An algorithm for Parkinson's disease speech classification based on isolated words analysis

On the inter-dataset generalization of machine learning approaches to Parkinson's disease detection from voice

BACKGROUND AND OBJECTIVE

Parkinson's disease is the second-most-common neurodegenerative disorder that affects motor skills, cognitive processes, mood, and everyday tasks such as speaking and walking. The voices of people with Parkinson's disease may become weak, breathy, or hoarse and may sound emotionless, with slurred words and mumbling. Algorithms for computerized voice analysis have been proposed and have shown highly accurate results. However, these algorithms were developed on single, limited datasets, with participants possessing similar demographics. Such models are prone to overfitting and are unsuitable for generalization, which is essential in real-world applications.

METHODS

We evaluated the computerized Parkinson's disease diagnosis performance of various machine learning models and showed that these models degraded rapidly when used on different datasets. We evaluated two mainstream state-of-the-art approaches, one based on deep convolutional neural networks and another based on voice feature extraction followed by a shallow classifier (i.e., extreme gradient boosting (XGBoost)).

RESULTS

An investigation with four datasets (CzechPD, PC-GITA, ITA, and RMIT-PD) proved that even if the algorithms yielded excellent performance on a single dataset, the results obtained on new data or even a mix of datasets were very unsatisfactory.

CONCLUSIONS

More work needs to be done to make computerized voice analysis methods for Parkinson's disease diagnosis suitable for real-world applications.

Keystroke Biometrics as a Tool for the Early Diagnosis and Clinical Assessment of Parkinson's Disease

(1) Background: Parkinson's disease (PD) is the second most common neurodegenerative disease. Early diagnosis and reliable clinical assessments are essential for appropriate therapy and improving patients' quality of life. Keystroke biometrics, which capture unique typing behavior, have shown potential for early PD diagnosis. This study aimed to evaluate keystroke biometric parameters from two datasets to identify indicators that can effectively distinguish de novo PD patients from healthy controls. (2) Methods: Data from natural typing tasks in Physionet were analyzed to estimate keystroke biometric parameters. The parameters investigated included alternating-finger tapping (afTap) and standard deviations of interkey latencies (ILSD) and release latencies (RLSD). Sensitivity rates were calculated to assess the discriminatory ability of these parameters. (3) Results: Significant differences were observed in three parameters, namely afTap, ILSD, and RLSD, between de novo PD patients and healthy controls. The sensitivity rates were high, with values of 83%, 88%, and 96% for afTap, ILSD, and RLSD, respectively. Correlation analysis revealed a significantly negative correlation between typing speed and number of words typed with the standard motor assessment for PD, UPDRS-III, in patients with early PD. (4) Conclusions: Simple algorithms utilizing keystroke biometric parameters can serve as effective screening tests in distinguishing de novo PD patients from healthy controls. Moreover, typing speed and number of words typed were identified as reliable tools for assessing clinical statuses in PD patients. These findings underscore the potential of keystroke biometrics for early PD diagnosis and clinical severity assessment.

Robust and language-independent acoustic features in Parkinson's disease

Introduction

The analysis of vocal samples from patients with Parkinson's disease (PDP) can be relevant in supporting early diagnosis and disease monitoring. Intriguingly, speech analysis embeds several complexities influenced by speaker characteristics (e.g., gender and language) and recording conditions (e.g., professional microphones or smartphones, supervised, or non-supervised data collection). Moreover, the set of vocal tasks performed, such as sustained phonation, reading text, or monologue, strongly affects the speech dimension investigated, the feature extracted, and, as a consequence, the performance of the overall algorithm.

Methods

We employed six datasets, including a cohort of 176 Healthy Control (HC) participants and 178 PDP from different nationalities (i.e., Italian, Spanish, Czech), recorded in variable scenarios through various devices (i.e., professional microphones and smartphones), and performing several speech exercises (i.e., vowel phonation, sentence repetition). Aiming to identify the effectiveness of different vocal tasks and the trustworthiness of features independent of external co-factors such as language, gender, and data collection modality, we performed several intra- and inter-corpora statistical analyses. In addition, we compared the performance of different feature selection and classification models to evaluate the most robust and performing pipeline.

Results

According to our results, the combined use of sustained phonation and sentence repetition should be preferred over a single exercise. As for the set of features, the Mel Frequency Cepstral Coefficients demonstrated to be among the most effective parameters in discriminating between HC and PDP, also in the presence of heterogeneous languages and acquisition techniques.

Conclusion

Even though preliminary, the results of this work can be exploited to define a speech protocol that can effectively capture vocal alterations while minimizing the effort required to the patient. Moreover, the statistical analysis identified a set of features minimally dependent on gender, language, and recording modalities. This discloses the feasibility of extensive cross-corpora tests to develop robust and reliable tools for disease monitoring and staging and PDP follow-up.

