Predictive models in SMA II natural history trajectories using machine learning: A proof of concept study

• Published in: PloS one Vol. 17; no. 5; p. e0267930
• Main Authors: Coratti, Giorgia, Lenkowicz, Jacopo, Patarnello, Stefano, Gullì, Consolato, Pera, Maria Carmela, Masciocchi, Carlotta, Rinaldi, Riccardo, Lovato, Valeria, Leone, Antonio, Cesario, Alfredo, Mercuri, Eugenio
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 05.05.2022; Public Library of Science (PLoS)
• Subjects: Age; Algorithms; Analysis; Artificial Intelligence; Atrophy; Biology and Life Sciences; Care and treatment; Child, Preschool; Computer and Information Sciences; Concept learning; Datasets; Diagnosis; Humans; Learning algorithms; Machine Learning; Medicine and Health Sciences; Muscular Atrophy, Spinal - diagnosis; Natural history; Neuromuscular diseases; Nutritional status; Patients; People and Places; Physical Sciences; Prediction models; Proof of Concept Study; Puberty; Research and Analysis Methods; Spinal Muscular Atrophies of Childhood; Spinal muscular atrophy; Values; Variables; Ventilation; Italy
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0267930

It is known from previous literature that type II Spinal Muscular Atrophy (SMA) patients generally, after the age of 5 years, presents a steep deterioration until puberty followed by a relative stability, as most abilities have been lost. Although it is possible to identify points of slope indicating early improvement, steep decline and relative stabilizations, there is still a lot of variability within each age group and it's not always possible to predict individual trajectories of progression from age only. The aim of the study was to develop a predictive model based on machine learning using an XGBoost algorithm for regression and report, explore and quantify, in a single centre longitudinal natural history study, the influence of clinical variables on the 6/12-months Hammersmith Motor Functional Scale Expanded score prediction (HFMSE). This study represents the first approach to artificial intelligence and trained models for the prediction of individualized trajectories of HFMSE disease progression using individual characteristics of the patient. The application of this method to larger cohorts may allow to identify different classes of progression, a crucial information at the time of the new commercially available therapies.