An AI-Based Prediction of Cognitive Capacity in Older Adults and Individuals With Mild Cognitive Impairment During Virtual Reality Driving Tasks
From Eye Movements to Visuomotor Coupling: An AI-Based Prediction of Cognitive Capacity in Older Adults and Individuals With Mild Cognitive Impairment During Virtual Reality Driving Tasks
Driving ability in older adults is essential for independent mobility and social participation, yet declines under high cognitive load or distraction often lead to visual attention failures such as "look-but-fail-to-see," increasing crash risk. Older adults and individuals with mild cognitive impairment (MCI) show impairments in visual attention, executive control, and visuomotor integration, which are not adequately captured by conventional assessments. Virtual reality (VR) integrated with eye-tracking and upper-limb motion analysis enables ecologically valid simulation of driving scenarios and precise quantification of visuomotor behavior. However, current studies are limited by single-scenario designs, unimodal AI models, and insufficient integration of action-related data.
This study proposes a multi-phase framework: Year 1 develops an eye-movement-based AI model for MCI identification; Year 2 integrates multimodal data in VR driving tasks; and Year 3 establishes an explainable AI system with longitudinal validation. The study aims to advance cognitive assessment and develop a digital tool for early MCI detection and driving risk prediction.
Visão geral do estudo
Status
Descrição detalhada
Driving ability in older adults is closely associated with independent mobility and social participation. However, under conditions of high cognitive load or distraction, visual attention failures-such as the "look-but-fail-to-see" phenomenon-frequently occur and substantially increase crash risk. Previous studies have demonstrated that older adults and individuals with mild cognitive impairment (MCI) exhibit declines in visual attention allocation, executive control, and visuomotor transformation efficiency. These dynamic regulatory processes are difficult to capture using conventional paper-and-pencil or static neuropsychological assessments, underscoring the need for ecologically valid and dynamic evaluation approaches.
Virtual reality (VR), when integrated with eye-tracking and upper-limb motion analysis, enables the simulation of realistic driving environments under safe and controlled conditions. This approach facilitates precise quantification of visual search behavior, hazard detection, and visuomotor coupling, thereby offering a novel framework for cognitive assessment and driving risk prediction. Despite these advances, three critical gaps remain in the current literature: (1) a lack of systematic investigations focusing on older adults and individuals with MCI across diverse VR driving scenarios to examine visual search and attentional control; (2) artificial intelligence (AI) models that are predominantly limited to single tasks or single modalities, restricting their ability to generalize across contexts; and (3) insufficient integration of upper-limb operational data to fully characterize the dynamic interactions among vision, action, and cognition.
To address these gaps, this study adopts a multi-phase, multi-level research design. In Year 1, a VR-based eye-movement system incorporating controllable cognitive load will be developed to examine pro-saccade and anti-saccade performance among young adults, cognitively healthy older adults, and individuals with MCI. This phase will establish a high-sensitivity, eye-movement-based AI model for MCI identification. In Year 2, the framework will be extended to multi-scenario VR driving tasks through the synchronous integration of eye-tracking and upper-limb operational data, enabling characterization of visuomotor coupling under varying cognitive demands. External validation, transfer learning, and multimodal fusion techniques will be applied to enhance cross-scenario generalizability. In Year 3, multimodal datasets will be integrated to develop an explainable artificial intelligence (XAI) prediction system. Longitudinal follow-up will be conducted to evaluate its prognostic validity for changes in cognitive and driving performance, ultimately leading to a clinically applicable decision-support prototype.
At the theoretical level, this study aims to elucidate the mechanisms underlying visual attention, working memory, executive control, and visuomotor coupling in older adults and individuals with MCI under dynamic conditions. At the clinical and practical levels, it seeks to develop a non-invasive and repeatable digital cognitive screening tool for early MCI detection and older-driver risk assessment, as well as to provide evidence-based support for traffic safety policy development.
