Detection of Bulbar Involvement in Patients With Amyotrophic Lateral Sclerosis by Machine Learning Voice Analysis: Diagnostic Decision Support Development Study.

Alberto Tena,Francec Claria,Monica Povedano,Francesc Solsona,Einar Meister

doi:10.2196/21331

Abstract

BackgroundBulbar involvement is a term used in amyotrophic lateral sclerosis (ALS) that refers to motor neuron impairment in the corticobulbar area of the brainstem, which produces a dysfunction of speech and swallowing. One of the earliest symptoms of bulbar involvement is voice deterioration characterized by grossly defective articulation; extremely slow, laborious speech; marked hypernasality; and severe harshness. Bulbar involvement requires well-timed and carefully coordinated interventions. Therefore, early detection is crucial to improving the quality of life and lengthening the life expectancy of patients with ALS who present with this dysfunction. Recent research efforts have focused on voice analysis to capture bulbar involvement.ObjectiveThe main objective of this paper was (1) to design a methodology for diagnosing bulbar involvement efficiently through the acoustic parameters of uttered vowels in Spanish, and (2) to demonstrate that the performance of the automated diagnosis of bulbar involvement is superior to human diagnosis.MethodsThe study focused on the extraction of features from the phonatory subsystem—jitter, shimmer, harmonics-to-noise ratio, and pitch—from the utterance of the five Spanish vowels. Then, we used various supervised classification algorithms, preceded by principal component analysis of the features obtained.ResultsTo date, support vector machines have performed better (accuracy 95.8%) than the models analyzed in the related work. We also show how the model can improve human diagnosis, which can often misdiagnose bulbar involvement.ConclusionsThe results obtained are very encouraging and demonstrate the efficiency and applicability of the automated model presented in this paper. It may be an appropriate tool to help in the diagnosis of ALS by multidisciplinary clinical teams, in particular to improve the diagnosis of bulbar involvement.

Highlights

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease with an irregular and asymmetric progression, characterized by a progressive loss of both upper and lower motor neurons that leads to muscular atrophy, paralysis, and death, mainly from respiratory failure
To date, support vector machines have performed better than the models analyzed in the related work
This paper suggests that machine learning may be an appropriate tool to help in the diagnosis of amyotrophic lateral sclerosis (ALS) by multidisciplinary clinical teams

Summary

Introduction

Background Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease with an irregular and asymmetric progression, characterized by a progressive loss of both upper and lower motor neurons that leads to muscular atrophy, paralysis, and death, mainly from respiratory failure. The disease is referred to as spinal ALS when the first symptoms appear in the arms and legs (limb or spinal onset; 80% of cases) and bulbar ALS when it begins in cranial nerve nuclei (bulbar onset; 20% of cases). Patients with the latter form tend to have a shorter life span because of the critical nature of the bulbar muscle function that is responsible for speech and swallowing. Bulbar involvement is a term used in amyotrophic lateral sclerosis (ALS) that refers to motor neuron impairment in the corticobulbar area of the brainstem, which produces a dysfunction of speech and swallowing. Recent research efforts have focused on voice analysis to capture bulbar involvement

Methods

Results

Discussion

Conclusion