Explainable Artificial Intelligence (EXAI) Models for Early Prediction of Parkinson’s Disease Based on Spiral and Wave Drawings
Parkinson’s disease (PD) is a rapidly growing neurodegenerative disorder that primarily affects the elderly population. Until now, there has been no antidote for PD. However, diagnosing Parkinson’s disease in its early stages is difficult. Early treatment will help people with...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10171347/ |
| _version_ | 1797782843579957248 |
|---|---|
| author | S. Saravanan Kannan Ramkumar K. Narasimhan Subramaniyaswamy Vairavasundaram Ketan Kotecha Ajith Abraham |
| author_facet | S. Saravanan Kannan Ramkumar K. Narasimhan Subramaniyaswamy Vairavasundaram Ketan Kotecha Ajith Abraham |
| author_sort | S. Saravanan |
| collection | DOAJ |
| description | Parkinson’s disease (PD) is a rapidly growing neurodegenerative disorder that primarily affects the elderly population. Until now, there has been no antidote for PD. However, diagnosing Parkinson’s disease in its early stages is difficult. Early treatment will help people with Parkinson’s disease improve their quality of life. The primary goal of this work is to increase the early diagnostic accuracy of Parkinson’s disease using deep learning models and to make the models more transparent and trustworthy. It proved challenging to comprehend the methods by which the classifiers made predictions about Parkinson’s disease. It would be valuable if the outcomes generated by these classifiers could be clarified in a reliable and trustworthy manner. Explainable Artificial Intelligence (EXAI) focuses on enhancing clinical health practises and bringing transparency to predictive analysis, both of which are critical in the healthcare arena. We proposed a new hybrid deep transfer learning model to distinguish PD patients from healthy individuals. The proposed architecture combines the advantages of both VGG19 Net and Google Net. This study also shows the experimental outcomes of various pre-trained models such as Alex Net, DenseNet-201, VGG-19 Net, Squeeze Net1.1, and ResNet-50. The VGG19-INC model predicts PD with an accuracy of 98.45%, which is greater than other state-of-the-art approaches, demonstrating the proposed work’s superiority and robustness. To demystify the VGG19-INC model, explainable AI approaches such as LIME are used to identify the specific parts of the spiral and wave drawings that contribute most to the model’s prediction. These methods provide local interpretation, making it easier to understand how the model arrives at its conclusions. |
| first_indexed | 2024-03-13T00:17:41Z |
| format | Article |
| id | doaj.art-bdb1b5e2fdc642c5a7e81d5a4e6f2480 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T00:17:41Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-bdb1b5e2fdc642c5a7e81d5a4e6f24802023-07-11T23:00:26ZengIEEEIEEE Access2169-35362023-01-0111683666837810.1109/ACCESS.2023.329140610171347Explainable Artificial Intelligence (EXAI) Models for Early Prediction of Parkinson’s Disease Based on Spiral and Wave DrawingsS. Saravanan0Kannan Ramkumar1https://orcid.org/0000-0003-2988-1852K. Narasimhan2https://orcid.org/0000-0001-6929-6039Subramaniyaswamy Vairavasundaram3https://orcid.org/0000-0001-5328-7672Ketan Kotecha4https://orcid.org/0000-0003-2653-3780Ajith Abraham5https://orcid.org/0000-0002-0169-6738School of Electrical and Electronics Engineering, SASTRA Deemed University, Thanjavur, IndiaSchool of Electrical and Electronics Engineering, SASTRA Deemed University, Thanjavur, IndiaSchool of Electrical and Electronics Engineering, SASTRA Deemed University, Thanjavur, IndiaSchool of Computing, SASTRA Deemed University, Thanjavur, IndiaSymbiosis Centre for Applied Artificial Intelligence, Symbiosis International (Deemed University), Pune, IndiaSchool of Computer Science Engineering & Technology, Bennett University, Greater Noida, Uttar Pradesh, IndiaParkinson’s disease (PD) is a rapidly growing neurodegenerative disorder that primarily affects the elderly population. Until