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

Abstract

Background 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. 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. Objective The 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. Methods The 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. Results To 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. Conclusions The 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.

Detecting Bulbar Involvement in Patients with Amyotrophic Lateral Sclerosis Based on Phonatory and Time-Frequency Features

“…This indicates that some participants in the NB group were probably incorrectly diagnosed. This is coherent with [ 6 ]. Similarly, the excellent performance achieved in C vs. A suggests that some of the members of A (14 out of 47) have bulbar involvement.…”

“…A total of 15 features from the phonatory subsystem defined in [ 6 , 13 ] were used. They were computed by means of the standard methods used in Praat [ 29 ] and the setting details used were the same as in [ 6 ]. These features were: Fundamental period cycle-to-cycle variation ( Jitter(absolute) , Equation ( 2 )).…”

“…The classification algorithms used were the most popular ones in ALS: Support Vector Machine (SVM), Neural Networks (NN), Linear Discriminant Analysis (LDA), Logistic Regression (LR) and Random Forest (RF). For more details, see [ 6 ].…”

“…Among these were jitter, shimmer, harmonic-to-noise ratio (HNR), pitch, formant trajectories, correlations of formants with articulation patterns, fractal jitter, and Mel Frequency Cepstral Coefficients. Consequently, as suggested in previous works [ 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ], imperceptible changes in speech and voice can be detected through objective measures.…”

“…Based on previous works, and starting from our recent studies [ 6 , 18 ], our paper suggests using phonatory-subsystem [ 6 ] and time-frequency [ 18 ] features jointly. This also is our hypothesis and main contribution.…”