Identifying Mild-to-Moderate Atopic Dermatitis Using a Generic Machine Learning Approach: A Danish National Health Register Study

Atopic dermatitis is a chronic skin disease, causing itching and recurrent eczematous lesions. In Danish national register data, adults with atopic dermatitis can only be identified if they have a hospital-diagnosed atopic dermatitis. The purpose of this study was to develop a machine learning model...

Full description

Saved in:
Bibliographic Details
Main Authors: Mie Sylow Liljendahl, Kristina Ibler, Christian Vestergaard, Lone Skov, Pavika Jain, Jan Håkon Rudolfsen, Ann Hærskjold, Mathias Torpet
Format: Article
Language:English
Published: Medical Journals Sweden 2025-05-01
Series:Acta Dermato-Venereologica
Subjects:
Online Access:https://medicaljournalssweden.se/actadv/article/view/42250
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850033194703781888
author Mie Sylow Liljendahl
Kristina Ibler
Christian Vestergaard
Lone Skov
Pavika Jain
Jan Håkon Rudolfsen
Ann Hærskjold
Mathias Torpet
author_facet Mie Sylow Liljendahl
Kristina Ibler
Christian Vestergaard
Lone Skov
Pavika Jain
Jan Håkon Rudolfsen
Ann Hærskjold
Mathias Torpet
author_sort Mie Sylow Liljendahl
collection DOAJ
description Atopic dermatitis is a chronic skin disease, causing itching and recurrent eczematous lesions. In Danish national register data, adults with atopic dermatitis can only be identified if they have a hospital-diagnosed atopic dermatitis. The purpose of this study was to develop a machine learning model to identify all patients with atopic dermatitis by proxy, using data for contacts with primary care, prescription medication, and hospital contacts not related to skin diseases. Individuals redeeming a prescription for dermatological preparations were extracted as potential patients with atopic dermatitis. Individuals with a registered hospital diagnosis of atopic dermatitis were classified as “Known AD”, “Other skin disease” (registrations of other dermatological diagnosis codes indicating other skin disease), or “Uncertain AD status”’ (no hospital diagnosis registered). Patients categorized as “Known AD” and “Other skin disease” were used to develop the model. All uses of healthcare services 2 years prior to hospital diagnosis were used as potential predictors. The data were split into training and validation sets (70/30). From 1996 to 2022, 385,135 individuals had uncertain atopic dermatitis status. The most important predictors were corticosteroid prescriptions for dermatological use, consultations with dermatologist, and age. Of the 385,135 individuals, the model predicted that 230,522 individuals likely have atopic dermatitis.
format Article
id doaj-art-b0fe9ae122934d79b7d11e8cb2916916
institution DOAJ
issn 0001-5555
1651-2057
language English
publishDate 2025-05-01
publisher Medical Journals Sweden
record_format Article
series Acta Dermato-Venereologica
spelling doaj-art-b0fe9ae122934d79b7d11e8cb29169162025-08-20T02:58:18ZengMedical Journals SwedenActa Dermato-Venereologica0001-55551651-20572025-05-0110510.2340/actadv.v105.42250Identifying Mild-to-Moderate Atopic Dermatitis Using a Generic Machine Learning Approach: A Danish National Health Register StudyMie Sylow Liljendahl0Kristina Ibler1Christian Vestergaard2Lone Skov3Pavika Jain4Jan Håkon Rudolfsen5Ann Hærskjold6Mathias Torpet7Department of Dermatology and Allergy, Copenhagen University Hospital - Herlev and Gentofte, Copenhagen, DenmarkDepartment of Dermatology, Bispebjerg Hospital, Copenhagen University Hospital, DenmarkDepartment of Dermatology, Aarhus University Hospital, Aarhus, DenmarkDepartment of Dermatology and Allergy, Copenhagen University Hospital - Herlev and Gentofte, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, DenmarkMarket Access, Sanofi Denmark A/SEY, Frederiksberg, DenmarkDepartment of Dermatology, Bispebjerg Hospital, Copenhagen University Hospital, DenmarkMedical Affairs, Sanofi Denmark A/SAtopic