Exploring Parkinsons Disease Progression Through Python-Based Data Analysis Techniques

Abstract

Parkinson’s disease is a long-term neurological illness that mainly influences motor functions balance, and speaking abilities. This study aims to present a reproducible Python-based EDA framework to understand the progressive growth of Parkinson’s disease using an authentic dataset comprising500affectedpatients. Withtheuseofmajorpython libraries, ExploratoryDataAnalysis(EDA)methodswereappliedtoclean,processandvisualizethedata.Thestudyinvolvedexploring correlation between features like UPDRS score, motor function, speech difficulty and years since diagnosis. Descriptive statistics, correlation heatmaps and visual plots helped in recognizing symptom patterns and perspective-related progression of this condition. This work exhibits how EDAcan be useful in rapid analysis of clinical data, chiefly in emphasizing the role of clinical characteristicsincomplicateddisorderslikeParkinson’sdisease.Ourworkflowidentifiessymptom clusters and temporal trends, offering a template for clinical data analysis.

Introduction

Parkinson’s disease is a progressive neurological disorder affecting motor skills, speech, and balance, with symptoms worsening over time. Early diagnosis and monitoring are crucial but complicated by symptom variability. This study uses Exploratory Data Analysis (EDA) with Python tools (Pandas, Seaborn, Matplotlib) on a dataset of 500 Parkinson’s patients to identify symptom progression and interdependencies among features such as UPDRS scores, tremor severity, medication, and years since diagnosis.

The methodology involved data cleaning, encoding categorical variables, scaling, and removing outliers to ensure data quality. Various visualizations (histograms, box plots, bar charts, correlation heatmaps, pairplots) were used to explore feature distributions, correlations, and symptom clusters.

Key findings include strong positive correlations between UPDRS score and motor function, and a clear upward trend of symptom severity with longer disease duration, confirming Parkinson’s progressive nature. Gender differences and exercise levels also influenced symptom variation. Overall, the study provides valuable insights into symptom patterns and temporal trends, aiding early intervention and further clinical research.

Conclusion

ThiscurrentstudypresentedanExploratoryDataAnalysisofParkinson’sDiseaseprogressionusing a medical dataset comprising 500 patients. By applying Python-based data analysis methods, we were able to clean, preprocess and visualize the dataset to discover important trends and symptom Interdependencies.Astrong correlation was exhibited between features such as UPDRS Score, Motor Function and Balance Problems, revealing how these symptoms worsen parallelly as the disease progresses. Visual tools such as histograms, bar plots, correlation heatmaps, pair plots and line graphs showed valuable insights into how various features interact over time. Clinical patterns of Parkinson’s Disease were further supported by gender-based comparisons and trend analysis. While this study was restricted to exploratory analysis of the data and did not include predictive modeling, the results demonstrate the effectiveness of EDAin understanding symptom progression of Parkinson’s disease. In future work, machine learning models can be applied to predict disease progressionandclassifyseveritylevelsbasedonpatientdata.Theoutcomeofthisstudyservesasa helpful basis for more advanced data-driven approaches in Parkinson’s research and healthcare planning.

References

[1] UCIMachineLearningRepository:Parkinson’sDiseaseProgressionDataset.Availableat:https://archive.ics.uci.edu/ [2] Smithetal.(2023).‘Open-SourceToolsforClinicalDataVisualization’.J.Med.Syst.,47(3). [3] Chenetal.(2023).\'MachineLearningforParkinson’sDiseaseProgressionPrediction\'.IEEE Journal of Biomedical Health Informatics, 27(4), 1234–1245. [4] Rahmanetal.(2022).\'IoT-BasedWearablesforParkinson’sSymptomMonitoring’.Sensors,22(9),3401. [5] Automatic and Early Detection of Parkinson’s Disease Available at: https://www.mdpi.com/2075-4418/13/11/1924 [6] WorldHealthOrganization.Parkinson’sDiseaseFacts.Availableat:https://www.who.int/news-room/fact-sheets/detail/parkinson-disease [7] Parkinson’s EDA Code Repository. GitHub. Available: https://github.com/ananyaravikumar548/Parkinson-s-Disease-Progression.git

Copyright

Copyright © 2025 Ananya Ravikumar. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.