Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Predicting Type 1 Diabetes Onset using Novel Survival Analysis with Biomarker Ontology

Li, Ying ; Liu, Bin ; Anand, Vibha ; Dunne, Jessica L. ; Lundgren, Markus LU ; Ng, Kenney ; Rewers, Marian ; Veijola, Riitta LU and Ghalwash, Mohamed (2020) In AMIA ... Annual Symposium proceedings. AMIA Symposium 2020. p.727-736
Abstract

Type 1 diabetes (T1D) is a chronic autoimmune disease that affects about 1 in 300 children and up to 1 in 100 adults during their life-time1. Improvements in early prediction of T1D onset may help prevent diagnosis for diabetic ketoacidosis, a serious complication often associated with a missed or delayed T1D diagnosis. In addition to genetic factors, progression to T1D is strongly associated with immunologic factors that can be measured during clinical visits. We developed a T1D-specific ontology that captures the dynamic patterns of these biomarkers and used it together with a survival model, RankSvx, proposed in our prior work2. We applied this approach to a T1D dataset harmonized from three birth cohort studies from the United... (More)

Type 1 diabetes (T1D) is a chronic autoimmune disease that affects about 1 in 300 children and up to 1 in 100 adults during their life-time1. Improvements in early prediction of T1D onset may help prevent diagnosis for diabetic ketoacidosis, a serious complication often associated with a missed or delayed T1D diagnosis. In addition to genetic factors, progression to T1D is strongly associated with immunologic factors that can be measured during clinical visits. We developed a T1D-specific ontology that captures the dynamic patterns of these biomarkers and used it together with a survival model, RankSvx, proposed in our prior work2. We applied this approach to a T1D dataset harmonized from three birth cohort studies from the United States, Finland, and Sweden. Results show that the dynamic biomarker patterns captured in the proposed ontology are able to improve prediction performance (in concordance index) by 5.3%, 3.3%, 2.8%, and 1.0% over baseline for 3, 6, 9, and 12 month duration windows, respectively.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; and
author collaboration
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
AMIA ... Annual Symposium proceedings. AMIA Symposium
volume
2020
pages
10 pages
publisher
American Medical Informatics Association
external identifiers
  • pmid:33936447
  • scopus:85105334324
ISSN
1942-597X
language
English
LU publication?
yes
id
49d62de2-c5ef-4275-945e-947e814d422d
date added to LUP
2021-06-01 14:12:58
date last changed
2024-04-06 04:44:16
@article{49d62de2-c5ef-4275-945e-947e814d422d,
  abstract     = {{<p>Type 1 diabetes (T1D) is a chronic autoimmune disease that affects about 1 in 300 children and up to 1 in 100 adults during their life-time1. Improvements in early prediction of T1D onset may help prevent diagnosis for diabetic ketoacidosis, a serious complication often associated with a missed or delayed T1D diagnosis. In addition to genetic factors, progression to T1D is strongly associated with immunologic factors that can be measured during clinical visits. We developed a T1D-specific ontology that captures the dynamic patterns of these biomarkers and used it together with a survival model, RankSvx, proposed in our prior work2. We applied this approach to a T1D dataset harmonized from three birth cohort studies from the United States, Finland, and Sweden. Results show that the dynamic biomarker patterns captured in the proposed ontology are able to improve prediction performance (in concordance index) by 5.3%, 3.3%, 2.8%, and 1.0% over baseline for 3, 6, 9, and 12 month duration windows, respectively.</p>}},
  author       = {{Li, Ying and Liu, Bin and Anand, Vibha and Dunne, Jessica L. and Lundgren, Markus and Ng, Kenney and Rewers, Marian and Veijola, Riitta and Ghalwash, Mohamed}},
  issn         = {{1942-597X}},
  language     = {{eng}},
  pages        = {{727--736}},
  publisher    = {{American Medical Informatics Association}},
  series       = {{AMIA ... Annual Symposium proceedings. AMIA Symposium}},
  title        = {{Predicting Type 1 Diabetes Onset using Novel Survival Analysis with Biomarker Ontology}},
  volume       = {{2020}},
  year         = {{2020}},
}