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

Abstract

The term “bulbar involvement” is employed in ALS to refer to deterioration of motor neurons within the corticobulbar area of the brainstem, which results in speech and swallowing dysfunctions. One of the primary symptoms is a deterioration of the voice. Early detection is crucial for improving the quality of life and lifespan of ALS patients suffering from bulbar involvement. The main objective, and the principal contribution, of this research, was to design a new methodology, based on the phonatory-subsystem and time-frequency characteristics for detecting bulbar involvement automatically. This study focused on providing a set of 50 phonatory-subsystem and time-frequency features to detect this deficiency in males and females through the utterance of the five Spanish vowels. Multivariant Analysis of Variance was then used to select the statistically significant features, and the most common supervised classifications models were analyzed. A set of statistically significant features was obtained for males and females to capture this dysfunction. To date, the accuracy obtained (98.01% for females and 96.10% for males employing a random forest) outperformed the models in the literature. Adding time-frequency features to more classical phonatory-subsystem features increases the prediction capabilities of the machine-learning models for detecting bulbar involvement. Studying men and women separately gives greater success. The proposed method can be deployed in any kind of recording device (i.e., smartphone).

Voiceprint and machine learning models for early detection of bulbar dysfunction in ALS

“…3% and a Speci f icity of 100 . 0% outperforming the results obtained by [9,10] . This suggests that having well-annotated patients is essential for properly assessing bulbar dysfunction in B vs. NB.…”

“…To date, only Tena et al [9,10] have conducted studies considering additional cases. In [9] , they used phonatory subsystem fea-tures, such as jitter, shimmer, harmonic-to-noise ratio and pitch and PCA.…”

“…In [9] , they used phonatory subsystem fea-tures, such as jitter, shimmer, harmonic-to-noise ratio and pitch and PCA. In [10] a set of time-frequency features were added to the analysis and better results were achieved. The performance of several machine learning models were evaluated considering four scenarios (C vs. B, C vs. NB, B vs. NB and C vs. A).…”

“…Great uncertainty in the annotated corpus of the ALS patients without bulbar involvement was found. In a more recent study [10] timefrequency features were added improving the results. Although all methods performed well in general, this performance dropped significantly when diagnosing bulbar involvement among ALS patients.…”

Detecting bulbar amyotrophic lateral sclerosis (ALS) using automatic acoustic analysis

“…Additional differences included our preponderance of ALS patients vs. controls (119 patients vs 22 controls) as compared to the inverse in Neumann’s work (29 patients vs 68 controls). Higher performance of voice-based classification has been reported [ 35 , 39 ], but these either did not stratify patients into groups, or included mel-frequency cepstral coefficients, that we did not include in the present work because of the difficulty in their clinical interpretation.…”