arXiv:2511.15485v1 Announce Type: cross 
Abstract: Parkinson's disease is a neurodegenerative disorder that can be very tricky to diagnose and treat. Such early symptoms can include tremors, wheezy breathing, and changes in voice quality as critical indicators of neural damage. Notably, there has been growing interest in utilizing changes in vocal attributes as markers for the detection of PD early on. Based on this understanding, the present paper was designed to focus on the acoustic feature analysis based on voice recordings of patients diagnosed with PD and healthy controls (HC). In this paper, we introduce a novel classification and visualization model known as CustNetGC, combining a Convolutional Neural Network (CNN) with Custom Network Grad-CAM and CatBoost to enhance the efficiency of PD diagnosis. We use a publicly available dataset from Figshare, including voice recordings of 81 participants: 40 patients with PD and 41 healthy controls. From these recordings, we extracted the key spectral features: L-mHP and Spectral Slopes. The L-mHP feature combines three spectrogram representations: Log-Mel spectrogram, harmonic spectrogram, and percussive spectrogram, which are derived using Harmonic-Percussive Source Separation (HPSS). Grad-CAM was used to highlight the important regions in the data, thus making the PD predictions interpretable and effective. Our proposed CustNetGC model achieved an accuracy of 99.06% and precision of 95.83%, with the area under the ROC curve (AUC) recorded at 0.90 for the PD class and 0.89 for the HC class. Additionally, the combination of CatBoost, a gradient boosting algorithm, enhanced the robustness and the prediction performance by properly classifying PD and non-PD samples. Therefore, the results provide the potential improvement in the CustNetGC system in enhancing diagnostic accuracy and the interpretability of the Parkinson's Disease prediction model.

تم تطوير نموذج جديد يسمى CustNetGC لتحسين التنبؤ بمرض باركنسون (PD) من خلال تحليل السمات الصوتية. يجمع هذا النموذج بين شبكة عصبية تلافيفية (CNN) وCustom Network Grad-CAM وCatBoost، باستخدام تسجيلات صوتية من 81 مشاركًا، بما في ذلك 40 مريضًا بمرض PD و41 شخصًا سليمًا. تهدف الدراسة إلى تحسين الكشف المبكر عن مرض PD من خلال تحليل الميزات الصوتية.

Se ha desarrollado un nuevo modelo llamado CustNetGC para mejorar la predicción de la enfermedad de Parkinson (EP) mediante el análisis de atributos vocales. Este modelo integra una red neuronal convolucional (CNN) con Custom Network Grad-CAM y CatBoost, utilizando grabaciones de voz de 81 participantes, incluidos 40 pacientes con EP y 41 controles sanos. El estudio tiene como objetivo mejorar la detección temprana de la EP a través del análisis de características acústicas.

Un nouveau modèle appelé CustNetGC a été développé pour améliorer la prédiction de la maladie de Parkinson (MP) en analysant les attributs vocaux. Ce modèle intègre un réseau de neurones convolutifs (CNN) avec Custom Network Grad-CAM et CatBoost, utilisant des enregistrements vocaux de 81 participants, dont 40 patients atteints de MP et 41 témoins sains. L'étude vise à améliorer la détection précoce de la MP grâce à l'analyse des caractéristiques acoustiques.

A novel model called CustNetGC has been developed to enhance the prediction of Parkinson's disease (PD) by analyzing vocal attributes. This model integrates a Convolutional Neural Network (CNN) with Custom Network Grad-CAM and CatBoost, utilizing voice recordings from 81 participants, including 40 PD patients and 41 healthy controls. The study aims to improve early detection of PD through acoustic feature analysis.

A Novel CustNetGC Boosted Model with Spectral Features for Parkinson's Disease Prediction

arXiv:2511.16856v1 Announce Type: new 
Abstract: Parkinson's disease (PD) is a progressive neurodegenerative disorder that, in addition to directly impairing functional mobility, is frequently associated with vocal impairments such as hypophonia and dysarthria, which typically manifest in the early stages. The use of vocal biomarkers to support the early diagnosis of PD presents a non-invasive, low-cost, and accessible alternative in clinical settings. Thus, the objective of this cross-sectional study was to consistently evaluate the effectiveness of a Deep Neural Network (DNN) in distinguishing individuals with Parkinson's disease from healthy controls, in comparison with traditional Machine Learning (ML) methods, using vocal biomarkers. Two publicly available voice datasets were used. Mel-frequency cepstral coefficients (MFCCs) were extracted from the samples, and model robustness was assessed using a validation strategy with 1000 independent random executions. Performance was evaluated using classification statistics. Since normality assumptions were not satisfied, non-parametric tests (Kruskal-Wallis and Bonferroni post-hoc tests) were applied to verify whether the tested classification models were similar or different in the classification of PD. With an average accuracy of $98.65\%$ and $92.11\%$ on the Italian Voice dataset and Parkinson's Telemonitoring dataset, respectively, the DNN demonstrated superior performance and efficiency compared to traditional ML models, while also achieving competitive results when benchmarked against relevant studies. Overall, this study confirms the efficiency of DNNs and emphasizes their potential to provide greater accuracy and reliability for the early detection of neurodegenerative diseases using voice-based biomarkers.

