Untapping the potential of utilizing electronic medical records to identify patients with atopic dermatitis: an algorithm using ICD-10 codes

Patient Phenotyping for Atopic Dermatitis with Transformers and Machine Learning

“…We initially sampled 2,000 patients and their clinical records from Epic Clarity, Penn Medicine's EHR database. We selected Penn Medicine patients who were diagnosed with a subset of AD-related ICD codes [9]. Of the 2,000 sampled patients, we identified 1,926 patients who had clinical notes for processing.…”

“…However, identifying appropriate cohorts of patients for medical studies can be difficult and time consuming. Because AD is so common as well as diagnosed and managed by many different clinicians in varying healthcare settings, a potential source population would be patients from a health system's electronic health records (EHRs) [9]. Investigators often ascertain a patient's illness using International Classification of Disease (ICD) hospital billing codes as recorded during routine office visits.…”

“…Investigators often ascertain a patient’s illness using International Classification of Disease (ICD) hospital billing codes as recorded during routine office visits. However, it has been previously demonstrated that reliance on ICD codes is not an accurate method for the ascertainment of AD study cohorts [9,10]. Furthermore, epidemiologic studies have used different methods and algorithms including the UK Working Party (UKWP) diagnostic criteria and the Hanifin and Rajka (HR) criteria [11,12].…”

“…Furthermore, epidemiologic studies have used different methods and algorithms including the UK Working Party (UKWP) diagnostic criteria and the Hanifin and Rajka (HR) criteria [10,11]. Investigators attempting to conduct clinical trials and observational studies have also relied on manual, large-scale chart review, a process that is inefficient, slow, and tedious [8]. This motivates the need for a standard method to accurately, automatically, and efficiently identify potential patient cohorts from their text medical records via natural language processing (NLP) and machine learning (ML) techniques.…”

Association between yearlong air pollution and moderate-severe atopic dermatitis: A United States cross-sectional claims analysis

“…Patients at least 12 years old with at least 6 months of continuous enrollment, an AD ICD-10 code, and either an asthma or allergic rhinitis code were included (Supplementary Table I, available via Mendeley at https://doi.org/10.17632/zsyrpbmx6j.1 ). 5 The primary outcome of having moderate-severe AD was identified by receipt of dupilumab, phototherapy, or a systemic immunosuppressant. Yearlong average PM 2.5 levels were collected from EPA stations nearest to each patient’s zip code.…”