Related Experiment Video
Updated: Jul 31, 2025
Measurements of Motor Function and Other Clinical Outcome Parameters in Ambulant Children with Duchenne Muscular Dystrophy
Published on: January 12, 2019
A machine learning analysis to evaluate the outcome measures in inflammatory myopathies
Maria Giovanna Danieli1, Alberto Paladini2, Eleonora Longhi3
1SOS Immunologia delle Malattie Rare e dei Trapianti, AOU delle Marche & Dipartimento di Scienze Cliniche e Molecolari, Università Politecnica delle Marche, via Tronto 10/A, 60126 Torrette di Ancona, Italy; Postgraduate School of Allergy and Clinical Immunology, Università Politecnica delle Marche, via Tronto 10/A, 60126 Ancona, Italy.
Objective:
To assess the long-term outcome in patients with Idiopathic Inflammatory Myopathies (IIM), focusing on damage and activity disease indexes using artificial intelligence (AI).
Background:
IIM are a group of rare diseases characterized by involvement of different organs in addition to the musculoskeletal. Machine Learning analyses large amounts of information, using different algorithms, decision-making processes and self-learning neural networks.
Methods:
We evaluate the long-term outcome of 103 patients with IIM, diagnosed on 2017 EULAR/ACR criteria. We considered different parameters, including clinical manifestations and organ involvement, number and type of treatments, serum creatine kinase levels, muscle strength (MMT8 score), disease activity (MITAX score), disability (HAQ-DI score), disease damage (MDI score), and physician and patient global assessment (PGA). The data collected were analysed, applying, with R, supervised ML algorithms such as lasso, ridge, elastic net, classification, and regression trees (CART), random forest and support vector machines (SVM) to find the factors that best predict disease outcome.
Results And Conclusion:
Using artificial intelligence algorithms we identified the parameters that best correlate with the disease outcome in IIM. The best result was on MMT8 at follow-up, predicted by a CART regression tree algorithm. MITAX was predicted based on clinical features such as the presence of RP-ILD and skin involvement. A good predictive capacity was also demonstrated on damage scores: MDI and HAQ-DI. In the future Machine Learning will allow us to identify the strengths or weaknesses of the composite disease activity and damage scores, to validate new criteria or to implement classification criteria.
