Applications of artificial intelligence in dementia research

Use of artificial intelligence to support quality of life of people with dementia: A scoping review

BACKGROUND

Dementia has an impact on the quality of life (QoL) of people with dementia. Tailored services are crucial for improving their QoL. Advances in artificial intelligence (AI) offer opportunities for personalised care, potentially delaying institutionalisation and enhancing QoL. However, AI's specific role in approaches to support QoL for people with dementia remains unclear. This scoping review aims to synthesise the scientific evidence and grey literature on how AI can support the QoL of people with dementia.

METHOD

Following Joanna Briggs Institute guidelines, we searched PubMed, Scopus, ACM Digital Library, and Google Scholar in January 2024. Studies on AI, QoL (using Lawton's four-domain QoL definition), and people with dementia across various care settings were included. Two reviewers conducted a two-stage screening, and a narrative synthesis identified common themes arising from the individual studies to address the research question.

RESULTS

The search yielded 5.467 studies, after screening, thirty studies were included. Three AI categories were identified: monitoring systems, social robots, and AI approaches for performing activities of daily living. Most studies were feasibility studies, with little active involvement of people with dementia during the research process. Most AI-based approaches were monitoring systems targeting Lawton's behavioural competence (capacity for independent functioning) domain.

CONCLUSION

This review highlights that AI applications for enhancing QoL in people with dementia are still in early development, with research largely limited to small-scale feasibility studies rather than demonstrating clinical effectiveness. While AI holds promise, further exploration and rigorous real-world validation are needed before AI can meaningfully impact the daily lives of people with dementia.

A preliminary study of the reliability and validity of the Uyghur version of the NUCOG cognitive screening application

INTRODUCTION

Technological advances and artificial intelligence now make it feasible to administer cognitive assessments on touch-screen devices. The aim of this study is to develop a Uyghur version of the NUCOG cognitive screening application and evaluate its reliability, validity, and optimal cutoff scores among Uyghur people with cognitive impairment.

METHODS

The English version of the NUCOG app was translated and adapted into the Uyghur version (NUCOG-U). A total of 250 Uyghur people aged 55-80, including 90 normal controls, 91 patients with mild cognitive impairment (MCI), and 69 dementia patients, were randomly selected and administered with NUCOG, MoCA-U, Mini-Mental State Examination (MMSE), and other neuropsychological batteries. ROC curves were generated to determine the optimal cutoff values.

RESULTS

NUCOG-U version showed high internal consistency (Cronbach's α = 0. 826), inter-rater reliability (ICC = 0.999), and test - retest reliability (r = 0.998, p < 0.001). NUCOG scores were significantly correlated with those of MoCA-U (r = 0.896, p < 0.001) and MMSE(r = 0.899, p < 0.001). NUCOG scores were significantly different among the three groups (p < 0.001). The optimal cutoff value for MCI was 80.5, with a sensitivity of 100% and specificity of 73%, and 70 for dementia, with a sensitivity of 94.1% and specificity of 100%.

CONCLUSION

The NUCOG-U shows high reliability and validity and is suitable for screening cognitive function in the elderly Uyghur population. The optimal cutoff scores to detect mild cognitive impairment and dementia in the Uyghur people are 80.5 and 70, respectively.

Neuropsychological and electrophysiological measurements for diagnosis and prediction of dementia: a review on Machine Learning approach

INTRODUCTION

Emerging and advanced technologies in the field of Artificial Intelligence (AI) represent promising methods to predict and diagnose neurodegenerative diseases, such as dementia. By using multimodal approaches, Machine Learning (ML) seems to provide a better understanding of the pathological mechanisms underlying the onset of dementia. The purpose of this review was to discuss the current ML application in the field of neuropsychology and electrophysiology, exploring its results in both prediction and diagnosis for different forms of dementia, such as Alzheimer's disease (AD), Vascular Dementia (VaD), Dementia with Lewy bodies (DLB), and Frontotemporal Dementia (FTD).

METHODS

Main ML-based papers focusing on neuropsychological assessments and electroencephalogram (EEG) studies were analyzed for each type of dementia.

RESULTS

An accuracy ranging between 70 % and 90 % or even more was observed in all neurophysiological and electrophysiological results trained by ML. Among all forms of dementia, the most significant findings were observed for AD. Relevant results were mostly related to diagnosis rather than prediction, because of the lack of longitudinal studies with appropriate follow-up duration. However, it remains unclear which ML algorithm performs better in diagnosing or predicting dementia.

