Prediction of Parkinson's Disease Using Machine Learning Techniques

Sharma, Kirti

doi:10.2139/ssrn.3742953

Cited by 6 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to [38], where they applied feature selection for data processing, the RF model achieved 90.5% precision and 97.3% accuracy. In contrast, [30] used the same dataset from Oxford University, but achieved 85% in precision and 87% in accuracy with the RF model, which are lower than those obtained in this study. One of the most marked differences is the use of optimization techniques, since in [30] they did not employ feature selection.…”

Section: Discussioncontrasting

confidence: 86%

“…In contrast, [30] used the same dataset from Oxford University, but achieved 85% in precision and 87% in accuracy with the RF model, which are lower than those obtained in this study. One of the most marked differences is the use of optimization techniques, since in [30] they did not employ feature selection. In contrast, [43] applied the SMOTE oversampling technique to generate synthetic data and achieved 97.4% accuracy with the RF model, which is a higher result than that obtained in this study.…”

Section: Discussioncontrasting

confidence: 86%

“…Likewise, the LR model achieved third place with 89% accuracy and 90% precision. Similar to those obtained in [30], where LR obtained 83.05% in precision and 83% in accuracy, using the same data set, but with different optimization techniques. In contrast to [28], with the use of a dataset on the non-motor and olfactory characteristics of the patients, the model achieved 97.159% accuracy, being superior results to those obtained in this study.…”

Section: Discussionsupporting

confidence: 80%

“…The AdaBoost model obtained a precision of 82% and an accuracy of 79%. Similar to the study [30], where the model achieved 87% precision and 86.4% accuracy. Different from those achieved in [37], where with a different data set than the one used in this study, the AdaBoost model achieved 97.4% accuracy.…”

Section: Discussionsupporting

confidence: 73%

“…The study concluded that MLP is the best detector with 0.9831 accuracy, followed by SVM with 0.95 accuracy. Similarly, Sharma and Mishra [30] analyzed seven ML models focused on predicting Parkinson's disease, they used a dataset from Oxford University with voice biometric recordings from 31 patients. The results position the AdaBoost model as the best predictor with a precision and accuracy of 0.87 and 0.864 respectively, followed by RF and LR which achieved a precision of 0.85 and 0.8305 respectively.…”

Section: Review Of the Literaturementioning

confidence: 99%

See 4 more Smart Citations

Evaluation of machine learning algorithms in the early detection of Parkinson's disease: a comparative study

Zapata-Paulini,

Cabanillas-Carbonell

2024

IJEECS

View full text Add to dashboard Cite

Parkinson's is a neurodegenerative disease that generally affects people over 60 years of age. The disease destroys neurons and increases the accumulation of α-synuclein in many parts of the brain stem, although at present its causes remain unknown. It is therefore a priority to identify a method that can detect the disease, and this is where machine learning models become important. This study aims to perform a comparative analysis of machine learning models focused on the early detection of Parkinson's disease. Logistic regression (LR), support vector machines (SVM), decision trees (DT), extra trees classifiers (ETC), K-nearest neighbors (KNN), random forests (RF), adaptive boosting (AdaBoost) and gradient boosting (GB) algorithms are described and developed to identify the one that offers the best performance. In the training stage, we used the Oxford University dataset for Parkinson's disease detection, which has a total of 23 attributes and 195 records on patient voice recordings. The article is structured into six sections, such as introduction, related work, methodology, results, discussions, and conclusions. The metrics of accuracy, sensitivity, F1 count, and precision were used to measure the models' performance. The results position the KNN model as the best predictor with 95% accuracy, precision, sensitivity, and F1 score.

show abstract

Section: Discussioncontrasting

confidence: 86%