Tipo de estudo
Inscrição (Estimado)
Contactos e Locais
Contato de estudo
- Nome: Hsiu-Yun Hsu, Ph.D
- Número de telefone: 2669 886-6-2353535
- E-mail: hyhsu@mail.ncku.edu.tw
Locais de estudo
-
-
Taiwan
-
Tainan, Taiwan, Taiwan, 704
- National Cheng-Kung University Hospital
-
-
Critérios de participação
Critérios de elegibilidade
Idades elegíveis para estudo
- Adulto
- Adulto mais velho
Aceita Voluntários Saudáveis
Método de amostragem
População do estudo
Descrição
Inclusion Criteria:
- (1) a score of 23 or higher on the Montreal Cognitive Assessment; (2) a Clinical Dementia Rating score of 0 for cognitively healthy participants or 0.5 for participants with mild cognitive impairment (MCI); (3) healthy young adults aged between 30 and 39 years, and cognitively healthy older adults and participants with MCI aged between 65 and 85 years; (4) right-hand dominance; and (5) adequate visual function to complete VR and eye-tracking tasks, defined as corrected binocular visual acuity of at least 0.5 without severe visual field deficits.
Exclusion Criteria:
- (1) the presence or history of major psychiatric disorders or central nervous system diseases; (2) significant ocular diseases, such as untreated cataracts, active retinal diseases, moderate-to-severe or poorly controlled glaucoma, or marked visual field deficits beyond a specified level; (3) epilepsy; and (4) severe dizziness or VR-induced motion sickness.
Plano de estudo
Como o estudo é projetado?
Detalhes do projeto
Coortes e Intervenções
Grupo / Coorte |
|---|
|
Young Adults
Healthy young adults (aged 30-39 years) with no history of neurological or psychiatric disorders.
Participants will complete standardized virtual reality (VR) driving tasks with integrated eye-tracking and upper-limb motion recording to establish normative visuomotor and cognitive performance benchmarks.
|
|
Cognitively Healthy Older Adults
Community-dwelling older adults (≥65 years) with normal cognitive function based on standardized screening (e.g., MoCA within normal range).
Participants will undergo the same VR-based assessments to examine age-related changes in visual attention, executive control, and visuomotor coupling.
|
|
Mild Cognitive Impairment (MCI)
Older adults clinically identified with mild cognitive impairment according to established diagnostic criteria.
Participants will complete identical VR driving tasks to investigate alterations in visual search behavior, attentional control, and visuomotor integration, and to support development of predictive AI models for cognitive decline and driving risk.
|
O que o estudo está medindo?
Medidas de resultados primários
Medida de resultado |
Descrição da medida |
Prazo |
|---|---|---|
|
Time to First Fixation (TFF) within the Area of Interest
Prazo: Baseline
|
Time to First Fixation (TFF) is defined as the time interval from event onset (t₀) to the participant's first fixation within the predefined Area of Interest (AOI).
A shorter TFF indicates faster attentional orienting.
Units of Measure: milliseconds (ms) for each predefined AOI/event condition.
|
Baseline
|
Medidas de resultados secundários
Medida de resultado |
Descrição da medida |
Prazo |
|---|---|---|
|
Number of Fixations on the Area of Interest
Prazo: Baseline
|
Number of Fixations is defined as the total count of fixations within the predefined Area of Interest (AOI) during task performance.
A higher number of fixations indicates greater visual search activity toward target stimuli.
Unit of Measure: count.
|
Baseline
|
|
Total Fixation Duration (TFD) on the Area of Interest
Prazo: Baseline
|
Total Fixation Duration (TFD) is defined as the cumulative fixation time within the predefined Area of Interest (AOI) during the task.
Longer fixation duration indicates greater attentional engagement with the target stimulus.
Unit of measure: Milliseconds.
|
Baseline
|
|
Steering Reaction Time
Prazo: Baseline
|
Steering Reaction Time is defined as the interval from event onset (t₀) to the initial steering wheel deviation of ≥5°.
This measure reflects motor initiation speed during driving tasks.
Steering Reaction Time will be calculated separately for each driving scenario or curve type.
Unit of Measure: Milliseconds (ms).
|
Baseline
|
|
Steering Reversal Rate (SRR)
Prazo: Baseline
|
Steering Reversal Rate (SRR) is defined as the number of steering direction changes per minute during curve driving, using a steering-wheel angle threshold of 0.5°.
Higher SRR values indicate increased steering corrections and may reflect reduced motor control stability and increased driving workload.
Unit of Measure: Reversals/minute.
|
Baseline
|
|
Speed Change During Driving Tasks
Prazo: Baseline
|
Speed Change is defined as the difference in average vehicle speed before and after event onset during driving tasks.
This measure reflects adaptive driving behavior in response to traffic events or environmental changes, with larger changes indicating greater speed adjustment.
Speed Change will be calculated separately for each driving condition.
