological insight. Disclosure N. Naamane: None. E. Niemantsverdriet: None. N. Thalayasingam: None. N. Nair: None. A.D. Clark: None. K. Murray: None. B. Hargreaves: None. L.N. Reynard: None. S. Eyre: None. A. Barton: None. A.H.M. van der Helm-van Mil: None. A.G. Pratt: None.

Download Full-text

Diagnostic accuracy of a clinical prediction rule (CPR) for identifying patients with recent-onset undifferentiated arthritis who are at a high risk of developing rheumatoid arthritis: A systematic review and meta-analysis

Seminars in Arthritis and Rheumatism ◽

10.1016/j.semarthrit.2013.08.005 ◽

2014 ◽

Vol 43 (4) ◽

pp. 498-507 ◽

Cited By ~ 12

Author(s):

Emma McNally ◽

Claire Keogh ◽

Rose Galvin ◽

Tom Fahey

Keyword(s):

Rheumatoid Arthritis ◽

Systematic Review ◽

High Risk ◽

Diagnostic Accuracy ◽

Meta Analysis ◽

Prediction Rule ◽

Clinical Prediction Rule ◽

Clinical Prediction ◽

Undifferentiated Arthritis ◽

Recent Onset

Download Full-text

Faculty Opinions recommendation of Derivation and validation of a clinical prediction rule for uncomplicated ureteral stone--the STONE score: retrospective and prospective observational cohort studies.

Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature ◽

10.3410/f.718326320.793493330 ◽

2014 ◽

Author(s):

M Hammad Ather

Keyword(s):

Cohort Studies ◽

Ureteral Stone ◽

Prediction Rule ◽

Clinical Prediction Rule ◽

Clinical Prediction ◽

Observational Cohort

Download Full-text

Inter‐rater reliability and prospective validation of a clinical prediction rule for SARS‐CoV‐2 infection

Academic Emergency Medicine ◽

10.1111/acem.14309 ◽

2021 ◽

Author(s):

Adam E. Nevel ◽

Jeffrey A. Kline

Keyword(s):

Prediction Rule ◽

Clinical Prediction Rule ◽

Clinical Prediction ◽

Rater Reliability

Download Full-text

Development and validation of a clinical prediction rule for development of diabetic foot ulceration: an analysis of data from five cohort studies

BMJ Open Diabetes Research & Care ◽

10.1136/bmjdrc-2021-002150 ◽

2021 ◽

Vol 9 (1) ◽

pp. e002150

Author(s):

Francesca M Chappell ◽

Fay Crawford ◽

Margaret Horne ◽

Graham P Leese ◽

Angela Martin ◽

...

Keyword(s):

Cohort Studies ◽

Secondary Care ◽

Prediction Rule ◽

Clinical Prediction Rule ◽

Initial Assessment ◽

Validation Dataset ◽

Benefit Analysis ◽

Clinical Prediction ◽

Net Benefit ◽

Foot Ulceration

IntroductionThe aim of the study was to develop and validate a clinical prediction rule (CPR) for foot ulceration in people with diabetes.Research design and methodsDevelopment of a CPR using individual participant data from four international cohort studies identified by systematic review, with validation in a fifth study. Development cohorts were from primary and secondary care foot clinics in Europe and the USA (n=8255, adults over 18 years old, with diabetes, ulcer free at recruitment). Using data from monofilament testing, presence/absence of pulses, and participant history of previous ulcer and/or amputation, we developed a simple CPR to predict who will develop a foot ulcer within 2 years of initial assessment and validated it in a fifth study (n=3324). The CPR’s performance was assessed with C-statistics, calibration slopes, calibration-in-the-large, and a net benefit analysis.ResultsCPR scores of 0, 1, 2, 3, and 4 had a risk of ulcer within 2 years of 2.4% (95% CI 1.5% to 3.9%), 6.0% (95% CI 3.5% to 9.5%), 14.0% (95% CI 8.5% to 21.3%), 29.2% (95% CI 19.2% to 41.0%), and 51.1% (95% CI 37.9% to 64.1%), respectively. In the validation dataset, calibration-in-the-large was −0.374 (95% CI −0.561 to −0.187) and calibration slope 1.139 (95% CI 0.994 to 1.283). The C-statistic was 0.829 (95% CI 0.790 to 0.868). The net benefit analysis suggested that people with a CPR score of 1 or more (risk of ulceration 6.0% or more) should be referred for treatment.ConclusionThe clinical prediction rule is simple, using routinely obtained data, and could help prevent foot ulcers by redirecting care to patients with scores of 1 or above. It has been validated in a community setting, and requires further validation in secondary care settings.

Download Full-text

Developing a clinical prediction rule for repeated consultations with functional somatic symptoms in primary care: a cohort study

BMJ Open ◽

10.1136/bmjopen-2020-040730 ◽

2021 ◽

Vol 11 (1) ◽

pp. e040730

Author(s):

Gea A Holtman ◽

Huibert Burger ◽

Robert A Verheij ◽

Hans Wouters ◽

Marjolein Y Berger ◽

...

Keyword(s):

Primary Care ◽

Cohort Study ◽

Somatic Symptoms ◽

Prediction Rule ◽

Clinical Prediction Rule ◽

Model Discrimination ◽

Clinical Prediction ◽

Internal Validation ◽

Predictive Values ◽

Healthy Activity

ObjectivesPatients who present in primary care with chronic functional somatic symptoms (FSS) have reduced quality of life and increased health care costs. Recognising these early is a challenge. The aim is to develop and internally validate a clinical prediction rule for repeated consultations with FSS.Design and settingRecords from the longitudinal population-based (‘Lifelines’) cohort study were linked to electronic health records from general practitioners (GPs).ParticipantsWe included patients consulting a GP with FSS within 1 year after baseline assessment in the Lifelines cohort.Outcome measuresThe outcome is repeated consultations with FSS, defined as ≥3 extra consultations for FSS within 1 year after the first consultation. Multivariable logistic regression, with bootstrapping for internal validation, was used to develop a risk prediction model from 14 literature-based predictors. Model discrimination, calibration and diagnostic accuracy were assessed.Results18 810 participants were identified by database linkage, of whom 2650 consulted a GP with FSS and 297 (11%) had ≥3 extra consultations. In the final multivariable model, older age, female sex, lack of healthy activity, presence of generalised anxiety disorder and higher number of GP consultations in the last year predicted repeated consultations. Discrimination after internal validation was 0.64 with a calibration slope of 0.95. The positive predictive value of patients with high scores on the model was 0.37 (0.29–0.47).ConclusionsSeveral theoretically suggested predisposing and precipitating predictors, including neuroticism and stressful life events, surprisingly failed to contribute to our final model. Moreover, this model mostly included general predictors of increased risk of repeated consultations among patients with FSS. The model discrimination and positive predictive values were insufficient and preclude clinical implementation.

Download Full-text