Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Artificial intelligence-enabled detection and assessment of Parkinson's disease using multimodal data: A survey

Aite Zhao, Yongcan Liu, Xinglin Yu, Xinyue Xing

TL;DR

The surveyed work addresses the challenge of diagnosing and monitoring Parkinson's disease (PD) without clear biomarkers by compiling ML and DL approaches that fuse multimodal symptom data (speech, gait, hand movements). It highlights a shift from single-modality analyses toward multimodal fusion using architectures such as CorrMNN, ASTCapsNet, Transformers, and capsule networks, achieving strong diagnostic and severity-estimation performance. The review catalogs public datasets across speech, gait, hand movements, and multimodal collections, and discusses trends, strengths, and limitations, including data heterogeneity and standardization gaps. It also outlines future directions, emphasizing the need for comprehensive multimodal datasets, privacy-aware data collection, and clinical integration of AI-enabled PD assessment tools.

Abstract

The rapid emergence of highly adaptable and reusable artificial intelligence (AI) models is set to revolutionize the medical field, particularly in the diagnosis and management of Parkinson's disease (PD). Currently, there are no effective biomarkers for diagnosing PD, assessing its severity, or tracking its progression. Numerous AI algorithms are now being used for PD diagnosis and treatment, capable of performing various classification tasks based on multimodal and heterogeneous disease symptom data, such as gait, hand movements, and speech patterns of PD patients. They provide expressive feedback, including predicting the potential likelihood of PD, assessing the severity of individual or multiple symptoms, aiding in early detection, and evaluating rehabilitation and treatment effectiveness, thereby demonstrating advanced medical diagnostic capabilities. Therefore, this work provides a surveyed compilation of recent works regarding PD detection and assessment through biometric symptom recognition with a focus on machine learning and deep learning approaches, emphasizing their benefits, and exposing their weaknesses, and their impact in opening up newer research avenues. Additionally, it also presents categorized and characterized descriptions of the datasets, approaches, and architectures employed to tackle associated constraints. Furthermore, the paper explores the potential opportunities and challenges presented by data-driven AI technologies in the diagnosis of PD.

Artificial intelligence-enabled detection and assessment of Parkinson's disease using multimodal data: A survey

TL;DR

The surveyed work addresses the challenge of diagnosing and monitoring Parkinson's disease (PD) without clear biomarkers by compiling ML and DL approaches that fuse multimodal symptom data (speech, gait, hand movements). It highlights a shift from single-modality analyses toward multimodal fusion using architectures such as CorrMNN, ASTCapsNet, Transformers, and capsule networks, achieving strong diagnostic and severity-estimation performance. The review catalogs public datasets across speech, gait, hand movements, and multimodal collections, and discusses trends, strengths, and limitations, including data heterogeneity and standardization gaps. It also outlines future directions, emphasizing the need for comprehensive multimodal datasets, privacy-aware data collection, and clinical integration of AI-enabled PD assessment tools.

Abstract

The rapid emergence of highly adaptable and reusable artificial intelligence (AI) models is set to revolutionize the medical field, particularly in the diagnosis and management of Parkinson's disease (PD). Currently, there are no effective biomarkers for diagnosing PD, assessing its severity, or tracking its progression. Numerous AI algorithms are now being used for PD diagnosis and treatment, capable of performing various classification tasks based on multimodal and heterogeneous disease symptom data, such as gait, hand movements, and speech patterns of PD patients. They provide expressive feedback, including predicting the potential likelihood of PD, assessing the severity of individual or multiple symptoms, aiding in early detection, and evaluating rehabilitation and treatment effectiveness, thereby demonstrating advanced medical diagnostic capabilities. Therefore, this work provides a surveyed compilation of recent works regarding PD detection and assessment through biometric symptom recognition with a focus on machine learning and deep learning approaches, emphasizing their benefits, and exposing their weaknesses, and their impact in opening up newer research avenues. Additionally, it also presents categorized and characterized descriptions of the datasets, approaches, and architectures employed to tackle associated constraints. Furthermore, the paper explores the potential opportunities and challenges presented by data-driven AI technologies in the diagnosis of PD.

Paper Structure

This paper contains 14 sections, 10 figures, 8 tables.

Table of Contents

  1. Introduction
  2. PD Diagnosis and Assessment through ML-based Approaches
  3. Single Modal PD Symptom Analysis
  4. Multimodal PD Symptom Analysis
  5. PD Diagnosis and Assessment through DL-based Approaches
  6. Single Modal Learning for PD Symptom
  7. Single-task-based Research on PD
  8. Multimodal Learning for PD Symptom
  9. Multi-Source Datasets
  10. Speech datasets
  11. Hand-movement datasets
  12. Gait dataset:
  13. Multimodal dataset:
  14. CONCLUSIONS AND FUTURE DIRECTIONS

Figures (10)

  • Figure 1: The process of PD multi-modality and multi-symptom detection and evaluation.
  • Figure 2: Classification of modalities for the diagnosis and assessment of Parkinson’s Disease (PD).
  • Figure 3: Single modal PD symptom assessment and diagnosis methods using ML (2014-2024).
  • Figure 4: Single modal PD symptom assessment and diagnosis methods using DL (2014-2024).
  • Figure 5: Multimodal PD symptom assessment and diagnosis methods using DL and ML (2014-2024).
  • ...and 5 more figures