%0 Journal Article %J J Alzheimers Dis %D 2022 %T Automated Early Detection of Alzheimer's Disease by Capturing Impairments in Multiple Cognitive Domains with Multiple Drawing Tasks. %A Kobayashi, Masatomo %A Yamada, Yasunori %A Shinkawa, Kaoru %A Nemoto, Miyuki %A Nemoto, Kiyotaka %A Arai, Tetsuaki %X

BACKGROUND: Automatic analysis of the drawing process using a digital tablet and pen has been applied to successfully detect Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, most studies focused on analyzing individual drawing tasks separately, and the question of how a combination of drawing tasks could improve the detection performance thus remains unexplored.

OBJECTIVE: We aimed to investigate whether analysis of the drawing process in multiple drawing tasks could capture different, complementary aspects of cognitive impairments, with a view toward combining multiple tasks to effectively improve the detection capability.

METHODS: We collected drawing data from 144 community-dwelling older adults (27 AD, 65 MCI, and 52 cognitively normal, or CN) who performed five drawing tasks. We then extracted motion- and pause-related drawing features for each task and investigated the statistical associations of the features with the participants' diagnostic statuses and cognitive measures.

RESULTS: The drawing features showed gradual changes from CN to MCI and then to AD, and the changes in the features for each task were statistically associated with cognitive impairments in different domains. For classification into the three diagnostic categories, a machine learning model using the features from all five tasks achieved a classification accuracy of 75.2%, an improvement by 7.8% over that of the best single-task model.

CONCLUSION: Our results demonstrate that a common set of drawing features from multiple drawing tasks can capture different, complementary aspects of cognitive impairments, which may lead to a scalable way to improve the automated detection of AD and MCI.

%B J Alzheimers Dis %V 88 %P 1075-1089 %8 2022 Aug 02 %G eng %N 3 %R 10.3233/JAD-215714 %0 Journal Article %J J Alzheimers Dis %D 2021 %T Combining Multimodal Behavioral Data of Gait, Speech, and Drawing for Classification of Alzheimer's Disease and Mild Cognitive Impairment. %A Yamada, Yasunori %A Shinkawa, Kaoru %A Kobayashi, Masatomo %A Caggiano, Vittorio %A Nemoto, Miyuki %A Nemoto, Kiyotaka %A Arai, Tetsuaki %K Aged %K Alzheimer Disease %K Cognitive Dysfunction %K Female %K Gait %K Humans %K Male %K Neuropsychological Tests %K Speech %X

BACKGROUND: Gait, speech, and drawing behaviors have been shown to be sensitive to the diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, previous studies focused on only analyzing individual behavioral modalities, although these studies suggested that each of these modalities may capture different profiles of cognitive impairments associated with AD.

OBJECTIVE: We aimed to investigate if combining behavioral data of gait, speech, and drawing can improve classification performance compared with the use of individual modality and if each of these behavioral data can be associated with different cognitive and clinical measures for the diagnosis of AD and MCI.

METHODS: Behavioral data of gait, speech, and drawing were acquired from 118 AD, MCI, and cognitively normal (CN) participants.

RESULTS: Combining all three behavioral modalities achieved 93.0% accuracy for classifying AD, MCI, and CN, and only 81.9% when using the best individual behavioral modality. Each of these behavioral modalities was statistically significantly associated with different cognitive and clinical measures for diagnosing AD and MCI.

CONCLUSION: Our findings indicate that these behaviors provide different and complementary information about cognitive impairments such that classification of AD and MCI is superior to using either in isolation.

%B J Alzheimers Dis %V 84 %P 315-327 %8 2021 %G eng %N 1 %1 https://www.ncbi.nlm.nih.gov/pubmed/34542076?dopt=Abstract %R 10.3233/JAD-210684 %0 Journal Article %J J Alzheimers Dis %D 2016 %T Ventilatory Response to Hypercapnia Predicts Dementia with Lewy Bodies in Late-Onset Major Depressive Disorder. %A Takahashi, Sho %A Mizukami, Katsuyoshi %A Arai, Tetsuaki %A Ogawa, Ryoko %A Kikuchi, Norihiro %A Hattori, Satoshi %A Darby, David %A Asada, Takashi %K 3-Iodobenzylguanidine %K Aged %K Aged, 80 and over %K Depressive Disorder, Major %K Follow-Up Studies %K Heart Rate %K Humans %K Hypercapnia %K Hypotension, Orthostatic %K Kaplan-Meier Estimate %K Lewy Body Disease %K Middle Aged %K Partial Pressure %K Psychiatric Status Rating Scales %K Retrospective Studies %K Ventilators, Mechanical %X

BACKGROUND: Studies have shown that developing major depressive disorder (MDD) at 50 years of age or older can predict dementia. Depression is particularly common in dementia with Lewy bodies (DLB), and occasionally occurs before the onset of extrapyramidal symptoms. Moreover, systemic autonomic dysfunction, including an abnormal ventilatory response to hypercapnia (VRH), is common in patients with DLB.

OBJECTIVE: Here, we aimed to determine whether the VRH is useful for distinguishing depression that is predictive of DLB from other types of MDD.

METHODS: Participants were 35 consecutive patients with first onset MDD at 50 years or older with bradykinesia. After diagnosing the clinical subtype of MDD according to DSM-IV criteria, each subject underwent a battery of psychological tests, autonomic examinations including VRH, brain magnetic resonance imaging, and 123I-meta-iodobenzylguanidine scintigraphy.

RESULTS: Longitudinal follow-up showed that all 18 patients with abnormal VRH results developed DLB, whereas none of the 17 patients with normal VRH results converted to DLB within the study period (sensitivity: 100% , specificity: 100%). Additionally, over half of the DLB converters showed abnormalities on other autonomic examinations. For converters, the most common MDD subtype had psychotic and melancholic features simultaneously. The frequency of hypersensitivity to psychotropics was higher in converters than it was in non-converters.

CONCLUSION: In the present study, patients with abnormal VRH results were very likely to develop DLB. Thus, for patients with late-onset MDD accompanied by bradykinesia, the VRH in combination with the clinical subtype of MDD or hypersensitivity to psychotropics may be useful for diagnosing prodromal DLB.

%B J Alzheimers Dis %V 50 %P 751-8 %8 2016 %G eng %N 3 %1 http://www.ncbi.nlm.nih.gov/pubmed/26757183?dopt=Abstract %R 10.3233/JAD-150507