Application of unsupervised machine learning in cluster analysis in patients with rheumatoid arthrit

The concept of health management is becoming increasingly popular, and scientific health knowledge is gaining widespread attention. RA patients face a significant increase in the risk of cardiovascular disease (CV), but the existing 10-year estimation tools often do not perform well. The study evaluated whether the uML cluster can identify specific disease patterns associated with different major cardiovascular events (MACE) associated with RA patients, while following up on the MACE incidence rate for more than five years.

This study included RA patients who met the 2010 ACR/EULAR classification criteria in January 2019 and followed up with their MACE incidence over 5 years. Through this study, we assessed the superiority of unsupervised machine learning (uML) clusters in identifying specific RA patient disease patterns and followed up with MACE incidence over 5 years in order to provide more scientific evidence and reference methods for disease management in RA patients. Clinical data (including conventional CV risk factors and SCORE2 estimates) and demographic data (including conventional CV risk factors and SCORE2 estimates) are collected.

Bootstrapized eigenvalue distribution determined the number of FAMD components for clustering, followed by Hierarchical Clustering on Principal Components using Ward's criterion and Euclidean distance . An XGBoost model a. It should be noted that the above content is based on international public research findings and is for reference in HealthCop and does not constitute a clinical recommendation.

If you have any health questions, please consult professional medical professionals.