Machine learning-enhanced electrical impedance myography to diagnose and track spinal muscular atrophy progression.


To evaluate electrical impedance myography (EIM) in conjunction with machine learning to detect infantile spinal muscular atrophy (SMA) and disease progression.
Approach:
Twenty-six infants with SMA and twenty-seven healthy infants had been enrolled and assessed with EIM as part of the NeuroNEXT SMA biomarker study. We applied a variety of modern, supervised machine learning approaches to this data, first seeking to differentiate healthy from SMA muscle, and then, using the best method, to track SMA progression.
Main Results:
Several of the machine learning algorithms worked well, but linear discriminant analysis (LDA) achieved 100% accuracy on several of the individual muscles studied. This contrasts with a maximum of 66% accuracy that was achieved using the single or multifrequency assessment approaches available at the time. LDA scores were also able to track progression effectively, although a multifrequency reactance-based measure also performed very well in this context.
Significance:
EIM enhanced with machine learning promises to be effective for providing early diagnosis and tracking children and adults with SMA treated with currently available therapies. The normative values and trends identified here will also be valuable for other pediatric applications of the technology. The basic analyses applied here could also likely be applied to other neuromuscular disorders characterized by muscle atrophy.&#xD.