A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine Learning

OBJECTIVE

Published predictive models of disease outcomes in idiopathic inflammatory myopathies (IIMs) are sparse and of limited accuracy due to disease heterogeneity. Computational methods may address this heterogeneity by partitioning patients based on clinical and biological phenotype.

METHODS

To identify new patient groups, we applied similarity network fusion (SNF) to clinical and biological data from 168 patients with myositis (64 adult polymyositis [PM], 65 adult dermatomyositis [DM], and 39 juvenile DM [JDM]) in the Rituximab in Myositis trial. We generated a sparse proof-of-concept bedside classifier using multinomial regression and identified characteristics that distinguished these groups. We conducted χ² tests to link new patient groups with the myositis subtypes.

RESULTS

SNF identified five patient groups in the discovery cohort that subdivided the myositis subtypes. The sparse multinomial regressor to predict patient group assignments (areas under the receiver operating characteristic curve = [0.78, 0.97]; areas under the precision-recall curve = [0.55, 0.96]) found that autoantibody enrichment defined four of these groups: anti-Mi-2, anti-signal recognition peptide (SRP), anti-nuclear matrix protein 2 (NXP2), and anti-synthetase (Syn). Depletion of immunoglobulin M (IgM) defined the fifth group. Each group was associated with one subtype, with adult DM being associated with anti-Mi-2 and anti-Syn autoantibodies, JDM being associated with anti-NXP2 autoantibodies, and adult PM being associated with IgM depletion and anti-SRP autoantibodies. These associations enabled us to further resolve the current myositis subtypes.

CONCLUSION

Using unsupervised machine learning, we identified clinically and biologically homogeneous groups of patients with IIMs, forming the basis of an integrated disease classification based on both clinical and biological phenotype, thus validating other approaches and what has been previously described.

Cutaneous dermatomyositis disease course followed over time using the Cutaneous Dermatomyositis Disease Area and Severity Index

BACKGROUND

Limited studies describe the longitudinal course of cutaneous dermatomyositis (DM).

OBJECTIVE

To characterize disease course in treated cutaneous DM by using the Cutaneous Dermatomyositis Disease Area and Severity Index (CDASI), a validated outcome instrument.

METHODS

A retrospective cohort included patients with DM who had their CDASI activity subscore recorded for at least 2 years. Disease progression was classified as improved, worsened, or stable, and disease course was classified as monophasic, polyphasic, or chronic. Subjects were divided into groups with disease of mild (n = 16) and moderate-to-severe (n = 24) baseline severity.

RESULTS

A total of 40 patients with DM met inclusion criteria. The majority demonstrated improvement in disease activity (n = 21 [52.5%]) rather than worsening (n = 7 [17.5%]) and stable (n = 12 [30.0%]) disease. Most patients with mild disease remained stable (n = 10 [62.5%]), whereas most with moderate-to-severe disease improved (n = 19 [79.2%]). A polyphasic course (n = 33 [82.5%]) predominated over monophasic (n = 5 [12.5%]) and chronic (n = 2 [5%]) courses. The average number of flares per year per number of years of follow-up was independent of baseline disease activity.

LIMITATIONS

The retrospective design, potential referral bias, and cutoff values in classification criteria are limitations.

CONCLUSION

Baseline CDASI activity score is associated with particular patterns of disease course and progression in cutaneous DM.

Clinical Features, Etiologic Factors, Associated Disorders, and Treatment of Palmoplantar Pustulosis: The Mayo Clinic Experience, 1996-2013

OBJECTIVE

To further characterize clinical characteristics, etiologic factors, associated disorders, and treatment of palmoplantar pustulosis (PPP).

PATIENTS AND METHODS

We conducted a retrospective review of patients with PPP at Mayo Clinic between January 1, 1996, and December 31, 2013.

RESULTS

Of 215 patients with PPP identified, 179 (83%) were female, and the mean age at onset was 45.3 years. Most patients (n=165, 77%) were current or former smokers. At diagnosis, 15 patients (7%) had an anxiety diagnosis and 9 (4%) had an infection. Nineteen cases (9%) were drug induced. Comorbid conditions included thyroid disease in 18 patients (8%), gluten sensitivity in 3 (1%), and type 2 diabetes mellitus in 21 (10%). In all, 194 patients (90%) received topical corticosteroids, 55 (26%) received phototherapy, and 54 (25%) received systemic agents.

CONCLUSION

More than three-fourths of the patients in this study had a history of smoking, which is considered a triggering or aggravating factor for PPP. Regarding comorbid conditions, gluten sensitivity and thyroid disease were found less frequently than previously reported in the literature. Treatment regimens and responses in this cohort varied considerably.

Adipokine gene expression in peripheral blood of adult and juvenile dermatomyositis patients and their relation to clinical parameters and disease activity measures

Objective

Recently adipokines have been implicated in the regulation of immune and inflammatory responses in autoimmune disease. To investigate the role of adipokines in adult and pediatric patients with newly diagnosed dermatomyositis (DM), we analyzed peripheral blood and skeletal muscle gene expression of four adipokines: visfatin, leptin, adiponectin and resistin.

Methods

Peripheral blood mononuclear cells (PBMCs) were collected for 21 adult DM, 26 juvenile DM, 5 non-disease adult controls, and 6 non-disease pediatric controls at two time points: baseline and 6 months. Muscle biopsies from 5 adult DM patients and 5 non-disease adult controls were collected at baseline. Similarly, muscle biopsies from 7 juvenile DM patients and 5 non-disease pediatric controls were collected at baseline. The gene expression levels of leptin, adiponectin, resistin, visfatin and related inflammatory cytokines, IL-6, TNF- α, and housekeeping genes GAPDH, B2M, and ACTB were generated using a custom RT² Profiler PCR Array.

Results

Visfatin gene expression levels in peripheral blood were significantly higher in newly diagnosed adult DM cases compared to non-disease controls (P = 0.004) and these levels correlated with baseline clinical parameters such as age (r = 0.34, P = 0.020), male sex (r = −0.35, P = 0.017), prednisone use (r = −0.42, P = 0.006), and DMARD use (r = 0.35, P = 0.025). No significant association was found between change in visfatin gene expression levels and change in disease activity measures. While visfatin gene expression was significantly up-regulated in muscle tissue of juvenile DM patients (P = 0.028), in adult DM patients only a trend towards significance was observed (P = 0.08). Also, muscle gene expression levels of resistin were significantly elevated in both adult and juvenile DM patients compared respectively to non-disease adult and pediatric controls. Furthermore, an association between peripheral blood resistin gene expression and DM disease activity, including global, muscle, and extra-skeletal disease activity was also observed.

Conclusion

Peripheral blood visfatin gene expression and muscle resistin gene expression are significantly increased in newly diagnosed adult DM patients. Further longitudinal studies should explore the possibility of using gene expression levels of adipokines such as visfatin and resistin as novel clinical diagnostic biomarkers in DM.

Early detection of melanoma: reviewing the ABCDEs

Over the course of their nearly 30-year history, the ABCD(E) criteria have been used globally in medical education and in the lay press to provide simple parameters for assessment of pigmented lesions that need to be further evaluated by a dermatologist. In this article, the efficacy and limitations of the ABCDE criteria as both a clinical tool and a public message will be reviewed.