dermatitis is a chronic skin disease, causing itching and recurrent eczematous lesions. In Danish national register data, adults with atopic dermatitis can only be identified if they have a hospital-diagnosed atopic dermatitis. The purpose of this study was to develop a machine learning model to identify all patients with atopic dermatitis by proxy, using data for contacts with primary care, prescription medication, and hospital contacts not related to skin diseases. Individuals redeeming a prescription for dermatological preparations were extracted as potential patients with atopic dermatitis. Individuals with a registered hospital diagnosis of atopic dermatitis were classified as “Known AD”, “Other skin disease” (registrations of other dermatological diagnosis codes indicating other skin disease), or “Uncertain AD status”’ (no hospital diagnosis registered). Patients categorized as “Known AD” and “Other skin disease” were used to develop the model. All uses of healthcare services 2 years prior to hospital diagnosis were used as potential predictors. The data were split into training and validation sets (70/30). From 1996 to 2022, 385,135 individuals had uncertain atopic dermatitis status. The most important predictors were corticosteroid prescriptions for dermatological use, consultations with dermatologist, and age. Of the 385,135 individuals, the model predicted that 230,522 individuals likely have atopic dermatitis. https://medicaljournalssweden.se/actadv/article/view/42250atopic dermatitismachine learninghealthcare registerprediction
spellingShingle Mie Sylow Liljendahl
Kristina Ibler
Christian Vestergaard
Lone Skov
Pavika Jain
Jan Håkon Rudolfsen
Ann Hærskjold
Mathias Torpet
Identifying Mild-to-Moderate Atopic Dermatitis Using a Generic Machine Learning Approach: A Danish National Health Register Study
Acta Dermato-Venereologica
atopic dermatitis
machine learning
healthcare register
prediction
title Identifying Mild-to-Moderate Atopic Dermatitis Using a Generic Machine Learning Approach: A Danish National Health Register Study
title_full Identifying Mild-to-Moderate Atopic Dermatitis Using a Generic Machine Learning Approach: A Danish National Health Register Study
title_fullStr Identifying Mild-to-Moderate Atopic Dermatitis Using a Generic Machine Learning Approach: A Danish National Health Register Study
title_full_unstemmed Identifying Mild-to-Moderate Atopic Dermatitis Using a Generic Machine Learning Approach: A Danish National Health Register Study
title_short Identifying Mild-to-Moderate Atopic Dermatitis Using a Generic Machine Learning Approach: A Danish National Health Register Study
title_sort identifying mild to moderate atopic dermatitis using a generic machine learning approach a danish national health register study
topic atopic dermatitis
machine learning
healthcare register
prediction
url https://medicaljournalssweden.se/actadv/article/view/42250
work_keys_str_mv AT miesylowliljendahl identifyingmildtomoderateatopicdermatitisusingagenericmachinelearningapproachadanishnationalhealthregisterstudy
AT kristinaibler identifyingmildtomoderateatopicdermatitisusingagenericmachinelearningapproachadanishnationalhealthregisterstudy
AT christianvestergaard identifyingmildtomoderateatopicdermatitisusingagenericmachinelearningapproachadanishnationalhealthregisterstudy
AT loneskov identifyingmildtomoderateatopicdermatitisusingagenericmachinelearningapproachadanishnationalhealthregisterstudy
AT pavikajain identifyingmildtomoderateatopicdermatitisusingagenericmachinelearningapproachadanishnationalhealthregisterstudy
AT janhakonrudolfsen identifyingmildtomoderateatopicdermatitisusingagenericmachinelearningapproachadanishnationalhealthregisterstudy
AT annhærskjold identifyingmildtomoderateatopicdermatitisusingagenericmachinelearningapproachadanishnationalhealthregisterstudy
AT mathiastorpet identifyingmildtomoderateatopicdermatitisusingagenericmachinelearningapproachadanishnationalhealthregisterstudy