Unit of Measure: Kilometers per hour (km/h).
|
Baseline
|
|
Reaction Time in Speed-Limit Judgment Tasks
Prazo: Baseline
|
Reaction Time in Speed-Limit Judgment Tasks is defined as the elapsed time between the presentation of a speed-limit stimulus and the participant's response.
This measure assesses the speed of driving-related decision-making under varying cognitive demands, with longer reaction times indicating greater cognitive processing demands.
Reaction time will be calculated for each task condition.
Unit of Measure: Milliseconds (ms).
|
Baseline
|
|
Accuracy in Speed-Limit Judgment Tasks
Prazo: Baseline
|
Accuracy in Speed-Limit Judgment Tasks is defined as the percentage of correct responses to speed-limit judgment tasks performed during driving.
This measure assesses cognitive performance under dual-task conditions, with higher accuracy indicating better task performance and cognitive processing.
Accuracy will be calculated for each task condition.
Unit of Measure: Percentage (%).
|
Baseline
|
|
Standard Deviation of Lane Position (SDLP)
Prazo: Baseline
|
Standard Deviation of Lane Position (SDLP) is defined as the variability of the vehicle's lateral lane position during driving tasks.
SDLP reflects lane-keeping ability and driving stability under different driving conditions.
The lower SDLP mean better driving stability.
Unit of Measure: Meters (m).
|
Baseline
|
|
Frequency of Driving Errors
Prazo: Baseline
|
Driving Errors are defined as the number of adverse driving events occurring during the driving task, including lane departures, collisions, and incorrect responses to secondary tasks.
This measure reflects overall driving performance and safety.
Error frequencies will be calculated for each driving condition, and error types will be analyzed separately.
Unit of Measure: Count.
|
Baseline
|
|
Montreal Cognitive Assessment (MoCA) Score
Prazo: Baseline
|
The MoCA is used to assess global cognitive function.
Participants complete a standardized set of tasks covering attention, memory, language, visuospatial abilities, and executive functions.
The total MoCA score reflects overall cognitive performance.Unit of Measure: Points (0-30).
|
Baseline
|
|
Digit Span Test Score
Prazo: baseline
|
The Digit Span Test evaluates working memory capacity by requiring participants to recall sequences of numbers in forward and backward order.
The highest correctly recalled sequence length is recorded separately for forward and backward trials.
Unit of Measure: Number of digits correctly recalled.
|
baseline
|
|
Knox Cube Test-Revised Score
Prazo: baseline
|
The Knox Cube Test-Revised assesses visuospatial sequential memory.
Participants must replicate sequences of cube taps demonstrated by the examiner.
The total number of correctly recalled sequences reflects visuospatial memory performance.
Unit of Measure: Number of sequences correctly recalled.
|
baseline
|
|
Conners Continuous Performance Test 3 (CPT 3) Metrics
Prazo: baseline
|
The Conners CPT 3 assesses sustained attention and inhibitory control.
Primary metrics include reaction time, omission errors, commission errors, and detectability (d').
Each metric will be reported separately for each test condition.
Unit of Measure: Reaction Time: milliseconds (ms); Omission Errors: count; Commission Errors: count; and Detectability (d'): unitless index.
|
baseline
|
Colaboradores e Investigadores
Patrocinador
Datas de registro do estudo
Datas Principais do Estudo
Início do estudo (Estimado)
Conclusão Primária (Estimado)
Conclusão do estudo (Estimado)
Datas de inscrição no estudo
Enviado pela primeira vez
Enviado pela primeira vez que atendeu aos critérios de CQ
Primeira postagem (Real)
Atualizações de registro de estudo
Última Atualização Postada (Real)
Última atualização enviada que atendeu aos critérios de controle de qualidade
Última verificação
Mais Informações
Termos relacionados a este estudo
Termos MeSH relevantes adicionais
Outros números de identificação do estudo
- A-ER-115-039
Informações sobre medicamentos e dispositivos, documentos de estudo
Estuda um medicamento regulamentado pela FDA dos EUA
Estuda um produto de dispositivo regulamentado pela FDA dos EUA
Essas informações foram obtidas diretamente do site clinicaltrials.gov sem nenhuma alteração. Se você tiver alguma solicitação para alterar, remover ou atualizar os detalhes do seu estudo, entre em contato com register@clinicaltrials.gov. Assim que uma alteração for implementada em clinicaltrials.gov, ela também será atualizada automaticamente em nosso site .