Refining Parkinson’s syndrome symptom forecasting using incorporated ocular imaging and the SymptoSense model
Abstract Diagnosing Parkinson's disease (PD) in its early stages, particularly in older adults, remains a challenge due to the complexity of symptoms and their overlap with other age-related conditions. To improve early diagnosis, our study introduces the SymptoSense Model, which integrates adv...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-05-01
|
| Series: | Discover Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-025-07195-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Diagnosing Parkinson's disease (PD) in its early stages, particularly in older adults, remains a challenge due to the complexity of symptoms and their overlap with other age-related conditions. To improve early diagnosis, our study introduces the SymptoSense Model, which integrates advanced Natural Language Processing (NLP) with ocular imaging techniques to accurately predict PD symptoms from patient-generated text. Leveraging a corpus developed by the Michael J. Fox Foundation for Parkinson's Research and the Institute for Clinical Evaluative Sciences, the model creates a patient-specific dictionary by correlating segmented words from patient responses with predefined standards. Additionally ocular imaging features of microvascular changes of retina and abnormalities in eye movements patterns are investigated to enhance prediction accuracy. Combining NLP and ocular imaging, this innovative approach is evaluated against benchmark models like Forward Maximal Matching, Backward Maximal Matching, Bi-directional Maximal Matching, Word Embeddings, Sentiment Analysis, and Term Frequency-Inverse Document Frequency. The SymptoSense Model shows superior performance, achieving 94.2% accuracy and 0.943 precision, alongside an impressive average word segmentation time of 0.129 s. These results highlight its efficiency and potential as a robust tool in the early and accurate diagnosis of Parkinson's disease, showcasing a significant advancement in medical diagnostics and the intersection of NLP and ocular imaging in healthcare. |
|---|---|
| ISSN: | 3004-9261 |