• Matthewman, Julian
• Mulick, Amy
• Brown, Sara J.
• Pearce, Neil
• Henderson, Alasdair
• Iskandar, Rita
• Denaxas, Spiros
• Roberts, Amanda
• Cornish, Rosie P.
• Paternoster, Lavinia
• Langan, Sinéad M.
• Major-Smith, Daniel
• Dand, Nick

Abstract

<jats:title>Abstract</jats:title><jats:sec><jats:title>Background</jats:title><jats:p>Subtypes of atopic dermatitis (AD) have been derived from the Avon Longitudinal Study of Parents and Children (ALSPAC) based on presence and severity of symptoms reported in questionnaires (Severe–Frequent, Moderate–Frequent, Moderate–Declining, Mild–Intermittent, Unaffected/Rare). Good agreement between ALSPAC and linked electronic health records (EHRs) would increase trust in the clinical validity of these subtypes and allow inferring subtypes from EHRs alone, which would enable their study in large primary care databases.</jats:p></jats:sec><jats:sec><jats:title>Objectives</jats:title><jats:p>1. Explore if presence and number of AD records in EHRs agrees with AD symptom and severity reports from ALSPAC; 2. Explore if EHRs agree with ALSPAC-derived AD subtypes; 3. Construct models to classify ALSPAC-derived AD subtype using EHRs.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>We used data from the ALSPAC prospective cohort study from 11 timepoints until age 14 years (1991–2008), linked to local general practice EHRs. We assessed how far ALSPAC questionnaire responses and derived subtypes agreed with AD as established in EHRs using different AD definitions (e.g., diagnosis and/or prescription) and other AD-related records. We classified AD subtypes using EHRs, fitting multinomial logistic regression models tuning hyperparameters and evaluating performance in the testing set (ROC AUC, accuracy, sensitivity, and specificity).</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>8,828 individuals out of a total 13,898 had both been assigned an AD subtype and had linked EHRs. The number of AD-related codes in EHRs generally increased with severity of AD subtype, however not all with the Severe-Frequent subtypes had AD in EHRs, and many with the Unaffected/Rare subtype did have AD in EHRs. When predicting ALSPAC AD subtype using EHRs, the best tuned model had ROC AUC of 0.65, sensitivity of 0.29 and specificity of 0.83 (both macro averaged); when different sets of predictors were used, individuals with missing EHR coverage excluded, and subtypes combined, sensitivity was not considerably improved.</jats:p></jats:sec><jats:sec><jats:title>Conclusions</jats:title><jats:p>ALSPAC and EHRs disagreed not just on AD subtypes, but also on whether children had AD or not. Researchers should be aware that individuals considered as having AD in one source may not be considered as having AD in another.</jats:p></jats:sec>

Topics

• size-exclusion chromatography