أظهرت دراسة حديثة إمكانية استخدام المؤشرات الصوتية في الكشف المبكر عن مرض باركنسون (PD) من خلال مقارنة فعالية شبكة عصبية عميقة (DNN) مع نماذج التعلم الآلي التقليدية. استخدمت الدراسة مجموعتين من بيانات الصوت المتاحة للجمهور لاستخراج معاملات ميل التردد (MFCC) وتقييم متانة النموذج من خلال استراتيجيات التحقق الواسعة.

Un estudio reciente ha demostrado el potencial de los biomarcadores vocales en la detección temprana de la enfermedad de Parkinson (EP) al comparar la efectividad de una Red Neuronal Profunda (DNN) con modelos de aprendizaje automático tradicionales. La investigación utilizó dos conjuntos de datos de voz disponibles públicamente para extraer coeficientes cepstrales en frecuencia Mel (MFCC) y evaluar la robustez del modelo a través de estrategias de validación extensas.

Une étude récente a démontré le potentiel des biomarqueurs vocaux dans la détection précoce de la maladie de Parkinson (MP) en comparant l'efficacité d'un réseau de neurones profond (DNN) aux modèles d'apprentissage automatique traditionnels. La recherche a utilisé deux ensembles de données vocales disponibles publiquement pour extraire les coefficients cepstraux en fréquence Mel (MFCC) et évaluer la robustesse du modèle à travers des stratégies de validation étendues.

A recent study has demonstrated the potential of vocal biomarkers in the early detection of Parkinson's disease (PD) by comparing the effectiveness of a Deep Neural Network (DNN) against traditional machine learning models. The research utilized two publicly available voice datasets to extract Mel-frequency cepstral coefficients (MFCCs) and assess model robustness through extensive validation strategies.

The use of vocal biomarkers in the detection of Parkinson's disease: a robust statistical performance comparison of classic machine learning models

arXiv:2506.08274v5 Announce Type: replace-cross 
Abstract: This research addresses the critical lack of comprehensive studies on feature scaling by systematically evaluating 12 scaling techniques - including several less common transformations - across 14 different Machine Learning algorithms and 16 datasets for classification and regression tasks. We meticulously analyzed impacts on predictive performance (using metrics such as accuracy, MAE, MSE, and $R^2$) and computational costs (training time, inference time, and memory usage). Key findings reveal that while ensemble methods (such as Random Forest and gradient boosting models like XGBoost, CatBoost and LightGBM) demonstrate robust performance largely independent of scaling, other widely used models such as Logistic Regression, SVMs, TabNet, and MLPs show significant performance variations highly dependent on the chosen scaler. This extensive empirical analysis, with all source code, experimental results, and model parameters made publicly available to ensure complete transparency and reproducibility, offers model-specific crucial guidance to practitioners on the need for an optimal selection of feature scaling techniques.

دراسة حديثة نُشرت على arXiv قامت بتقييم منهجي لـ 12 تقنية لتقييس الميزات عبر 14 خوارزمية تعلم آلي و16 مجموعة بيانات، كاشفة عن تباينات كبيرة في الأداء في نماذج مثل الانحدار اللوجستي وSVM، بينما أظهرت طرق التجميع قوة مستقلة عن التقييس.

Un estudio reciente publicado en arXiv evaluó sistemáticamente 12 técnicas de escalado de características a través de 14 algoritmos de aprendizaje automático y 16 conjuntos de datos, revelando variaciones significativas en el rendimiento de modelos como la regresión logística y los SVM, mientras que los métodos de ensamblaje mostraron robustez independientemente del escalado.

Une étude récente publiée sur arXiv a évalué systématiquement 12 techniques de mise à l'échelle des caractéristiques à travers 14 algorithmes d'apprentissage automatique et 16 ensembles de données, révélant des variations de performance significatives dans des modèles tels que la régression logistique et les SVM, tandis que les méthodes d'ensemble ont montré une robustesse indépendamment de la mise à l'échelle.

A recent study published on arXiv systematically evaluated 12 feature scaling techniques across 14 machine learning algorithms and 16 datasets, revealing significant performance variations in models like Logistic Regression and SVMs, while ensemble methods showed robustness regardless of scaling.

A Novel CustNetGC Boosted Model with Spectral Features for Parkinson's Disease Prediction

Was this article worth reading? Share it

Hypertune

Graphite Note

GPTHuman