Interstitial lung disease diagnosis and prognosis using an AI system integrating longitudinal data

Xueyan Mei (), Zelong Liu, Ayushi Singh, Marcia Lange, Priyanka Boddu, Jingqi Q. X. Gong, Justine Lee, Cody DeMarco, Chendi Cao, Samantha Platt, Ganesh Sivakumar, Benjamin Gross, Mingqian Huang, Joy Masseaux, Sakshi Dua, Adam Bernheim, Michael Chung, Timothy Deyer, Adam Jacobi, Maria Padilla, Zahi A. Fayad () and Yang Yang ()
Additional contact information
Xueyan Mei: Icahn School of Medicine at Mount Sinai
Zelong Liu: Icahn School of Medicine at Mount Sinai
Ayushi Singh: Icahn School of Medicine at Mount Sinai
Marcia Lange: Icahn School of Medicine at Mount Sinai
Priyanka Boddu: Icahn School of Medicine at Mount Sinai
Jingqi Q. X. Gong: Icahn School of Medicine at Mount Sinai
Justine Lee: Icahn School of Medicine at Mount Sinai
Cody DeMarco: Icahn School of Medicine at Mount Sinai
Chendi Cao: Icahn School of Medicine at Mount Sinai
Samantha Platt: Icahn School of Medicine at Mount Sinai
Ganesh Sivakumar: Icahn School of Medicine at Mount Sinai
Benjamin Gross: Icahn School of Medicine at Mount Sinai
Mingqian Huang: Icahn School of Medicine at Mount Sinai
Joy Masseaux: Icahn School of Medicine at Mount Sinai
Sakshi Dua: Critical Care and Sleep Medicine, Icahn School of Medicine at Mount Sinai
Adam Bernheim: Icahn School of Medicine at Mount Sinai
Michael Chung: Icahn School of Medicine at Mount Sinai
Timothy Deyer: Cornell Medicine
Adam Jacobi: Icahn School of Medicine at Mount Sinai
Maria Padilla: Critical Care and Sleep Medicine, Icahn School of Medicine at Mount Sinai
Zahi A. Fayad: Icahn School of Medicine at Mount Sinai
Yang Yang: Icahn School of Medicine at Mount Sinai

Nature Communications, 2023, vol. 14, issue 1, 1-11

Abstract: Abstract For accurate diagnosis of interstitial lung disease (ILD), a consensus of radiologic, pathological, and clinical findings is vital. Management of ILD also requires thorough follow-up with computed tomography (CT) studies and lung function tests to assess disease progression, severity, and response to treatment. However, accurate classification of ILD subtypes can be challenging, especially for those not accustomed to reading chest CTs regularly. Dynamic models to predict patient survival rates based on longitudinal data are challenging to create due to disease complexity, variation, and irregular visit intervals. Here, we utilize RadImageNet pretrained models to diagnose five types of ILD with multimodal data and a transformer model to determine a patient’s 3-year survival rate. When clinical history and associated CT scans are available, the proposed deep learning system can help clinicians diagnose and classify ILD patients and, importantly, dynamically predict disease progression and prognosis.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-023-37720-5 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-37720-5

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-023-37720-5

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().