Integrating Biomarkers From Virtual Reality and Magnetic Resonance Imaging for the Early Detection of Mild Cognitive Impairment Using a Multimodal Learning Approach: Validation Study (Preprint) DOI
Bogyeom Park, Yuwon Kim, Jinseok Park

и другие.

Опубликована: Ноя. 15, 2023

BACKGROUND Early detection of mild cognitive impairment (MCI), a transitional stage between normal aging and Alzheimer disease, is crucial for preventing the progression dementia. Virtual reality (VR) biomarkers have proven to be effective in capturing behaviors associated with subtle deficits instrumental activities daily living, such as challenges using food-ordering kiosk, early MCI. On other hand, magnetic resonance imaging (MRI) demonstrated their efficacy quantifying observable structural brain changes that can aid MCI detection. Nevertheless, relationship VR-derived MRI remains an open question. In this context, we explored integration enhance through multimodal learning approach. OBJECTIVE We aimed evaluate compare classification while also examining strengths weaknesses each Furthermore, focused on improving by leveraging integrate biomarkers. METHODS The study encompassed total 54 participants, comprising 22 (41%) healthy controls 32 (59%) patients Participants completed virtual kiosk test collect 4 (hand movement speed, scanpath length, time completion, number errors), T<sub>1</sub>-weighted scans were performed from both hemispheres. Analyses covariance used these MCI, age considered covariate. Subsequently, exhibited significant differences 2 groups train validate model at screening among controls. RESULTS support vector machine (SVM) only achieved sensitivity 87.5% specificity 90%, whereas showed 90.9% 71.4%. Moreover, correlation analysis revealed association MRI-observed atrophy impaired performance living VR environment. Notably, into SVM yielded superior results compared unimodal models, achieving higher accuracy (94.4%), (100%), (90.9%), precision (87.5%), <i>F</i><sub>1</sub>-score (93.3%). CONCLUSIONS indicate biomarkers, characterized high specificity, valuable robust, tool broader older adult population. known sensitivity, excel confirming presence approach introduced our provides insights improvement integrating diverse set

Язык: Английский

Applications of Artificial Intelligence in the Neuropsychological Assessment of Dementia: A Systematic Review DOI Open Access
Isabella Veneziani,

Angela Marra,

Caterina Formica

и другие.

Journal of Personalized Medicine, Год журнала: 2024, Номер 14(1), С. 113 - 113

Опубликована: Янв. 19, 2024

In the context of advancing healthcare, diagnosis and treatment cognitive disorders, particularly Mild Cognitive Impairment (MCI) Alzheimer’s Disease (AD), pose significant challenges. This review explores Artificial Intelligence (AI) Machine Learning (ML) in neuropsychological assessment for early detection personalized MCI AD. The includes 37 articles that demonstrate AI could be an useful instrument optimizing diagnostic procedures, predicting decline, outperforming traditional tests. Three main categories applications are identified: (1) combining with clinical data, (2) existing test batteries using ML techniques, (3) employing virtual reality games to overcome limitations Despite advancements, highlights a gap developing tools simplify clinician’s workflow underscores need explainable healthcare decision making. Future studies should bridge between technical performance measures practical utility yield accurate results facilitate clinicians’ roles. successful integration AI/ML dementia onset reduce global costs benefit aging societies.

Язык: Английский

Процитировано

19
Improving counseling effectiveness with virtual counselors through nonverbal compassion involving eye contact, facial mimicry, and head-nodding DOI Creative Commons

Doo Sung Choi,

Jongyoul Park, Martin Loeser

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Янв. 4, 2024

An effective way to reduce emotional distress is by sharing negative emotions with others. This why counseling a virtual counselor an emerging methodology, where the sharer can consult freely anytime and anywhere without having fear being judged. To improve effectiveness, most studies so far have focused on designing verbal compassion for counselors. However, recent showed that counselors' nonverbal through eye contact, facial mimicry, head-nodding also significant impact overall experience. verify this, we designed counselor's examined its effects effectiveness (i.e., intensity of anger general affect). A total 40 participants were recruited from university community. Participants then randomly assigned one two conditions: neutral condition compassionate head-nodding). shared their anger-inducing episodes average 16.30 min. Note was operated Wizard-of-Oz method actually technically implemented. Results reduced significantly more than (F(1, 37) = 30.822, p < 0.001, η

Язык: Английский

Процитировано

6
Integrating Biomarkers From Virtual Reality and Magnetic Resonance Imaging for the Early Detection of Mild Cognitive Impairment Using a Multimodal Learning Approach: Validation Study DOI Creative Commons
Bogyeom Park, Yuwon Kim, Jinseok Park

и другие.

