Predictors of nonresponse to dupilumab in patients with atopic dermatitis: A machine learning analysis.

BACKGROUND: Many patients with atopic dermatitis (AD) have a suboptimal response to systemic therapy. OBJECTIVE: This study assessed predictors of nonresponse to dupilumab in patients with AD. METHODS: Data (April 2017 through June 2019) for patients aged 12 years and above with AD (International Classification of Diseases-9/10-Clinical Modification: 691.8/L20.x) who initiated dupilumab on or after April 1, 2017 (index date) were collected from an electronic health record and insurance claims database. Nonresponse indicators (dupilumab discontinuation, addition of another systemic therapy or phototherapy, addition of a high-potency topical corticosteroid, AD-related hospital visit, AD-related emergency department visit, incident skin infection) were predicted from available demographic and clinical variables using machine learning. RESULTS: Among 419 patients (mean age: 45 years), 145 (35%) experienced at least 1 indicator of nonresponse in the 6-month postindex period. In patients with at least 1 indicator, the most common was dupilumab discontinuation (47% [68/145]). Of note, this analysis could not capture nonmedical reasons for dupilumab discontinuation (eg, cost, access). The most common predictors of nonresponse were a claim for ibuprofen (in 69% of patients with a nonresponse indicator) and a Quan-Charlson Comorbidity Index value of 3 to 4 (59%). CONCLUSION: Systemic dupilumab therapy for AD can be associated with a relatively high prevalence of nonresponse indicators. Factors associated with these indicators-that is, predictors of nonresponse-may be used to optimize disease management.

A 'Real Life' Service Evaluation Model for Multidisciplinary Thyroid Eye Services.

Background/Aims: There is no universal consensus on the practical implementation and evaluation of the Amsterdam Declaration on Graves Orbitopathy in a Multidisciplinary Thyroid Eye Disease (MDTED) pathway. Recent recommendations from the UK TEAMeD-5 and BOPSS initiative highlight the importance of prevention, screening, and prompt referral of patients with moderate to severe and sight-threatening thyroid eye disease to multidisciplinary (MDTED) clinics and recommends annual auditing. We propose a practical service evaluation model with Key Performance Indicators (KPI) that are achievable and could be implemented across most TED pathways. Material and Methods: We conducted a service evaluation from an integrated TED pathway in London with three MDTED clinics. Data was collected retrospectively from consecutive TED patients included: 1) Patient demographics, 2) Referral to first appointment time, 3) Documented smoking cessation and selenium supplementation advice, 4) Presenting disease activity and severity, 5) Investigations and treatments, including radio-iodine, 6) Time from decision to treatment initiation, 7) Initial and subsequent thyroid status. Results: The median age was 49.0 yrs, 77.5% (183/236) were female and 49.5% (101/204) Afro-Caribbean or Asian. At their first clinic attendance, 47.6% (110/231) were biochemically euthyroid and 76.7% (79/103) at discharge. All 23.1% (52/225) current smokers received smoking cessation advice and 64.8% (153/236) received selenium supplementation advice. Intravenous methylprednisolone was given to 33.9% (80/236) patients and 12.7% (30/236) received second-line immunosuppression. All 7.2% (17/236) patients with sight-threatening disease received treatment within two weeks of diagnosis. Conclusions: This study forms a waymark for other units using TEAMeD-5 and BOPSS audit criteria. Dedicated electronic patient records with ongoing data capture, including quality of life assessments, and diagnostic coding would significantly aid future auditing, improve patient care, and facilitate a national audit of TED management. A future survey when the TED standards have become embedded would be instructive to see whether this has improved TED care.