1
|
Park B, Kim Y, Park J, Choi H, Kim SE, Ryu H, Seo K. Integrating Biomarkers From Virtual Reality and Magnetic Resonance Imaging for the Early Detection of Mild Cognitive Impairment Using a Multimodal Learning Approach: Validation Study. J Med Internet Res 2024; 26:e54538. [PMID: 38631021 PMCID: PMC11063880 DOI: 10.2196/54538] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Revised: 12/29/2023] [Accepted: 03/09/2024] [Indexed: 04/19/2024] Open
Abstract
BACKGROUND Early detection of mild cognitive impairment (MCI), a transitional stage between normal aging and Alzheimer disease, is crucial for preventing the progression of dementia. Virtual reality (VR) biomarkers have proven to be effective in capturing behaviors associated with subtle deficits in instrumental activities of daily living, such as challenges in using a food-ordering kiosk, for early detection of MCI. On the other hand, magnetic resonance imaging (MRI) biomarkers have demonstrated their efficacy in quantifying observable structural brain changes that can aid in early MCI detection. Nevertheless, the relationship between VR-derived and MRI biomarkers remains an open question. In this context, we explored the integration of VR-derived and MRI biomarkers to enhance early MCI detection through a multimodal learning approach. OBJECTIVE We aimed to evaluate and compare the efficacy of VR-derived and MRI biomarkers in the classification of MCI while also examining the strengths and weaknesses of each approach. Furthermore, we focused on improving early MCI detection by leveraging multimodal learning to integrate VR-derived and MRI biomarkers. METHODS The study encompassed a total of 54 participants, comprising 22 (41%) healthy controls and 32 (59%) patients with MCI. Participants completed a virtual kiosk test to collect 4 VR-derived biomarkers (hand movement speed, scanpath length, time to completion, and the number of errors), and T1-weighted MRI scans were performed to collect 22 MRI biomarkers from both hemispheres. Analyses of covariance were used to compare these biomarkers between healthy controls and patients with MCI, with age considered as a covariate. Subsequently, the biomarkers that exhibited significant differences between the 2 groups were used to train and validate a multimodal learning model aimed at early screening for patients with MCI among healthy controls. RESULTS The support vector machine (SVM) using only VR-derived biomarkers achieved a sensitivity of 87.5% and specificity of 90%, whereas the MRI biomarkers showed a sensitivity of 90.9% and specificity of 71.4%. Moreover, a correlation analysis revealed a significant association between MRI-observed brain atrophy and impaired performance in instrumental activities of daily living in the VR environment. Notably, the integration of both VR-derived and MRI biomarkers into a multimodal SVM model yielded superior results compared to unimodal SVM models, achieving higher accuracy (94.4%), sensitivity (100%), specificity (90.9%), precision (87.5%), and F1-score (93.3%). CONCLUSIONS The results indicate that VR-derived biomarkers, characterized by their high specificity, can be valuable as a robust, early screening tool for MCI in a broader older adult population. On the other hand, MRI biomarkers, known for their high sensitivity, excel at confirming the presence of MCI. Moreover, the multimodal learning approach introduced in our study provides valuable insights into the improvement of early MCI detection by integrating a diverse set of biomarkers.
Collapse
Affiliation(s)
- Bogyeom Park
- Department of Applied Artificial Intelligence, Seoul National University of Science and Technology, Seoul, Republic of Korea
| | - Yuwon Kim
- Department of Applied Artificial Intelligence, Seoul National University of Science and Technology, Seoul, Republic of Korea
| | - Jinseok Park
- Department of Neurology, College of Medicine, Hanyang University, Seoul, Republic of Korea
| | - Hojin Choi
- Department of Neurology, College of Medicine, Hanyang University, Seoul, Republic of Korea
| | - Seong-Eun Kim
- Department of Applied Artificial Intelligence, Seoul National University of Science and Technology, Seoul, Republic of Korea
| | - Hokyoung Ryu
- Graduate School of Technology and Innovation Management, Hanyang University, Seoul, Republic of Korea
| | - Kyoungwon Seo
- Department of Applied Artificial Intelligence, Seoul National University of Science and Technology, Seoul, Republic of Korea
| |
Collapse
|
2
|
Gajardo-Vidal A, Montembeault M, Lorca-Puls DL, Licata AE, Bogley R, Erlhoff S, Ratnasiri B, Ezzes Z, Battistella G, Tsoy E, Pereira CW, DeLeon J, Tee BL, Henry ML, Miller ZA, Rankin KP, Mandelli ML, Possin KL, Gorno-Tempini ML. Assessing processing speed and its neural correlates in the three variants of primary progressive aphasia with a non-verbal tablet-based task. Cortex 2024; 171:165-177. [PMID: 38000139 PMCID: PMC10922977 DOI: 10.1016/j.cortex.2023.10.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2023] [Revised: 09/29/2023] [Accepted: 10/18/2023] [Indexed: 11/26/2023]
Abstract
Prior research has revealed distinctive patterns of impaired language abilities across the three variants of Primary Progressive Aphasia (PPA): nonfluent/agrammatic (nfvPPA), logopenic (lvPPA) and semantic (svPPA). However, little is known about whether, and to what extent, non-verbal cognitive abilities, such as processing speed, are impacted in PPA patients. This is because neuropsychological tests typically contain linguistic stimuli and require spoken output, being therefore sensitive to verbal deficits in aphasic patients. The aim of this study is to investigate potential differences in processing speed between PPA patients and healthy controls, and among the three PPA variants, using a brief non-verbal tablet-based task (Match) modeled after the WAIS-III digit symbol coding test, and to determine its neural correlates. Here, we compared performance on the Match task between PPA patients (n = 61) and healthy controls (n = 59) and across the three PPA variants. We correlated performance on Match with voxelwise gray and white matter volumes. We found that lvPPA and nfvPPA patients performed significantly worse on Match than healthy controls and svPPA patients. Worse performance on Match across PPA patients was associated with reduced gray matter volume in specific parts of the left middle frontal gyrus, superior parietal lobule, and precuneus, and reduced white matter volume in the left parietal lobe. To conclude, our behavioral findings reveal that processing speed is differentially impacted across the three PPA variants and provide support for the potential clinical utility of a tabled-based task (Match) to assess non-verbal cognition. In addition, our neuroimaging findings confirm the importance of a set of fronto-parietal regions that previous research has associated with processing speed and executive control. Finally, our behavioral and neuroimaging findings combined indicate that differences in processing speed are largely explained by the unequal distribution of atrophy in these fronto-parietal regions across the three PPA variants.