CNN-Based Identification of Parkinson's Disease from Continuous Speech in Noisy Environments

Parkinson's disease is a progressive neurodegenerative disorder caused by dopaminergic neuron degeneration. Parkinsonian speech impairment is one of the earliest presentations of the disease and, along with tremor, is suitable for pre-diagnosis. It is defined by hypokinetic dysarthria and accounts for respiratory, phonatory, articulatory, and prosodic manifestations. The topic of this article targets artificial-intelligence-based identification of Parkinson's disease from continuous speech recorded in a noisy environment. The novelty of this work is twofold. First, the proposed assessment workflow performed speech analysis on samples of continuous speech. Second, we analyzed and quantified Wiener filter applicability for speech denoising in the context of Parkinsonian speech identification. We argue that the Parkinsonian features of loudness, intonation, phonation, prosody, and articulation are contained in the speech, speech energy, and Mel spectrograms. Thus, the proposed workflow follows a feature-based speech assessment to determine the feature variation ranges, followed by speech classification using convolutional neural networks. We report the best classification accuracies of 96% on speech energy, 93% on speech, and 92% on Mel spectrograms. We conclude that the Wiener filter improves both feature-based analysis and convolutional-neural-network-based classification performances.

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson's Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

Parkinson's Disease (PD) is one of the most common non-curable neurodegenerative diseases. Diagnosis is achieved clinically on the basis of different symptoms with considerable delays from the onset of neurodegenerative processes in the central nervous system. In this study, we investigated early and full-blown PD patients based on the analysis of their voice characteristics with the aid of the most commonly employed machine learning (ML) techniques. A custom dataset was made with hi-fi quality recordings of vocal tasks gathered from Italian healthy control subjects and PD patients, divided into early diagnosed, off-medication patients on the one hand, and mid-advanced patients treated with L-Dopa on the other. Following the current state-of-the-art, several ML pipelines were compared usingdifferent feature selection and classification algorithms, and deep learning was also explored with a custom CNN architecture. Results show how feature-based ML and deep learning achieve comparable results in terms of classification, with KNN, SVM and naïve Bayes classifiers performing similarly, with a slight edge for KNN. Much more evident is the predominance of CFS as the best feature selector. The selected features act as relevant vocal biomarkers capable of differentiating healthy subjects, early untreated PD patients and mid-advanced L-Dopa treated patients.

How resistant are levodopa-resistant axial symptoms? Response of freezing, posture, and voice to increasing levodopa intestinal infusion rates in Parkinson disease

BACKGROUND AND PURPOSE

Treatment of freezing of gait (FoG) and other Parkinson disease (PD) axial symptoms is challenging. Systematic assessments of axial symptoms at progressively increasing levodopa doses are lacking. We sought to analyze the resistance to high levodopa doses of FoG, posture, speech, and altered gait features presenting in daily-ON therapeutic condition.

METHODS

We performed a pre-/postinterventional study including patients treated with levodopa/carbidopa intestinal gel infusion (LCIG) with disabling FoG in daily-ON condition. Patients were evaluated at their usual LCIG infusion rate (T1), and 1 h after 1.5× (T2) and 2× (T3) increase of the LCIG infusion rate by quantitative outcome measures. The number of FoG episodes (primary outcome), posture, speech, and gait features were objectively quantified during a standardized test by a blinded rater. Changes in motor symptoms, dyskinesia, and plasma levodopa concentrations were also analyzed.

RESULTS

We evaluated 16 patients with a mean age of 69 ± 9.4 years and treated with LCIG for a mean of 2.2 ± 2.1 years. FoG improved in 83.3% of patients by increasing the levodopa doses. The number of FoG episodes significantly decreased (mean = 2.3 at T1, 1.7 at T2, 1.2 at T3; p = 0.013). Posture and speech features did not show significant changes, whereas stride length (p = 0.049), turn duration (p = 0.001), and turn velocity (p = 0.024) significantly improved on doubling the levodopa infusion rate.

CONCLUSIONS

In a short-term evaluation, the increase of LCIG dose can improve "dopa-resistant" FoG and gait issues in most advanced PD patients with overall good control of motor symptoms in the absence of clinically significant dyskinesia.

Computerized analysis of speech and voice for Parkinson's disease: A systematic review

BACKGROUND AND OBJECTIVE

Speech impairment is an early symptom of Parkinson's disease (PD). This study has summarized the literature related to speech and voice in detecting PD and assessing its severity.

METHODS

A systematic review of the literature from 2010 to 2021 to investigate analysis methods and signal features. The keywords "Automatic analysis" in conjunction with "PD speech" or "PD voice" were used, and the PubMed and ScienceDirect databases were searched. A total of 838 papers were found on the first run, of which 189 were selected. One hundred and forty-seven were found to be suitable for the review. The different datasets, recording protocols, signal analysis methods and features that were reported are listed. Values of the features that separate PD patients from healthy controls were tabulated. Finally, the barriers that limit the wide use of computerized speech analysis are discussed.

RESULTS

Speech and voice may be valuable markers for PD. However, large differences between the datasets make it difficult to compare different studies. In addition, speech analytic methods that are not informed by physiological understanding may alienate clinicians.

CONCLUSIONS

The potential usefulness of speech and voice for the detection and assessment of PD is confirmed by evidence from the classification and correlation results.