Machine learning for the detection and diagnosis of cognitive impairment in Parkinson’s Disease - a systematic review

Aug 2, 2026

Upload by Eliana

Parkinson’s Disease is the second most common neurological condition in people over 60, and cognitive impairment is a major clinical symptom with long-term risk of severe dysfunction up to two decades after diagnosis. Existing detection and diagnostic processes struggle to predict early decline, influenced by ageing populations, limited specialist capacity, and subjective clinical interpretation. This systematic review surveys studies applying machine learning to identify and diagnose cognitive impairment in Parkinson’s Disease, assessing feasibility, implementation impacts, and recommending suitable methods, modalities, and outcome measures.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages39

Reading Time1 h 38 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusions

Introduction

Parkinson’s Disease and cognitive impairment

Clinical assessment and limitations

Emerging data modalities and criteria

Machine learning for the detection and diagnosis of cognitive impairment in Parkinson’s Disease: a systematic review Callum Altham 1Y*, Huaizhong Zhang 1Y, Ella Pereira 1Y , 1 Department of Computer Science, Edge Hill University, Ormskirk, Lancashire, United Kingdom YThese authors contributed equally to this work. * Corresponding Author E-mail: [althamc@edgehill.ac.uk](althamc@edgehill.ac.uk) Abstract Background Parkinson’s Disease is the second most common neurological disease in over 60s. Cognitive impairment is a major clinical symptom, with risk of severe dysfunction up to 20 years post-diagnosis. Processes for detection and diagnosis of cognitive impairments are not sufficient to predict decline at an early stage for significant impact. Ageing populations, neurologist shortages and subjective interpretations reduce the effectiveness of decisions and diagnoses. Researchers are now utilising machine learning for detection and diagnosis of cognitive impairment based on symptom presentation and clinical investigation. This work aims to provide an overview of published studies applying machine learning to detecting and diagnosing cognitive impairment, evaluate the feasibility of implemented methods, their impacts, and provide suitable recommendations for methods, modalities and outcomes. Methods To provide an overview of the machine learning techniques, data sources and modalities used for detection and diagnosis of cognitive impairment in Parkinson’s Disease, we conducted a review of studies published on the PubMed, IEEE Xplore, Scopus and ScienceDirect databases. 70 studies were included in this review, with the most relevant information extracted from each. From each study, strategy, modalities, sources, methods and outcomes were extracted. Results Literatures demonstrate that machine learning techniques have potential to provide considerable insight into investigation of cognitive impairment in Parkinson’s Disease. Our review demonstrates the versatility of machine learning in analysing a wide range of different modalities for the detection and diagnosis of cognitive impairment in Parkinson’s Disease, including imaging, EEG, speech and more, yielding notable diagnostic accuracy. Conclusions Machine learning based interventions have the potential to glean meaningful insight from data, and may offer non-invasive means of enhancing cognitive impairment 1 2 assessment, providing clear and formidable potential for implementation of machine 3 learning into clinical practice. 4 Introduction 5 Parkinson’s Disease (PD) is the most common neurodegenerative disorder [1], 6 characterised by motor and non-motor symptoms including dyskinesia, tremors and 7 balance issues [2] . Over 145K people in the UK are estimated to be living with PD [3], 8 making PD the second most common neurological disease in individuals over the age of 9 60. PD has an estimated global prevalence rate of 1%, doubling global PD populations 10 between 1990 and 2016 making PD the fastest-growing neurodegenerative condition in 11 the world [4–6] . 12 PD sufferers have a higher risk of developing severe cognitive complications resulting 13 in consistent and damaging cognitive impairments (CI) giving rise to a noticeable loss in 14 cognitive functioning and behavioural abilities, and can lead to the development of 15 overall cognitive decline characteristic of dementia, known as Parkinson’s Disease 16 Dementia (PDD) [7] . Between 70-95% of PD patients are likely to experience some 17 degree of CI as PD advances, with PDD frequently developing 10-20 years post 18 diagnosis [8,9], with potential for severe impacts on overall quality of life, familial 19 relationships and societal functioning [10] . Treatment and disease management create 20 severe burdens at medical [11], economic [12,13] and personal levels, with identification 21 of a direct, specific cause for CI development remaining a worki

FAQs

What problem does the review address in Parkinson’s Disease cognitive impairment care?

Detection and diagnosis often cannot reliably predict early decline, and decisions may be affected by subjective interpretation and limited specialist resources. This reduces the effectiveness of early-stage clinical decisions.

How was the systematic review conducted?

The review included studies from PubMed, IEEE Xplore, Scopus, and ScienceDirect, extracting strategies, modalities, data sources, methods, and outcomes. Seventy studies were included.

What types of data modalities are explored for machine learning–based detection and diagnosis?

The review highlights the versatility of machine learning across imaging, EEG, speech, and other modalities, aiming to improve diagnostic accuracy.

Aug 2, 2026

Upload by Eliana