Machine learning model for predicting the conversion to dementia using the Cube Copying Test

Shinozaki, Mio; Hishida, Hiroyuki; Gondo, Yasuyuki; Yamamoto, Michio; Suzuki, Takashi; Miura, Rina; Sakurai, Takashi; Takeda, Akinori; Arahata, Yutaka

doi:https://doi.org/10.1177/13872877251376939

Machine learning model for predicting the conversion to dementia using the Cube Copying Test

Shinozaki, Mio; Hishida, Hiroyuki; Gondo, Yasuyuki et al.

Journal of Alzheimer’s Disease, 2025, 108(1_suppl.), 141-158

アクセス数:326件（2026-02-15 21:48 集計）

固定URL: https://hdl.handle.net/11094/102844

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
JournalofAlzheimer’sDisease_404_1S_141	pdf	なし	2.78 MB	32	2025.11.06

Creative Commons : 表示 - 非営利

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Machine learning model for predicting the conversion to dementia using the Cube Copying Test
著者	NRID 1000030813828 1000030813828 ORCID 0000-0002-3103-7004 0000-0002-3103-7004 著者名 Shinozaki, Mio
	ORCID 0009-0000-4025-0088 0009-0000-4025-0088 著者名 Hishida, Hiroyuki
	NRID 1000040250196 1000040250196 ORCID 0000-0002-9805-2807 0000-0002-9805-2807 著者名 Gondo, Yasuyuki
	NRID 1000050721396 1000050721396 researchmap permalink 7000009476 7000009476 ORCID 0000-0003-1272-7090 0000-0003-1272-7090 Scopus Author ID 7405310823 7405310823 著者名 Yamamoto, Michio
	NRID 1000040114516 1000040114516 ORCID 0000-0002-0203-5587 0000-0002-0203-5587 researchmap permalink read0043227 read0043227 Scopus Author ID 55628569951 55628569951 著者名 Suzuki, Takashi
	著者名 Miura, Rina
	NRID 1000050335444 1000050335444 ORCID 0000-0002-2369-3095 0000-0002-2369-3095 著者名 Sakurai, Takashi
	NRID 1000090507013 1000090507013 ORCID 0000-0002-2761-3240 0000-0002-2761-3240 著者名 Takeda, Akinori
	NRID 1000080501212 1000080501212 ORCID 0000-0001-7810-8984 0000-0001-7810-8984 著者名 Arahata, Yutaka
内容	Shinozaki M, Hishida H, Gondo Y, et al. Machine learning model for predicting the conversion to dementia using the Cube Copying Test. Journal of Alzheimer’s Disease. 2025;108(1_suppl):S141-S158. doi:10.1177/13872877251376939
抄録	Background: Early detection of dementia requires highly accurate and efficient screening tests that minimize patient burden. Objective: To develop a machine learning model predicting dementia conversion within 3–5 years using Cube Copying Test (CCT) drawings at baseline. Methods: This retrospective study analyzed CCT drawing data from 767 patients at the Center for Comprehensive Care and Research on Memory Disorders (2011–2020). Of the 2303 patients who met the inclusion criteria, 534 were excluded due to mild cognitive impairment (MCI) persistence, pending diagnoses, or new neurovascular diseases, while 1002 were lost to follow-up. Eligibility criteria included a baseline Mini-Mental State Examination (MMSE) score ≥24, absence of dementia diagnosis or anti-dementia medication intake, and completion of a 3–5-year follow-up without meeting exclusion criteria. Results: Of 767 patients, 457 converted to dementia (318 with Alzheimer’s disease, 116 with dementia with Lewy bodies, and 23 with frontotemporal dementia) within 3–5 years, while 310 did not. The model achieved an area under the curve of 0.85 for predicting dementia conversion. Shapley Additive exPlanations analysis identified PatchCore-derived features as the strongest predictors, distinguishing drawing patterns of converters and non-converters. Conclusions: In patients who convert to Alzheimer’s disease, dementia with Lewy bodies, or frontotemporal dementia, the very early stages of constructional apraxia-like symptoms already exist at the preclinical stage or MCI stage. Applying deep learning-based anomaly-detection models can detect these early drawing distortions that differ from normal aging and contribute to improving the performance of dementia-conversion prediction.
