EczemaPred: A computational framework for personalised prediction of eczema severity dynamics.

Bayesian model PO-SCORAD atopic dermatitis machine learning prediction

Journal

Clinical and translational allergy
ISSN: 2045-7022
Titre abrégé: Clin Transl Allergy
Pays: England
ID NLM: 101576043

Informations de publication

Date de publication:
Mar 2022
Historique:
revised: 12 03 2022
received: 04 11 2021
accepted: 14 03 2022
entrez: 28 3 2022
pubmed: 29 3 2022
medline: 29 3 2022
Statut: ppublish

Résumé

Atopic dermatitis (AD) is a chronic inflammatory skin disease leading to substantial quality of life impairment with heterogeneous treatment responses. People with AD would benefit from personalised treatment strategies, whose design requires predicting how AD severity evolves for each individual. This study aims to develop a computational framework for personalised prediction of AD severity dynamics. We introduced EczemaPred, a computational framework to predict patient-dependent dynamic evolution of AD severity using Bayesian state-space models that describe latent dynamics of AD severity items and how they are measured. We used EczemaPred to predict the dynamic evolution of validated patient-oriented scoring atopic dermatitis (PO-SCORAD) by combining predictions from the models for the nine severity items of PO-SCORAD (six intensity signs, extent of eczema, and two subjective symptoms). We validated this approach using longitudinal data from two independent studies: a published clinical study in which PO-SCORAD was measured twice weekly for 347 AD patients over 17 weeks, and another one in which PO-SCORAD was recorded daily by 16 AD patients for 12 weeks. EczemaPred achieved good performance for personalised predictions of PO-SCORAD and its severity items daily to weekly. EczemaPred outperformed standard time-series forecasting models such as a mixed effect autoregressive model. The uncertainty in predicting PO-SCORAD was mainly attributed to that in predicting intensity signs (75% of the overall uncertainty). EczemaPred serves as a computational framework to make a personalised prediction of AD severity dynamics relevant to clinical practice. EczemaPred is available as an R package.

Sections du résumé

BACKGROUND BACKGROUND
Atopic dermatitis (AD) is a chronic inflammatory skin disease leading to substantial quality of life impairment with heterogeneous treatment responses. People with AD would benefit from personalised treatment strategies, whose design requires predicting how AD severity evolves for each individual.
OBJECTIVE OBJECTIVE
This study aims to develop a computational framework for personalised prediction of AD severity dynamics.
METHODS METHODS
We introduced EczemaPred, a computational framework to predict patient-dependent dynamic evolution of AD severity using Bayesian state-space models that describe latent dynamics of AD severity items and how they are measured. We used EczemaPred to predict the dynamic evolution of validated patient-oriented scoring atopic dermatitis (PO-SCORAD) by combining predictions from the models for the nine severity items of PO-SCORAD (six intensity signs, extent of eczema, and two subjective symptoms). We validated this approach using longitudinal data from two independent studies: a published clinical study in which PO-SCORAD was measured twice weekly for 347 AD patients over 17 weeks, and another one in which PO-SCORAD was recorded daily by 16 AD patients for 12 weeks.
RESULTS RESULTS
EczemaPred achieved good performance for personalised predictions of PO-SCORAD and its severity items daily to weekly. EczemaPred outperformed standard time-series forecasting models such as a mixed effect autoregressive model. The uncertainty in predicting PO-SCORAD was mainly attributed to that in predicting intensity signs (75% of the overall uncertainty).
CONCLUSIONS CONCLUSIONS
EczemaPred serves as a computational framework to make a personalised prediction of AD severity dynamics relevant to clinical practice. EczemaPred is available as an R package.

Identifiants

pubmed: 35344305
doi: 10.1002/clt2.12140
pmc: PMC8967258
doi:

Types de publication

Journal Article

Langues

eng

Pagination

e12140

Subventions

Organisme : British Skin Foundation
ID : 005R18
Organisme : Association Centre Nantais de Recherche Appliquée aux Affections Cutanées
Organisme : Laboratoires Dermatologiques Avène
Organisme : Eczema Foundation

Informations de copyright

© 2022 The Authors. Clinical and Translational Allergy published by John Wiley & Sons Ltd on behalf of European Academy of Allergy and Clinical Immunology.

Références

Br J Dermatol. 2017 Apr;176(4):979-984
pubmed: 27858989
Arch Dermatol. 2004 Dec;140(12):1513-9
pubmed: 15611432
J Allergy Clin Immunol. 2007 Dec;120(6):1389-98
pubmed: 17910890
J Am Acad Dermatol. 2020 May;82(5):1181-1186
pubmed: 31926221
J Allergy Clin Immunol. 2014 Oct;134(4):800-7
pubmed: 25282560
Clin Exp Allergy. 2020 Nov;50(11):1258-1266
pubmed: 32750186
Allergy. 2011 Aug;66(8):1114-21
pubmed: 21414011
Clin Transl Allergy. 2022 Mar;12(3):e12140
pubmed: 35344305
Br J Dermatol. 1999 Jan;140(1):109-11
pubmed: 10215778
Lancet. 2016 Mar 12;387(10023):1109-1122
pubmed: 26377142
Dermatology. 2009;218(3):246-51
pubmed: 19147989
J Stat Softw. 2017;76:
pubmed: 36568334
Br J Dermatol. 1996 Sep;135 Suppl 48:25-30
pubmed: 8881901
J Eur Acad Dermatol Venereol. 2018 Jul;32(7):1180-1187
pubmed: 29419920
Exp Dermatol. 2001 Feb;10(1):11-8
pubmed: 11168575
J Allergy Clin Immunol. 2016 May;137(5):1289-300
pubmed: 27155026
Dermatology. 1993;186(1):23-31
pubmed: 8435513
J Allergy Clin Immunol. 2017 Apr;139(4S):S58-S64
pubmed: 28390478

Auteurs

Guillem Hurault (G)

Department of Bioengineering, Imperial College London, London, UK.

Jean François Stalder (JF)

Clinique Dermatologique University Hospital, Nantes, France.

Sophie Mery (S)

Pierre Fabre Laboratories, Toulouse, France.

Alain Delarue (A)

Pierre Fabre Laboratories, Toulouse, France.

Markéta Saint Aroman (M)

Pierre Fabre Laboratories, Toulouse, France.

Gwendal Josse (G)

Pierre Fabre Laboratories, Toulouse, France.

Reiko J Tanaka (RJ)

Department of Bioengineering, Imperial College London, London, UK.

Classifications MeSH