Artificial Intelligence Applications for Assessment, Monitoring, and Management of Parkinson Disease Symptoms: Protocol for a Systematic Review
Bibliographic record
Abstract
BACKGROUND: Parkinson disease (PD) is the second most prevalent neurodegenerative disease, with around 10 million people with PD worldwide. Current assessments of PD symptoms are conducted by questionnaires and clinician assessments and have many limitations, including unreliable reporting of symptoms, little autonomy for patients over their disease management, and standard clinical review intervals regardless of disease status or clinical need. To address these limitations, digital technologies including wearable sensors, smartphone apps, and artificial intelligence (AI) methods have been implemented for this population. Many reviews have explored the use of AI in the diagnosis of PD and management of specific symptoms; however, there is limited research on the application of AI to the monitoring and management of the range of PD symptoms. A comprehensive review of the application of AI methods is necessary to address the gap of high-quality reviews and highlight the developments of the use of AI within PD care. OBJECTIVE: The purpose of this protocol is to guide a systematic review to identify and summarize the current applications of AI applied to the assessment, monitoring, and management of PD symptoms. METHODS: This review protocol was structured using the PRISMA-P (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocols) and the Population, Intervention, Comparator, Outcome, and Study (PICOS) frameworks. The following 5 databases will be systematically searched: PubMed, IEEE Xplore, Institute for Scientific Information's Web of Science, Scopus, and the Cochrane Library. Title and abstract screening, full-text review, and data extraction will be conducted by 2 independent reviewers. Data will be extracted into a predetermined form, and any disagreements in screening or extraction will be discussed. Risk of bias will be assessed using the Cochrane Collaboration Risk of Bias 2 tool for randomized trials and the Mixed Methods Appraisal Tool for nonrandomized trials. RESULTS: As of April 2023, this systematic review has not yet been started. It is expected to begin in May 2023, with the aim to complete by September 2023. CONCLUSIONS: The systematic review subsequently conducted as a product of this protocol will provide an overview of the AI methods being used for the assessment, monitoring, and management of PD symptoms. This will identify areas for further research in which AI methods can be applied to the assessment or management of PD symptoms and could support the future implementation of AI-based tools for the effective management of PD. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/46581.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.054 | 0.087 |
| Meta-epidemiology (narrow) | 0.005 | 0.004 |
| Meta-epidemiology (broad) | 0.015 | 0.015 |
| Bibliometrics | 0.011 | 0.012 |
| Science and technology studies | 0.004 | 0.004 |
| Scholarly communication | 0.007 | 0.007 |
| Open science | 0.005 | 0.005 |
| Research integrity | 0.006 | 0.006 |
| Insufficient payload (model declined to judge) | 0.068 | 0.008 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".