now, there has been no antidote for PD. However, diagnosing Parkinson’s disease in its early stages is difficult. Early treatment will help people with Parkinson’s disease improve their quality of life. The primary goal of this work is to increase the early diagnostic accuracy of Parkinson’s disease using deep learning models and to make the models more transparent and trustworthy. It proved challenging to comprehend the methods by which the classifiers made predictions about Parkinson’s disease. It would be valuable if the outcomes generated by these classifiers could be clarified in a reliable and trustworthy manner. Explainable Artificial Intelligence (EXAI) focuses on enhancing clinical health practises and bringing transparency to predictive analysis, both of which are critical in the healthcare arena. We proposed a new hybrid deep transfer learning model to distinguish PD patients from healthy individuals. The proposed architecture combines the advantages of both VGG19 Net and Google Net. This study also shows the experimental outcomes of various pre-trained models such as Alex Net, DenseNet-201, VGG-19 Net, Squeeze Net1.1, and ResNet-50. The VGG19-INC model predicts PD with an accuracy of 98.45%, which is greater than other state-of-the-art approaches, demonstrating the proposed work’s superiority and robustness. To demystify the VGG19-INC model, explainable AI approaches such as LIME are used to identify the specific parts of the spiral and wave drawings that contribute most to the model’s prediction. These methods provide local interpretation, making it easier to understand how the model arrives at its conclusions.https://ieeexplore.ieee.org/document/10171347/Explainable artificial intelligenceParkinson’s diseasedeep learningGoogle netLIMEspiral and wave drawings |
| spellingShingle | S. Saravanan Kannan Ramkumar K. Narasimhan Subramaniyaswamy Vairavasundaram Ketan Kotecha Ajith Abraham Explainable Artificial Intelligence (EXAI) Models for Early Prediction of Parkinson’s Disease Based on Spiral and Wave Drawings IEEE Access Explainable artificial intelligence Parkinson’s disease deep learning Google net LIME spiral and wave drawings |
| title | Explainable Artificial Intelligence (EXAI) Models for Early Prediction of Parkinson’s Disease Based on Spiral and Wave Drawings |
| title_full | Explainable Artificial Intelligence (EXAI) Models for Early Prediction of Parkinson’s Disease Based on Spiral and Wave Drawings |
| title_fullStr | Explainable Artificial Intelligence (EXAI) Models for Early Prediction of Parkinson’s Disease Based on Spiral and Wave Drawings |
| title_full_unstemmed | Explainable Artificial Intelligence (EXAI) Models for Early Prediction of Parkinson’s Disease Based on Spiral and Wave Drawings |
| title_short | Explainable Artificial Intelligence (EXAI) Models for Early Prediction of Parkinson’s Disease Based on Spiral and Wave Drawings |
| title_sort | explainable artificial intelligence exai models for early prediction of parkinson x2019 s disease based on spiral and wave drawings |
| topic | Explainable artificial intelligence Parkinson’s disease deep learning Google net LIME spiral and wave drawings |
| url | https://ieeexplore.ieee.org/document/10171347/ |
| work_keys_str_mv | AT ssaravanan explainableartificialintelligenceexaimodelsforearlypredictionofparkinsonx2019sdiseasebasedonspiralandwavedrawings AT kannanramkumar explainableartificialintelligenceexaimodelsforearlypredictionofparkinsonx2019sdiseasebasedonspiralandwavedrawings AT knarasimhan explainableartificialintelligenceexaimodelsforearlypredictionofparkinsonx2019sdiseasebasedonspiralandwavedrawings AT subramaniyaswamyvairavasundaram explainableartificialintelligenceexaimodelsforearlypredictionofparkinsonx2019sdiseasebasedonspiralandwavedrawings AT ketankotecha explainableartificialintelligenceexaimodelsforearlypredictionofparkinsonx2019sdiseasebasedonspiralandwavedrawings AT ajithabraham explainableartificialintelligenceexaimodelsforearlypredictionofparkinsonx2019sdiseasebasedonspiralandwavedrawings |