Machine learning and wearable sensors for automated Parkinson’s disease diagnosis aid: a systematic review

di Biase, Lazzaro; Pecoraro, Pasquale Maria; Pecoraro, Giovanni; Shah, Syed Ahmar; Di Lazzaro, Vincenzo

doi:10.1007/s00415-024-12611-x

J Neurol

2024

DOI: 10.1007/s00415-024-12611-x

|View full text |Cite

Machine learning and wearable sensors for automated Parkinson’s disease diagnosis aid: a systematic review

Lazzaro di Biase,

Pasquale Maria Pecoraro,

Giovanni Pecoraro

et al.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 99 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Improved Deep Learning for Parkinson’s Diagnosis Based on Wearable Sensors

Yu,

Meng,

Liang

et al. 2024

Electronics

View full text Add to dashboard Cite

Parkinson’s disease is a neurodegenerative disease that seriously affects the quality of life of patients. In this study, we propose a new Parkinson’s diagnosis method using deep learning techniques. The method takes multi-channel sensor signals as inputs, and the full convolutional and LSTM blocks of the model perceive the same time-series inputs from two different views, and connect the extracted spatial features with temporal features. In order to improve the detection performance, a channel attention mechanism was incorporated into the model, and a data augmentation approach was used to eliminate the effect of unbalanced datasets on model training. The pd vs. hc and pd vs. dd classification tasks were performed, which improved accuracy by 4.25% and 8.03%, respectively, compared to the previous best results. Both improvements were higher than the previous methods using machine learning combined with feature extraction. To utilize the available data resources more effectively, this study conducted the pd vs. hc vs. dd triple classification task for the first time, which improved the model’s ability to identify disease features. In that task, the accuracy rate reached 78.23%. The experimental results fully demonstrated the effectiveness of the proposed deep learning method for Parkinson’s diagnosis.

show abstract

Improved Deep Learning for Parkinson’s Diagnosis Based on Wearable Sensors

Yu,

Meng,

Liang

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

Biochemical Sensors for Personalized Therapy in Parkinson’s Disease: Where We Stand

Ciarrocchi,

Pecoraro,

Zompanti

et al. 2024

JCM

View full text Add to dashboard Cite

Since its first introduction, levodopa has remained the cornerstone treatment for Parkinson’s disease. However, as the disease advances, the therapeutic window for levodopa narrows, leading to motor complications like fluctuations and dyskinesias. Clinicians face challenges in optimizing daily therapeutic regimens, particularly in advanced stages, due to the lack of quantitative biomarkers for continuous motor monitoring. Biochemical sensing of levodopa offers a promising approach for real-time therapeutic feedback, potentially sustaining an optimal motor state throughout the day. These sensors vary in invasiveness, encompassing techniques like microdialysis, electrochemical non-enzymatic sensing, and enzymatic approaches. Electrochemical sensing, including wearable solutions that utilize reverse iontophoresis and microneedles, is notable for its potential in non-invasive or minimally invasive monitoring. Point-of-care devices and standard electrochemical cells demonstrate superior performance compared to wearable solutions; however, this comes at the cost of wearability. As a result, they are better suited for clinical use. The integration of nanomaterials such as carbon nanotubes, metal–organic frameworks, and graphene has significantly enhanced sensor sensitivity, selectivity, and detection performance. This framework paves the way for accurate, continuous monitoring of levodopa and its metabolites in biofluids such as sweat and interstitial fluid, aiding real-time motor performance assessment in Parkinson’s disease. This review highlights recent advancements in biochemical sensing for levodopa and catecholamine monitoring, exploring emerging technologies and their potential role in developing closed-loop therapy for Parkinson’s disease.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Machine learning and wearable sensors for automated Parkinson’s disease diagnosis aid: a systematic review

Cited by 2 publications

References 99 publications

Improved Deep Learning for Parkinson’s Diagnosis Based on Wearable Sensors

Improved Deep Learning for Parkinson’s Diagnosis Based on Wearable Sensors

Biochemical Sensors for Personalized Therapy in Parkinson’s Disease: Where We Stand

Contact Info

Product

Resources

About