CONCLUSIONS

Neuropsychological and electrophysiological measurements, together with ML analysis, may be considered as reliable instruments for early detection of dementia.

Introduction to Large Language Models (LLMs) for dementia care and research

Introduction

Dementia is a progressive neurodegenerative disorder that affects cognitive abilities including memory, reasoning, and communication skills, leading to gradual decline in daily activities and social engagement. In light of the recent advent of Large Language Models (LLMs) such as ChatGPT, this paper aims to thoroughly analyse their potential applications and usefulness in dementia care and research.

Method

To this end, we offer an introduction into LLMs, outlining the key features, capabilities, limitations, potential risks, and practical considerations for deployment as easy-to-use software (e.g., smartphone apps). We then explore various domains related to dementia, identifying opportunities for LLMs to enhance understanding, diagnostics, and treatment, with a broader emphasis on improving patient care. For each domain, the specific contributions of LLMs are examined, such as their ability to engage users in meaningful conversations, deliver personalized support, and offer cognitive enrichment. Potential benefits encompass improved social interaction, enhanced cognitive functioning, increased emotional well-being, and reduced caregiver burden. The deployment of LLMs in caregiving frameworks also raises a number of concerns and considerations. These include privacy and safety concerns, the need for empirical validation, user-centered design, adaptation to the user's unique needs, and the integration of multimodal inputs to create more immersive and personalized experiences. Additionally, ethical guidelines and privacy protocols must be established to ensure responsible and ethical deployment of LLMs.

Results

We report the results on a questionnaire filled in by people with dementia (PwD) and their supporters wherein we surveyed the usefulness of different application scenarios of LLMs as well as the features that LLM-powered apps should have. Both PwD and supporters were largely positive regarding the prospect of LLMs in care, although concerns were raised regarding bias, data privacy and transparency.

Discussion

Overall, this review corroborates the promising utilization of LLMs to positively impact dementia care by boosting cognitive abilities, enriching social interaction, and supporting caregivers. The findings underscore the importance of further research and development in this field to fully harness the benefits of LLMs and maximize their potential for improving the lives of individuals living with dementia.

Cognitive Screening for Mild Cognitive Impairment: Clinician Perspectives on Current Practices and Future Directions

 This study surveyed 51 specialist clinicians for their views on existing cognitive screening tests for mild cognitive impairment and their opinions about a hypothetical remote screener driven by artificial intelligence (AI). Responses revealed significant concerns regarding the sensitivity, specificity, and time taken to administer current tests, along with a general willingness to consider adopting telephone-based screening driven by AI. Findings highlight the need to design screeners that address the challenges of recognizing the earliest stages of cognitive decline and that prioritize not only accuracy but also stakeholder input.

Artificial Intelligence in Dementia: A Bibliometric Study

The applications of artificial intelligence (AI) in dementia research have garnered significant attention, prompting the planning of various research endeavors in current and future studies. The objective of this study is to provide a comprehensive overview of the research landscape regarding AI and dementia within scholarly publications and to suggest further studies for this emerging research field. A search was conducted in the Web of Science database to collect all relevant and highly cited articles on AI-related dementia research published in English until 16 May 2023. Utilizing bibliometric indicators, a search strategy was developed to assess the eligibility of titles, utilizing abstracts and full texts as necessary. The Bibliometrix tool, a statistical package in R, was used to produce and visualize networks depicting the co-occurrence of authors, research institutions, countries, citations, and keywords. We obtained a total of 1094 relevant articles published between 1997 and 2023. The number of annual publications demonstrated an increasing trend over the past 27 years. Journal of Alzheimer's Disease (39/1094, 3.56%), Frontiers in Aging Neuroscience (38/1094, 3.47%), and Scientific Reports (26/1094, 2.37%) were the most common journals for this domain. The United States (283/1094, 25.86%), China (222/1094, 20.29%), India (150/1094, 13.71%), and England (96/1094, 8.77%) were the most productive countries of origin. In terms of institutions, Boston University, Columbia University, and the University of Granada demonstrated the highest productivity. As for author contributions, Gorriz JM, Ramirez J, and Salas-Gonzalez D were the most active researchers. While the initial period saw a relatively low number of articles focusing on AI applications for dementia, there has been a noticeable upsurge in research within this domain in recent years (2018-2023). The present analysis sheds light on the key contributors in terms of researchers, institutions, countries, and trending topics that have propelled the advancement of AI in dementia research. These findings collectively underscore that the integration of AI with conventional treatment approaches enhances the effectiveness of dementia diagnosis, prediction, classification, and monitoring of treatment progress.