The study used deep phenotyping to identify several factors in adults and adolescents with the disease.
A cross-sectional study of adolescent and adult patients with atopic dermatitis involving deep phenotyping identified several severity-associated factors including total serum immunoglobulin E levels greater than 1708 IU/mL and eosinophil values greater than 6.8%.
Investigators led by Thomas Welchowski, PhD, UKB University of Bonn Medical Center, Germany, noted that the disease is often driven by a complex pathophysiology underlying highly heterogeneous phenotypes.
Due to this, a growing interest in deep phenotyping had been observed by Welchowski and colleagues.
As such, the team evaluated the phenotype and potential risk factors in adolescent and adult populations with atopic dermatitis stratified by disease severity.
For their study, Welchowski and colleagues analyzed cross-sectional data from the baseline visits of a prospective longitudinal study which investigated the phenotype of patients with atopic dermatitis.
From November 2016 to February 2020, inpatients and outpatients who were 12 years and older with active atopic dermatitis that met the Hanifin and Rajka criteria were enrolled in the CK-CARE program at the University Hospital Bonn.
A total of 367 patients were included in the study, 210 (57%) of whom were female, with the mean age being 39 years old.
Each participant was tasked with completing a standardized questionnaire regarding personal and family history of atopy, as well as disease course, comorbidities, lifestyle, environment, drug intake, and the Dermatology Life Quality Index (DLQI).
Participants were also examined regarding severity of eczema through the Eczema Area and Severity Index (EASI), SCORing Atopic Dermatitis (SCORAD), and atopic stigmata, the last of which was conducted by an experienced dermatologist.
Patients with an EASI of 7 or less were considered to have mild disease, EASI greater than 7 and less than or equal to 21 was moderate disease, and EASI greater than 21 was severe disease.
Finally, associations of 130 factors with atopic dermatitis severity were analyzed by utilizing a machine learning-gradient boosting approach with cross-validation-based tuning (MLGB) and multinomial logistic regression with forward variable selection (MLR).
According to EASI scores, 48.2% of all participants (177) had mild atopic dermatitis, while 32.7% (120) had moderate cases, and 19.1% (70) had severe cases.
Additionally, the DLQI correlated significantly with severity (EASI: rs = 0.49; 95% CI, 0.41-0.57; SCORAD: rs = 0.58; 95% CI, 0.51-0.65; oS- CORAD: rs = 0.52; 95% CI, 0.44-0.59; BSA rs = 0.59; 95% CI, 0.52-0.65; all P < .001).
Investigators also noted that 142 (38.9%) of all patients and greater than 50% of patients with moderate to severe atopic dermatitis reported a highly reduced quality of life with a DLQI greater than 11 (mild, 16.9% [n=30]; moderate, 57.1% [n=68]; severe, 63.8% [n=44]).
Regarding total serum immunoglobulin E levels and eosinophil values, both were considered important for predicting severity, correlated with EASI (rs = 0.43; 95% CI, 0.34-0.51 for IgE; rs = 0.24; 95% CI, 0.14-0.35 for eosinophil values [%]) and among each other (rs = 0.33; 95% CI, 0.22-0.43; all P < .001).
The probability of severe atopic dermatitis also rose strongly with tIgE levels that were greater than 1708 IU/mL, and a total of 263 patients (75.1%) exhibited increased tIgE levels. A total of 80 patients (23%) exhibited eosinophilia.
Other factors associated with severe disease included patients aged 12 to 21 years or older than 52 years, age of atopic dermatitis onset older than 12 years, and physical activity less than once a week.
Though investigators noted that ranges of tIgE levels and age data were conclusive regarding their predictive value for mild or severe cases of the disease, probabilities for moderate atopic dermatitis fluctuated often, prompting a call for more research.
“Further stratification of the heterogeneous phenotypes by several criteria is needed for better identification of critical life periods, bio- markers, and of the right patient for personalized therapeutic and preventive measures of (severe) AD,” the team wrote.
The study, “Machine Learning-Based Deep Phenotyping of Atopic Dermatitis: Severity-Associated Factors in Adolescent and Adult Patients,” was published online in JAMA Dermatology.