Collapse
Affiliation(s)
- Andrea Gajardo-Vidal
- Centro de Investigación en Complejidad Social (CICS), Facultad de Gobierno, Universidad del Desarrollo, Santiago, Chile.
| | - Maxime Montembeault
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA; Douglas Mental Health University Institute, Montréal, QC H4H 1R3, Canada; Department of Psychiatry, McGill University, Montréal, QC H3A 1A1, Canada
| | - Diego L Lorca-Puls
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA; Sección de Neurología, Departamento de Especialidades, Facultad de Medicina, Universidad de Concepción, Concepción, Chile
| | - Abigail E Licata
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Rian Bogley
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Sabrina Erlhoff
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Buddhika Ratnasiri
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Zoe Ezzes
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Giovanni Battistella
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Elena Tsoy
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Christa Watson Pereira
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Jessica DeLeon
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Boon Lead Tee
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Maya L Henry
- Department of Speech, Language, and Hearing Sciences, University of Texas, Austin, TX, USA
| | - Zachary A Miller
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Katherine P Rankin
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Maria Luisa Mandelli
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | - Katherine L Possin
- Memory and Aging Center, Department of Neurology, University of California, San Francisco, CA, USA
| | | |
Collapse
|
3
|
Singh NA, Graff-Radford J, Machulda MM, Thu NT, Schwarz CG, Reid RI, Lowe VJ, Petersen RC, Jack CR, Josephs KA, Whitwell JL. Diffusivity Changes in Posterior Cortical Atrophy and Logopenic Progressive Aphasia: A Longitudinal Diffusion Tensor Imaging Study. J Alzheimers Dis 2023; 94:709-725. [PMID: 37302032 PMCID: PMC10785680 DOI: 10.3233/jad-221217] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
BACKGROUND Posterior cortical atrophy (PCA) and logopenic progressive aphasia (LPA) are associated with characteristic patterns of structural network degeneration. Little is known about longitudinal patterns of white matter tract degeneration in these phenotypes. OBJECTIVE To assess longitudinal patterns of white matter degeneration and identify phenotype specific cross-sectional and longitudinal diffusion tensor imaging (DTI) biomarkers in PCA and LPA. METHODS Twenty-five PCA, 22 LPA and 25 cognitively unimpaired (CU) individuals were recruited and underwent structural MRI that included a DTI sequence with a follow-up one year later. Cross-sectional and longitudinal mixed effects models were fit to assess the effects of diagnosis on baseline and annualized change in regional DTI metrics. Discriminatory power was investigated using the area under the receiver operating characteristic curves (AUROC). RESULTS PCA and LPA showed overlapping white matter degeneration profiles predominantly in the left occipital and temporal lobes, the posterior thalamic radiation and sagittal stratum at baseline, as well as the parietal lobe longitudinally. PCA showed degeneration in the occipital and parietal white matter, cross-sectionally and longitudinally, compared to CU, while LPA showed greater degeneration in the temporal and inferior parietal white matter and the inferior fronto-occipital fasciculus cross-sectionally, and in parietal white matter longitudinally compared to CU. Cross-sectionally, integrity of the inferior occipital white matter was best able to differentiate PCA from LPA, with an AUROC of 0.82. CONCLUSION These findings contribute to our understanding of white matter degeneration and support usage of DTI as a useful additional diagnostic biomarker for PCA and LPA.
Collapse
Affiliation(s)
| | | | - Mary M. Machulda
- Department of Psychiatry & Psychology, Mayo Clinic, Rochester, MN, USA
| | - Nha Trang Thu
- Department of Radiology, Mayo Clinic, Rochester, MN, USA
| | | | - Robert I. Reid
- Department of Radiology, Mayo Clinic, Rochester, MN, USA
- Department of Information Technology, Mayo Clinic, Rochester, MN, USA
| | - Val J. Lowe
- Department of Radiology, Mayo Clinic, Rochester, MN, USA
| | | | | | | | | |
Collapse
|