Skip to main content

Research Repository

Advanced Search

Machine learning can predict disease manifestations and outcomes in lymphangioleiomyomatosis

Chernbumroong, Saisakul; Johnson, Janice; Gupta, Nishant; Miller, Suzanne; Mccormack, Francis X.; Garibaldi, Jonathan M; Johnson, Simon R

Machine learning can predict disease manifestations and outcomes in lymphangioleiomyomatosis Thumbnail


Saisakul Chernbumroong

Janice Johnson

Nishant Gupta

Senior Clinical Studies and Project Manager

Francis X. Mccormack

Professor of Respiratory Medicine


Saisakul Chernbumroong

Janice Johnson

Nishant Gupta

Francis X. McCormack


Background: Lymphangioleiomyomatosis (LAM) is a rare multisystem disease with variable clinical manifestations and differing rates of progression that make management decisions and giving prognostic advice difficult. We used machine learning to identify clusters of associated features which could be used to stratify patients and predict outcomes in individuals. Patients and methods: Using unsupervised machine learning we generated patient clusters using data from 173 women with LAM from the UK and 186 replication subjects from the US National Heart, Lung, and Blood Institute (NHLBI) LAM registry. Prospective outcomes were associated with cluster results. Results: Two- and three-cluster models were developed. A three-cluster model separated a large group of subjects presenting with dyspnoea or pneumothorax from a second cluster with a high prevalence of angiomyolipoma symptoms (p=0.0001) and tuberous sclerosis complex (TSC) (p=0.041). Patients in the third cluster were older, never presented with dyspnoea or pneumothorax (p=0.0001) and had better lung function. Similar clusters were reproduced in the NHLBI cohort. Assigning patients to clusters predicted prospective outcomes: in a two-cluster model the future risk of pneumothorax was 3.3 (95% CI 1.7-5.6)-fold greater in cluster 1 than cluster 2 (p=0.0002). Using the three-cluster model, the need for intervention for angiomyolipoma was lower in clusters 2 and 3 than cluster 1 (p<0.00001). In the NHLBI cohort, the incidence of death or lung transplant was much lower in clusters 2 and 3 (p=0.0045). Conclusions: Machine learning has identified clinically relevant clusters associated with complications and outcome. Assigning individuals to clusters could improve decision making and prognostic information for patients.


Chernbumroong, S., Johnson, J., Gupta, N., Miller, S., Mccormack, F. X., Garibaldi, J. M., & Johnson, S. R. (2021). Machine learning can predict disease manifestations and outcomes in lymphangioleiomyomatosis. European Respiratory Journal, 57(6), Article 2003036.

Journal Article Type Article
Acceptance Date Oct 1, 2020
Online Publication Date Dec 10, 2020
Publication Date Jun 1, 2021
Deposit Date Nov 27, 2020
Publicly Available Date Dec 11, 2021
Journal European Respiratory Journal
Print ISSN 0903-1936
Electronic ISSN 1399-3003
Publisher European Respiratory Society
Peer Reviewed Peer Reviewed
Volume 57
Issue 6
Article Number 2003036
Keywords Pulmonary and Respiratory Medicine
Public URL
Publisher URL
Additional Information This is an author-submitted, peer-reviewed version of a manuscript that has been accepted for publication in the European Respiratory Journal, prior to copy-editing, formatting and typesetting. This version of the manuscript may not be duplicated or reproduced without prior permission from the copyright owner, the European Respiratory Society. The publisher is not responsible or liable for any errors or omissions in this version of the manuscript or in any version derived from it by any other parties. The final, copy-edited, published article, which is the version of record, is available without a subscription 18 months after the date of issue publication.


You might also like

Downloadable Citations