Journal of Medical Internet Research, Год журнала: 2024, Номер 26, С. e54538 - e54538

Опубликована: Апрель 17, 2024

Early detection of mild cognitive impairment (MCI), a transitional stage between normal aging and Alzheimer disease, is crucial for preventing the progression dementia. Virtual reality (VR) biomarkers have proven to be effective in capturing behaviors associated with subtle deficits instrumental activities daily living, such as challenges using food-ordering kiosk, early MCI. On other hand, magnetic resonance imaging (MRI) demonstrated their efficacy quantifying observable structural brain changes that can aid MCI detection. Nevertheless, relationship VR-derived MRI remains an open question. In this context, we explored integration enhance through multimodal learning approach.

Язык: Английский

Процитировано

6
Eye tracking based detection of mild cognitive impairment: A review DOI Creative Commons
Hasnain Ali Shah,

Sultan Khalil,

Sami Andberg

и другие.

Information Fusion, Год журнала: 2025, Номер unknown, С. 103202 - 103202

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
CLONE: Synthetic Guideline-based Clinical Reasoning with Large Language Models for Early Diagnosis of Mild Cognitive Impairment DOI

Seungeon Cha,

Jinseok Park, Hojin Choi

и другие.

Опубликована: Апрель 23, 2025

Язык: Английский

Процитировано

0
Beyond Missing Data: A Multimodal Approach Using VR-EEG-MRI (VEEM) Biomarkers for Detecting MCI DOI
Yuwon Kim

Опубликована: Апрель 23, 2025

Язык: Английский

Процитировано

0
Exploring the Multimodal Integration of VR and MRI Biomarkers for Enhanced Early Detection of Mild Cognitive Impairment DOI Open Access
Bogyeom Park, Yuwon Kim, Jinseok Park

и другие.

Опубликована: Май 11, 2024

Early detection of mild cognitive impairment (MCI) is crucial to impede dementia progression. Virtual reality (VR) biomarkers are adept at detecting impairments in instrumental activities daily living (IADL), whereas magnetic resonance imaging (MRI) excel measuring observable structural changes the brain. However, efficacy integrating VR and MRI improve early MCI remains unclear. This study aims evaluate compare effectiveness investigates potential their combined use for more accurate detection. Through support vector machine analysis, distinct characteristics were observed. For identifying MCI, demonstrated high specificity (90.0%), showed sensitivity (90.9%). The combination both yielded superior results accuracy (94.4%), (100.0%), Drawing from these results, we suggest a sequential diagnostic approach, employing initial screening subsequent confirmation MCI.

Язык: Английский

Процитировано

2
Early Screening of Mild Cognitive Impairment using Multimodal VR-EP-EEG-MRI (VEEM) Biomarkers via Machine Learning DOI
Yuwon Kim, Bogyeom Park, DoHyun Kim

и другие.

2020 International Conference on Electronics, Information, and Communication (ICEIC), Год журнала: 2024, Номер unknown, С. 1 - 4

Опубликована: Янв. 28, 2024

This study introduces a novel multimodal biomarker approach for the early screening of mild cognitive impairment (MCI), integrating biomarkers from virtual reality (VR), evoked potential (EP), electroencephalogram (EEG), and magnetic resonance imaging (MRI). A total 46 participants, including 21 healthy controls 25 MCI patients, were recruited, nine distinct VR, EP, EEG, MRI collected each participant. These showed significant differences between patients. Leveraging machine learning model trained on these biomarkers, achieved outstanding classification performance with 94.12% accuracy, 100.0% sensitivity, 88.89% specificity, precision, F1-score. results surpassed models using unimodal or MRI. The findings highlight significance employing VR-EP-EEG-MRI in advocate further research this domain.

Язык: Английский

Процитировано

1
Decoding Behavior: Utilizing Virtual Reality Digital Marker and Machine Learning for Early Detection of Mild Cognitive Impairment DOI Open Access
Yuwon Kim, Jinseok Park, Hojin Choi

и другие.

Опубликована: Май 11, 2024

The imperative for early mild cognitive impairment (MCI) detection is underscored by the limitations of traditional biomarkers, high cost and invasiveness, they often fail to capture behavioral changes in MCI patients associated with impaired instrumental activities daily living (IADL). This study introduces a cost-effective, non-invasive alternative using digital markers, "virtual kiosk test", which involves performing IADL tasks such as ordering food via virtual reality (VR) detect at an stage. Involving 20 healthy controls 31 patients, four key features within VR markers effectively differentiate groups: hand movement speed, proportion fixation duration, time completion, number errors. A machine learning model demonstrated effectiveness 93.3% accuracy, 100% sensitivity, 83.3% specificity, 90% precision, 94.7% F1-score group differentiation. Findings suggest that observing behaviors test 5 minutes can be efficient approach detection, acting reliable markers.

Язык: Английский

Процитировано

1
Early Detection of Patients with Mild Cognitive Impairment through EEG-SSVEP-based Machine Learning Model DOI Creative Commons

Dohyun Kim,

Jinseok Park, Hojin Choi

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 172101 - 172114

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

1