Marjolein Engelkes

Automatic generation of case‐detection algorithms to identify children with asthma from large electronic health record databases

Most electronic health record databases contain unstructured free‐text narratives, which cannot be easily analyzed. Case‐detection algorithms are usually created manually and often rely only on using coded information such as International Classification of Diseases version 9 codes. We applied a machine‐learning approach to generate and evaluate an automated case‐detection algorithm that uses both free‐text and coded information to identify asthma cases.

Characteristics of adult onset vs. late onset asthma - a multinational database cohort study

Background: Although early onset asthma has been well characterised, data on adult onset asthma are scarce. Aims: To describe characteristics of adult onset asthma using data from 5 European electronic health record (EHR) databases in the study period 2008-2013. Methods: Asthma patients aged ≥18 yrs at diagnosis (COPD excluded) and with ≥1 year of follow-up were identified in EHR databases from the Netherlands (IPCI), Italy (HSD), UK (CPRD), Denmark (AUH) and Spain (SIDIAP). Patients were categorised into early adult onset asthma (>=18-39 yrs) or late onset asthma (>=40 yrs) based on the age at diagnosis. Characteristics were assessed at study start. Differences were tested with Chi-Square and Mann Whitney U test. The analysis was repeated in severe asthma only (use of high dose ICS + controller therapy for ≥120 days). Results: We included 504,745 patients (median age from 44.5-48.0 yrs) with asthma of whom 40,193 (8.0%) had severe asthma. The proportion of late onset asthma was 56.8% (range 56-60.1% across database) which increased to 70.4% (range 66.5-91.6%) in severe asthma. Compared to early adult onset asthma, patients with late onset asthma were less frequently atopic (range 9.2-28.7% across database vs. 21.5-39.5%), suffered more frequently from chronic rhinosinusitis (0.4-11.2% vs. 0.2-8.0%) and/or nasal polyposis (0.6-4.6% vs. 0.3-1.7%), GERD (2.8-14.3% vs. 0.9-7.5%) and obesity (10.5-72.2% vs. 9.3-54.7%) and had lower median IgE levels (63-91 vs. 108-226 IU/L)(all significant). Similar patterns were observed among severe asthma only. Conclusion: Differences in comorbidity in late onset vs. early adult onset asthma may be important for asthma management. GSK funded (PRJ2284)

Quick assessment of drug-related admissions over time (QUADRAT study).

To develop a computerized prescreening procedure for the identification of possible/probably Hospital Admissions potential Related to Medications (HARMs).