出版者	SAGE Publications
収録物名	Journal of Alzheimer’s Disease
巻(号)	108(1_suppl.)
ページ	141-158
刊行年月	2025-09-22
言語	英語
ハンドルURL	https://hdl.handle.net/11094/102844
PISSN	13872877
eISSN	18758908
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1177/13872877251376939
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Journal of Alzheimer’s Disease. 2025, 108(1_suppl.), p. 141-158
DC.title	Machine learning model for predicting the conversion to dementia using the Cube Copying Test
DC.creator	Shinozaki, Mio
	Hishida, Hiroyuki
	Gondo, Yasuyuki
	Yamamoto, Michio
	Suzuki, Takashi
	Miura, Rina
	Sakurai, Takashi
	Takeda, Akinori
	Arahata, Yutaka
DC.publisher	SAGE Publications
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-09-22
DC.identifier	https://doi.org/10.1177/13872877251376939
DC.description	Shinozaki M, Hishida H, Gondo Y, et al. Machine learning model for predicting the conversion to dementia using the Cube Copying Test. Journal of Alzheimer’s Disease. 2025;108(1_suppl):S141-S158. doi:10.1177/13872877251376939
DCTERMS.abstract	Background: Early detection of dementia requires highly accurate and efficient screening tests that minimize patient burden. Objective: To develop a machine learning model predicting dementia conversion within 3–5 years using Cube Copying Test (CCT) drawings at baseline. Methods: This retrospective study analyzed CCT drawing data from 767 patients at the Center for Comprehensive Care and Research on Memory Disorders (2011–2020). Of the 2303 patients who met the inclusion criteria, 534 were excluded due to mild cognitive impairment (MCI) persistence, pending diagnoses, or new neurovascular diseases, while 1002 were lost to follow-up. Eligibility criteria included a baseline Mini-Mental State Examination (MMSE) score ≥24, absence of dementia diagnosis or anti-dementia medication intake, and completion of a 3–5-year follow-up without meeting exclusion criteria. Results: Of 767 patients, 457 converted to dementia (318 with Alzheimer’s disease, 116 with dementia with Lewy bodies, and 23 with frontotemporal dementia) within 3–5 years, while 310 did not. The model achieved an area under the curve of 0.85 for predicting dementia conversion. Shapley Additive exPlanations analysis identified PatchCore-derived features as the strongest predictors, distinguishing drawing patterns of converters and non-converters. Conclusions: In patients who convert to Alzheimer’s disease, dementia with Lewy bodies, or frontotemporal dementia, the very early stages of constructional apraxia-like symptoms already exist at the preclinical stage or MCI stage. Applying deep learning-based anomaly-detection models can detect these early drawing distortions that differ from normal aging and contribute to improving the performance of dementia-conversion prediction.
DC.rights	This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
DC.format	102844
citation_title	Machine learning model for predicting the conversion to dementia using the Cube Copying Test
citation_author	Shinozaki, Mio
	Hishida, Hiroyuki
	Gondo, Yasuyuki
	Yamamoto, Michio
	Suzuki, Takashi
	Miura, Rina
	Sakurai, Takashi
	Takeda, Akinori
	Arahata, Yutaka
citation_publisher	SAGE Publications
citation_language	英語
citation_date	2025-09-22
citation_journal_title	Journal of Alzheimer’s Disease
citation_volume	108
citation_issue	1_suppl.
citation_firstpage	141
citation_lastpage	158
citation_doi	https://doi.org/10.1177/13872877251376939
citation_public_url	https://hdl.handle.net/11094/102844

Machine learning model for predicting the conversion to dementia using the Cube Copying Test

閲覧可能ファイル

論文情報

論文詳細を表示