Synthetic Parkinson's Disease Detection Dataset
Patient Health Records & Digital Health
Tags and Keywords
Trusted By




"No reviews yet"
£179.99
About
This synthetic Parkinson's Disease Detection Dataset is designed for educational and research purposes in the fields of data science, healthcare analytics, and medical research. It contains key clinical and speech features from individuals with Parkinson's Disease, which can be used to build predictive models, analyze disease progression, and assess the impact of motor and speech symptoms. The dataset is ideal for tasks such as classification, regression, and the study of biomarkers for Parkinson’s disease.
Dataset Features:
Index: Row identifier for each record.
Age: The age of the patient.
Sex: Gender of the patient (Male/Female).
Test_time: Duration or time of the test conducted (in minutes).
Motor_UPDRS: Motor component score from the Unified Parkinson’s Disease Rating Scale (UPDRS).
Total_UPDRS: Total score from the UPDRS, including both motor and non-motor components.
Jitter(%): Percentage of frequency variation in speech, a key indicator of Parkinson’s disease.
Jitter(Abs): Absolute jitter value, quantifying frequency variation.
Jitter:RAP: Jitter measured using the Relative Average Perturbation method.
Jitter:PPQ5: Jitter measured using the 5-point Perturbation Quotient.
Jitter:DDP: Jitter measured using the Difference of Difference of Polynomials method.
Shimmer: Amplitude variation in speech, indicating vocal instability.
Shimmer(dB): Amplitude variation in decibels.
Shimmer:APQ3: Shimmer measured using the 3-point Amplitude Perturbation Quotient.
Shimmer:APQ5: Shimmer measured using the 5-point Amplitude Perturbation Quotient.
Shimmer:APQ11: Shimmer measured using the 11-point Amplitude Perturbation Quotient.
Shimmer:DDA: Shimmer measured using the Difference of Difference of Amplitudes method.
NHR: Noise to Harmonics Ratio, a measure of voice quality and periodicity.
HNR: Harmonics to Noise Ratio, reflecting the periodicity of speech sounds.
RPDE: Recurrence Period Density Entropy, derived from voice signal analysis.
DFA: Detrended Fluctuation Analysis, studying self-similarity in speech signals.
PPE: Pitch Period Entropy, quantifying irregularity in pitch periods during speech.
Usage
This dataset is perfect for various applications related to Parkinson's Disease detection and analysis:
Disease Prediction: Develop machine learning models to predict the presence and progression of Parkinson’s Disease.
Speech Analysis: Study speech features like jitter and shimmer for early diagnosis and monitoring of Parkinson's Disease.
Predictive Modeling: Build models using clinical and speech features to assess disease severity.
Clinical Research: Investigate the relationship between motor and non-motor symptoms of Parkinson's Disease.
Healthcare Analytics: Apply data science techniques to improve the diagnosis and treatment of Parkinson’s Disease.
Coverage
This synthetic dataset is anonymized and designed for research and learning purposes. It includes a diverse range of speech and clinical data, simulating different stages of Parkinson’s Disease for analysis.
License
CC0 (Public Domain)
Who Can Use It
Data Science Practitioners: For practicing data preprocessing, classification, and regression tasks.
Healthcare Analysts and Researchers: To explore relationships between clinical and speech features in Parkinson's Disease.
Medical Professionals: To enhance understanding of Parkinson’s Disease symptoms and progressions.
Machine Learning Enthusiasts: To experiment with models for predicting Parkinson’s Disease using diverse features.
Academic Institutions: For use in educational settings to teach data science applications in healthcare.