RAdX: A New Ensemble Model using Classifiers for Parkinson's Disease Prediction
Abstract
Parkinson's disease (PD), a progressive neurological condition that hinders motor function, can be traced back to the loss of neurons that produce dopamine at the disease's origin. Tremors, rigidity, movement slowness, shaking, and instability are all symptoms of PD. Since a loss of motor control is a hallmark of Parkinson's disease, the patient's voice can be used as a diagnostic tool. Reliable models that can translate this auditory data into a screening tool for healthcare practitioners could lead to more affordable and precise diagnoses as technology advances and audio-collecting equipment becomes commonplace in daily life. UCI Machine Learning Repository's "Parkinsons Data Set" was used; it has 24 features and more than 195 participants. This research presents RAdX, a novel ensemble learning strategy that integrates the strengths of three separate classification algorithms (Random Forest, AdaBoost, and XGBoost). This study investigates the efficacy of a proposed ensemble model, “RAdX”, with an accuracy of 94.87%, recall of 100%, precision of 92.86%, and F1 score of 96.30%.
References
1. A. Bougea; New Markers in Parkinson's Disease. Advances in Clinical Chemistry, 96, 137-178 (2020).
2. A. Nawar; F. Rahman; N. Krishnamurthi; A. Som and Turaga; (2020) Topological Descriptors for Parkinson’s Disease Classification and Regression Analysis. In 2020 42nd Annual International Conference
of the IEEE Engineering in Medicine & Biology Society (EMBC), 793-797.
3. A. Tsanas; M. A. Little; P. E. McSharry; J. Spielman and L. O. Ramig; Novel Speech Signal Processing
Algorithms for High-Accuracy Classification of Parkinson's Disease. IEEE Transactions on Biomedical
Engineering, 59(5), 1264-1271 (2012).
4. D. M. Huse; K. Schulman; L. Orsini; J. Castelli‐ Haley; S. Kennedy and G. Lenhart; Burden of Illness in
Parkinson's Disease. Movement Disorders: Official Journal of the Movement Disorder Society, 20(11),
1449-1454 (2005).
5. E.Bisong;IntroductiontoScikit-learn.BuildingMachineLearningandDeepLearningModelsonGoogle
Cloud Platform: A Comprehensive Guide for Beginners, 215-229 (2019).
6. G.DeMaagdandA.Philip;Parkinson’sDiseaseandItsManagement:Part1:DiseaseEntity,RiskFactors,
Pathophysiology, Clinical Presentation, and Diagnosis. Pharmacy and Therapeutics, 40(8), 504 (2015).
7. L. K. Mischley; R. C. Lau and N. S. Weiss; Use of a Self-rating Scale of the Nature and Severity of Symptoms in Parkinson’s Disease (PRO-PD): Correlation with Quality of Life and Existing Scales of
Disease Severity. NPJ Parkinson's Disease, 3(1), 20, 1-7 (2017).
8. P. Ferreira; D. C. Le; A. N. Zincir-Heywood; (2019) Exploring Feature Normalization and Temporal
Information for Machine Learning-based Insider Threat Detection. International Conference on Network
and Service Management (CNSM), 1-7.
9. P. Surathi; K. Jhunjhunwala; R. Yadav; P. K. Pal; Research in Parkinson's Disease in India: A Review.
Annals of Indian Academy of Neurology, 19(1), 9-20 (2016).
10. S. Heymann; M. Latapy and C. Magnien; (2012) Outskewer: Using skewness to Spot Outliers in Samples
and Time Series. In 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis
and Mining, 527-534.
11. T. Hao; J. Elith; J. J. Lahoz‐ Monfort and G. Guillera‐ Arroita; Testing whether Ensemble Modelling is
Advantageous for Maximizing Predictive Performance of Species Distribution Models. Ecography, 43(4)
549-558 (2020).
12. T. M. Khoshgoftaar; J. Van Hulse and A. Napolitano; Comparing Boosting and Bagging Techniques with
Noisy and Imbalanced Data. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and
Humans, 41(3) 552-568 (2010).
13. R. Yacouby and Dustin Axman; (2020) Probabilistic Extension of Precision, Recall, and F1 Score for a
more thorough Evaluation of Classification Models. In Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems, 79-91.
Trion Studio
