Machine Learning Prediction for Postdischarge Falls in Older Adults: A Multicenter Prospective Study

Takeshita, Yuko; Onishi, Mai; Masuda, Hirotada; Katsuhisa, Mizuki; Ikuta, Kasumi; Saizen, Yuichiro; Fujii, Misaki; Kasamatsu, Misaki; Inaizumi, Nobuyuki; Maeizumi, Yuzuki; Kishino, Yoshinobu; Nakajima, Tsuneo; Koujiya, Eriko; Yamakawa, Miyae; Takami, Yoichi; Yamamoto, Koichi; Umeda-Kameyama, Yumi; Satake, Shosuke; Umegaki, Hiroyuki; Takeya, Yasushi

doi:https://doi.org/10.1016/j.jamda.2024.105414

Machine Learning Prediction for Postdischarge Falls in Older Adults: A Multicenter Prospective Study

Takeshita, Yuko; Onishi, Mai; Masuda, Hirotada et al.

Journal of the American Medical Directors Association, 2025, 26(2), 105414

アクセス数:2,252件（2025-09-03 07:59 集計）

固定URL: https://hdl.handle.net/11094/100392

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
JAmMedDirAssoc_26_2_105414	pdf	なし	795 KB	37	2025.02.20

Creative Commons : 表示

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Machine Learning Prediction for Postdischarge Falls in Older Adults: A Multicenter Prospective Study
著者	ORCID 0009-0005-8354-3629 0009-0005-8354-3629 著者名 Takeshita, Yuko
	著者名 Onishi, Mai
	NRID 1000080793918 1000080793918 researchmap permalink hirotada_masuda hirotada_masuda Scopus Author ID 56148108800 56148108800 著者名 Masuda, Hirotada
	著者名 Katsuhisa, Mizuki
	著者名 Ikuta, Kasumi
	researchmap permalink embraced00r embraced00r 著者名 Saizen, Yuichiro
	著者名 Fujii, Misaki
	著者名 Kasamatsu, Misaki
	著者名 Inaizumi, Nobuyuki
	著者名 Maeizumi, Yuzuki
	著者名 Kishino, Yoshinobu
	NRID 1000010858525 1000010858525 researchmap permalink ntsuneo ntsuneo 著者名 Nakajima, Tsuneo
	NRID 1000060896455 1000060896455 ORCID 0000-0002-9256-0237 0000-0002-9256-0237 researchmap permalink koujiya koujiya Scopus Author ID 57211692446 57211692446 著者名 Koujiya, Eriko
	NRID 1000080403012 1000080403012 ORCID 0000-0002-2399-8366 0000-0002-2399-8366 researchmap permalink miyatabu miyatabu Scopus Author ID 16246912100 16246912100 著者名 Yamakawa, Miyae
	NRID 1000090621756 1000090621756 ORCID 0000-0001-9018-6707 0000-0001-9018-6707 researchmap permalink YT-1973 YT-1973 Scopus Author ID 8635744100 8635744100 著者名 Takami, Yoichi
	NRID 1000000528424 1000000528424 ORCID 0000-0003-0107-9315 0000-0003-0107-9315 researchmap permalink kymt0410 kymt0410 Scopus Author ID 55624482466 55624482466 著者名 Yamamoto, Koichi
	著者名 Umeda-Kameyama, Yumi
	NRID 1000050508116 1000050508116 著者名 Satake, Shosuke
	NRID 1000040345898 1000040345898 著者名 Umegaki, Hiroyuki
	NRID 1000070590339 1000070590339 researchmap permalink 551 551 Scopus Author ID 14041019200 14041019200 著者名 Takeya, Yasushi
キーワード等	Falls
	hospitalization-associated disability
	machine learning
	older patients
	predictive model
内容	Takeshita Y., Onishi M., Masuda H., et al. Machine Learning Prediction for Postdischarge Falls in Older Adults: A Multicenter Prospective Study. Journal of the American Medical Directors Association 26, 105414 (2025); https://doi.org/10.1016/j.jamda.2024.105414.
抄録	Objectives: The study aimed to develop a machine learning (ML) model to predict early postdischarge falls in older adults using data that are easy to collect in acute care hospitals. This may reduce the burden imposed by complex measures on patients and health care staff. Design: This prospective multicenter study included patients admitted to and discharged from geriatric wards at 3 university hospitals and 1 national medical center in Japan between October 2019 and July 2023. Setting and Participants: The participants were individuals aged ≥65 years. Of the 1307 individuals enrolled during the study period, 684 were excluded, leaving 706 for inclusion in the analysis. Methods: We extracted 19 variables from admission and discharge data, including physical, mental, psychological, and social aspects