Machine Learning in Antibody Diagnostics for Inflammatory Bowel Disease Subtype Classification
Antibody testing in inflammatory bowel disease (IBD) can add to diagnostic accuracy of the main subtypes Crohn’s disease (CD) and ulcerative colitis (UC). Whether modern modeling techniques such as supervised and unsupervised machine learning are of value for finer distinction of subtypes such as IB...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/13/15/2491 |
_version_ | 1797586898039865344 |
---|---|
author | Christiane Sokollik Aurélie Pahud de Mortanges Alexander B. Leichtle Pascal Juillerat Michael P. Horn |
author_facet | Christiane Sokollik Aurélie Pahud de Mortanges Alexander B. Leichtle Pascal Juillerat Michael P. Horn |
author_sort | Christiane Sokollik |
collection | DOAJ |
description | Antibody testing in inflammatory bowel disease (IBD) can add to diagnostic accuracy of the main subtypes Crohn’s disease (CD) and ulcerative colitis (UC). Whether modern modeling techniques such as supervised and unsupervised machine learning are of value for finer distinction of subtypes such as IBD-unclassified (IBD-U) is not known. We determined the antibody profile of 100 adult IBD patients from the Swiss IBD cohort study with known subtype (50 CD, 50 UC) as well as of 76 IBD-U patients. We included ASCA IgG and IgA, p-ANCA, MPO- and PR3-ANCA, and xANCA measurements for computing different antibody panels as well as machine learning models. The AUC of an optimized antibody panel was 85% (95%CI, 78–92%) to distinguish CD from UC patients. The antibody profile of IBD-U patients was closely related to UC. No specific antibody profile was predictive for IBD-U nor for re-classification. The panel diagnostic was in favor of UC reclassification prediction with a correct assignment rate of 69.2–73.1% depending on the cut-off applied. Supervised machine learning could not distinguish between CD, UC, and IBD-U. More so, unsupervised machine learning suggested only two distinct clusters as a likely number of IBD subtypes. Antibodies in IBD are supportive in confirming clinical determined subtypes CD and UC but have limited capacity to predict IBD-U and reclassification during follow-up. In terms of antibody profiles, IBD-U is not a distinct subtype of IBD. |
first_indexed | 2024-03-11T00:29:41Z |
format | Article |
id | doaj.art-b02f4a34c2b54f90bd9932ddea33b772 |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-11T00:29:41Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-b02f4a34c2b54f90bd9932ddea33b7722023-11-18T22:46:14ZengMDPI AGDiagnostics2075-44182023-07-011315249110.3390/diagnostics13152491Machine Learning in Antibody Diagnostics for Inflammatory Bowel Disease Subtype ClassificationChristiane Sokollik0Aurélie Pahud de Mortanges1Alexander B. Leichtle2Pascal Juillerat3Michael P. Horn4Division of Pediatric Gastroenterology, Hepatology and Nutrition, University Children’s Hospital, Inselspital, University of Bern, 3010 Bern, SwitzerlandARTORG Center for Biomedical Engineering Research, University of Bern, 3010 Bern, SwitzerlandDepartment of Clinical Chemistry, Inselspital, Bern University Hospital, University of Bern, 3010 Bern, SwitzerlandDepartment of Gastroenterology, Clinic for Visceral Surgery and Medicine, Inselspital, Bern University Hospital, University of Bern, 3010 Bern, SwitzerlandDepartment of Clinical Chemistry, Inselspital, Bern University Hospital, University of Bern, 3010 Bern, SwitzerlandAntibody testing in inflammatory bowel disease (IBD) can add to diagnostic accuracy of the main subtypes Crohn’s disease (CD) and ulcerative colitis (UC). Whether modern modeling techniques such as supervised and unsupervised machine learning are of value for finer distinction of subtypes such as IBD-unclassified (IBD-U) is not known. We determined the antibody profile of 100 adult IBD patients from the Swiss IBD cohort study with known subtype (50 CD, 50 UC) as well as of 76 IBD-U patients. We included ASCA IgG and IgA, p-ANCA, MPO- and PR3-ANCA, and xANCA measurements for computing different antibody panels as well as machine learning models. The AUC of an optimized antibody panel was 85% (95%CI, 78–92%) to distinguish CD from UC patients. The antibody profile of IBD-U patients was closely related to UC. No specific antibody profile was predictive for IBD-U nor for re-classification. The panel diagnostic was in favor of UC reclassification prediction with a correct assignment rate of 69.2–73.1% depending on the cut-off applied. Supervised machine learning could not distinguish between CD, UC, and IBD-U. More so, unsupervised machine learning suggested only two distinct clusters as a likely number of IBD subtypes. Antibodies in IBD are supportive in confirming clinical determined subtypes CD and UC but have limited capacity to predict IBD-U and reclassification during follow-up. In terms of antibody profiles, IBD-U is not a distinct subtype of IBD.https://www.mdpi.com/2075-4418/13/15/2491Crohn’s diseaseulcerative colitisPR3-ANCAserologyASCA |
spellingShingle | Christiane Sokollik Aurélie Pahud de Mortanges Alexander B. Leichtle Pascal Juillerat Michael P. Horn Machine Learning in Antibody Diagnostics for Inflammatory Bowel Disease Subtype Classification Diagnostics Crohn’s disease ulcerative colitis PR3-ANCA serology ASCA |
title | Machine Learning in Antibody Diagnostics for Inflammatory Bowel Disease Subtype Classification |
title_full | Machine Learning in Antibody Diagnostics for Inflammatory Bowel Disease Subtype Classification |
title_fullStr | Machine Learning in Antibody Diagnostics for Inflammatory Bowel Disease Subtype Classification |
title_full_unstemmed | Machine Learning in Antibody Diagnostics for Inflammatory Bowel Disease Subtype Classification |
title_short | Machine Learning in Antibody Diagnostics for Inflammatory Bowel Disease Subtype Classification |
title_sort | machine learning in antibody diagnostics for inflammatory bowel disease subtype classification |
topic | Crohn’s disease ulcerative colitis PR3-ANCA serology ASCA |
url | https://www.mdpi.com/2075-4418/13/15/2491 |
work_keys_str_mv | AT christianesokollik machinelearninginantibodydiagnosticsforinflammatoryboweldiseasesubtypeclassification AT aureliepahuddemortanges machinelearninginantibodydiagnosticsforinflammatoryboweldiseasesubtypeclassification AT alexanderbleichtle machinelearninginantibodydiagnosticsforinflammatoryboweldiseasesubtypeclassification AT pascaljuillerat machinelearninginantibodydiagnosticsforinflammatoryboweldiseasesubtypeclassification AT michaelphorn machinelearninginantibodydiagnosticsforinflammatoryboweldiseasesubtypeclassification |