Pilot Study Employing a Machine Learning Approach as a Potential Method for Predicting Parkinson's Disease Using Voice as a Digital Biomarker and the SHAP Approach for Feature Engineering.

Overview

1. Department of Mathematics and Physics “E. De Giorgi”, University of Salento, Via Lecce-Arnesano, 73100 Lecce, Italy
2. PolitoBioMed Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Torino, Italy
3. Department of Research and Development (R&D), GPI SpA, 38123 Trento, Italy; (A.B.); (M.D.)
4. Department of Experimental Medicine, University of Salento, Via Lecce-Monteroni, 73100 Lecce, Italy
5. Human Science Department, University of Verona, Lungadige Porta Vittoria, 17, 37129 Verona, Italy
6. Department of Human and Social Sciences, University of Salento, 73100 Lecce, Italy
7. Division of Neurology, Vito Fazzi Hospital, 73100 Lecce, Italy; (A.L.); (F.M.); (M.L.)

Abstract

Introduction: Voice-based digital biomarkers have emerged as a promising approach for distinguishing individuals with neurodegenerative disorders, particularly Parkinson’s disease (PD), from healthy subjects (HS). With the increasing availability of smartphone and web-based recording tools, voice data can be collected efficiently in both clinical and remote settings. However, further validation is required before such approaches can be translated into routine clinical practice. Methods: This study used a cross-sectional analysis at the recording level, treating repeated recordings from the same participant as separate observations collected at Vito Fazzi Hospital in Lecce, Italy. Speech recordings from individuals with Parkinson’s disease (PD) and healthy controls were collected using the dedicated Talia smartphone and web application. Sustained vowel phonation (/a/) was analyzed as the primary speech task. Following data acquisition, feature extraction was performed as a crucial step in the speech analysis pipeline, as the quality and relevance of the extracted features directly influence the ability of machine learning models to discriminate between Parkinson’s disease (PD) patients and healthy controls. To capture various aspects of speech impairment associated with PD, a comprehensive set of acoustic features was extracted, including long-term features (pitch, jitter, and shimmer), nonlinear descriptors such as Recurrence Period Density Entropy (RPDE), and short-term feature based on Mel-Frequency Cepstral Coefficients (MFCCs). These features were subsequently used to develop and evaluate machine learning models for the classification of Parkinson’s disease and healthy subjects. Feature selection was performed using SHAP to identify the most informative vocal biomarkers. Model performance was assessed using five independent random train–test splits (70% training and 30% testing), supported by an internal five-fold cross-validation procedure within the training data. Multiple machine learning models were developed and evaluated, including Random Forest, Logistic Regression, Support Vector Machine, Naive Bayes, K-Nearest Neighbors, Decision Tree, Artificial Neural Network, and Gradient Boosting. Results: The evaluated models demonstrated strong recording-level classification performance. Artificial Neural Networks (ANN) and K-Nearest Neighbors (KNN) achieved the highest accuracy scores (0.9545 and 0.9494, respectively), along with superior recall (up to 0.9500), precision (up to 0.9551), and F1-score (up to 0.9525). Both models also exhibited excellent discriminative ability, with ROC-AUC values reaching 0.9882 (ANN) and 0.9893 (KNN). In contrast, Naive Bayes and Decision Tree showed comparatively lower performance across all metrics. Log-loss analysis further confirmed the robustness of ANN and KNN, which achieved the lowest values (0.2552 and 0.2510, respectively), indicating well-calibrated predictions. Overall, the findings highlight the consistency and generalizability of ANN and KNN across cross-validation splits. Conclusions: This study demonstrates that machine learning models, particularly ANN and KNN, can effectively differentiate Parkinson’s disease from healthy conditions using voice recordings. The integration of explainable AI for feature selection enhances model transparency and clinical relevance. However, the reported performance estimates were obtained from a recording-level analysis and should be interpreted as preliminary findings. Further studies involving larger cohorts and participant-level validation strategies are required to determine the generalizability and clinical applicability of these approaches.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

No file of the authors' code could be read here: it is described below, and read at its source.

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

• 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
• 0 scripts, each with its path and the digest of its content;
• no match between paragraphs and code yet;
• neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

The datasets generated and analyzed during the current study are available from the corresponding author upon reasonable request and subject to approval by the relevant ethical and institutional regulations. Due to privacy and confidentiality considerations associated with clinical voice recordings from human participants, the raw voice data cannot be made publicly available without appropriate authorization. To promote transparency and reproducibility, the source code used for machine learning model development, and performance evaluation has been made publicly available through GitHub: https://github.com/mehdi1366-com (I checked this online resource on 10 August 2026.).

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 10 authors, 5 keywords, 2 funders, 42 references.

Cite

This paper

Rashidi, M., Shah, S. A. H., Coppola, C., Buccoliero, A., Arima, S., Lupo, A., My, F., Lorenzo, M., Donzella, M., & Maffia, M. (2026). Pilot Study Employing a Machine Learning Approach as a Potential Method for Predicting Parkinson's Disease Using Voice as a Digital Biomarker and the SHAP Approach for Feature Engineering. Bioengineering (Basel, Switzerland), 13(8), 917. https://doi.org/10.3390/bioengineering13080917

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3390/biomimetics11060369

Bio-Inspired Deep Learning for Parkinson's Disease Detection: A Comparative Study Based on Vocal Biomarkers and Archimedean Spiral Analysis.

Journal: Biomimetics (Basel, Switzerland)

In common: Parkinson's, clinical / translational, 2 references

[2] doi:10.7717/peerj-cs.3860

Systematic review of unveiling the potential of AI using machine learning and deep learning methods in neurodegenerative diseases.

Journal: PeerJ. Computer science

In common: Parkinson's, 2 references

[3] doi:10.1038/s41531-026-01408-6 [code]

A stacked multi-classifier for multi-modal data fusion in transcranial sonography-based Parkinson's disease assessment.

Journal: NPJ Parkinson's disease

In common: Parkinson's, clinical / translational, 2 references

[4] doi:10.1016/j.isci.2026.117185

Impact of Amazonian dance on speech performance in people with Parkinson's disease.

Journal: iScience

In common: Parkinson's, 2 references

[5] doi:10.1016/j.ibneur.2026.06.002

Altered static and dynamic functional network connectivity in Parkinson's disease: A multisite functional magnetic resonance imaging study.

Journal: IBRO neuroscience reports

In common: Parkinson's, 2 references

[6] doi:10.1038/s41467-026-71351-w [code]

Variants in the proteasome regulator PSMF1 cause a phenotypic spectrum from parkinsonism to perinatal lethality.

Journal: Nature communications

In common: Parkinson's, 2 references

[7] doi:10.1016/j.prdoa.2026.100480 [code]

Multitype hand writing as a digital marker for Parkinson's disease.

Journal: Clinical parkinsonism & related disorders

In common: Parkinson's, clinical / translational, 1 reference

[8] doi:10.1038/s43856-026-01606-6 [code]

Validation of remote multimodal AI screening for Parkinson disease across diverse settings.

Journal: Communications medicine

In common: Parkinson's, clinical / translational, 1 reference

[9] doi:10.1371/journal.pone.0333158 [code]

Alpha-synuclein overexpression reduces neural activity within a basal ganglia vocal nucleus in a zebra finch model.

Journal: PloS one

In common: Parkinson's, 1 reference

[10] doi:10.1038/s41531-026-01422-8 [code]

Lewy pathology largely absent in prefrontal cortices of Parkinson's disease patients undergoing deep brain stimulation.

Journal: NPJ Parkinson's disease

In common: Parkinson's, clinical / translational, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.