Multilevel Modeling of Joint Damage in Rheumatoid Arthritis

While most deep learning approaches are developed for single images, in real‐world applications, images are often obtained as a series to inform decision‐making. Due to hardware (memory) and software (algorithm) limitations, few methods have been developed to integrate multiple images so far. Herein...

Full description

Bibliographic Details
Main Authors: Hongyang Li, Yuanfang Guan
Format: Article
Language:English
Published: Wiley 2022-11-01
Series:Advanced Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1002/aisy.202200184
_version_ 1811179798751346688
author Hongyang Li
Yuanfang Guan
author_facet Hongyang Li
Yuanfang Guan
author_sort Hongyang Li
collection DOAJ
description While most deep learning approaches are developed for single images, in real‐world applications, images are often obtained as a series to inform decision‐making. Due to hardware (memory) and software (algorithm) limitations, few methods have been developed to integrate multiple images so far. Herein, an approach that seamlessly integrates deep learning and traditional machine learning models is presented, to study multiple images and score joint damages in rheumatoid arthritis. This method allows the quantification of joining space narrowing to approach the clinical upper limit. Beyond predictive performance, the multilevel interconnections across joints and damage types into the machine learning model are integrated and the crossregulation map of joint damages in rheumatoid arthritis is revealed. An interactive preprint version of the article can be found at https://doi.org/10.22541/au.165828097.71839600/v1.
first_indexed 2024-04-11T06:39:39Z
format Article
id doaj.art-b87f8062db044ff485347b90ca806a43
institution Directory Open Access Journal
issn 2640-4567
language English
last_indexed 2024-04-11T06:39:39Z
publishDate 2022-11-01
publisher Wiley
record_format Article
series Advanced Intelligent Systems
spelling doaj.art-b87f8062db044ff485347b90ca806a432022-12-22T04:39:34ZengWileyAdvanced Intelligent Systems2640-45672022-11-01411n/an/a10.1002/aisy.202200184Multilevel Modeling of Joint Damage in Rheumatoid ArthritisHongyang Li0Yuanfang Guan1Department of Computational Medicine and Bioinformatics University of Michigan 100 Washtenaw Avenue Ann Arbor MI 48109 USADepartment of Computational Medicine and Bioinformatics University of Michigan 100 Washtenaw Avenue Ann Arbor MI 48109 USAWhile most deep learning approaches are developed for single images, in real‐world applications, images are often obtained as a series to inform decision‐making. Due to hardware (memory) and software (algorithm) limitations, few methods have been developed to integrate multiple images so far. Herein, an approach that seamlessly integrates deep learning and traditional machine learning models is presented, to study multiple images and score joint damages in rheumatoid arthritis. This method allows the quantification of joining space narrowing to approach the clinical upper limit. Beyond predictive performance, the multilevel interconnections across joints and damage types into the machine learning model are integrated and the crossregulation map of joint damages in rheumatoid arthritis is revealed. An interactive preprint version of the article can be found at https://doi.org/10.22541/au.165828097.71839600/v1.https://doi.org/10.1002/aisy.202200184deep learningmachine learningrheumatoid arthritis
spellingShingle Hongyang Li
Yuanfang Guan
Multilevel Modeling of Joint Damage in Rheumatoid Arthritis
Advanced Intelligent Systems
deep learning
machine learning
rheumatoid arthritis
title Multilevel Modeling of Joint Damage in Rheumatoid Arthritis
title_full Multilevel Modeling of Joint Damage in Rheumatoid Arthritis
title_fullStr Multilevel Modeling of Joint Damage in Rheumatoid Arthritis
title_full_unstemmed Multilevel Modeling of Joint Damage in Rheumatoid Arthritis
title_short Multilevel Modeling of Joint Damage in Rheumatoid Arthritis
title_sort multilevel modeling of joint damage in rheumatoid arthritis
topic deep learning
machine learning
rheumatoid arthritis
url https://doi.org/10.1002/aisy.202200184
work_keys_str_mv AT hongyangli multilevelmodelingofjointdamageinrheumatoidarthritis
AT yuanfangguan multilevelmodelingofjointdamageinrheumatoidarthritis