and in-hospital events, to assess the main outcome measure: falls occurring within 3 months postdischarge. We developed a prediction model using 4 major classifiers, Extra Trees, Bernoulli Naive Bayes, AdaBoost, and Random Forest, which were evaluated using a 5-fold cross-validation. The area under the receiver operating characteristic curve (AUC) was used to evaluate predictive performance. Results: Among the 706 patients, 114 (16.1%) reported a fall within 3 months postdischarge. The Extra Trees classifier demonstrated the best predictive performance, with an AUC of 0.73 on the test data. Important features included the Lawton Instrumental Activities of Daily Living scale, Clinical Frailty Scale (≥4 points), presence of urinary incontinence, 15-item Geriatric Depression Scale (≥5 points), and preadmission residence, all assessed at admission. Conclusions and Implications: To our knowledge, this is the first study to develop an ML model for predicting early postdischarge falls among older patients in acute care hospitals. The findings suggest that this model could assist in developing fall-prevention strategies to ensure seamless transition of care from hospitals to communities.
出版者	Elsevier Inc.
収録物名	Journal of the American Medical Directors Association
巻(号)	26(2)
ページ	105414
刊行年月	2025-02-01
言語	英語
ハンドルURL	https://hdl.handle.net/11094/100392
PISSN	15258610
eISSN	15389375
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1016/j.jamda.2024.105414
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution 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
DCTERMS.bibliographicCitation	Journal of the American Medical Directors Association. 2025, 26(2), p. 105414
DC.title	Machine Learning Prediction for Postdischarge Falls in Older Adults: A Multicenter Prospective Study
DC.creator	Takeshita, Yuko
	Onishi, Mai
	Masuda, Hirotada
	Katsuhisa, Mizuki
	Ikuta, Kasumi
	Saizen, Yuichiro
	Fujii, Misaki
	Kasamatsu, Misaki
	Inaizumi, Nobuyuki
	Maeizumi, Yuzuki
	Kishino, Yoshinobu
	Nakajima, Tsuneo
	Koujiya, Eriko
	Yamakawa, Miyae
	Takami, Yoichi
	Yamamoto, Koichi
	Umeda-Kameyama, Yumi
	Satake, Shosuke
	Umegaki, Hiroyuki
	Takeya, Yasushi
DC.publisher	Elsevier Inc.
DC.language' scheme='DCTERMS.RFC1766	英語
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-02-01
DC.identifier	https://doi.org/10.1016/j.jamda.2024.105414
DC.subject	Falls
	hospitalization-associated disability
	machine learning
	older patients
	predictive model
DC.description	Takeshita Y., Onishi M., Masuda H., et al. Machine Learning Prediction for Postdischarge Falls in Older Adults: A Multicenter Prospective Study. Journal of the American Medical Directors Association 26, 105414 (2025); https://doi.org/10.1016/j.jamda.2024.105414.
DCTERMS.abstract	Objectives: The study aimed to develop a machine learning (ML) model to predict early postdischarge falls in older adults using data that are easy to collect in acute care hospitals. This may reduce the burden imposed by complex measures on patients and health care staff. Design: This prospective multicenter study included patients admitted to and discharged from geriatric wards at 3 university hospitals and 1 national medical center in Japan between October 2019 and July 2023. Setting and Participants: The participants were individuals aged ≥65 years. Of the 1307 individuals enrolled during the study period, 684 were excluded, leaving 706 for inclusion in the analysis. Methods: We extracted 19 variables from admission and discharge data, including physical, mental, psychological, and social aspects and in-hospital events, to assess the main outcome measure: falls occurring within 3 months postdischarge. We developed a prediction model using 4 major classifiers, Extra Trees, Bernoulli Naive Bayes, AdaBoost, and Random Forest, which were evaluated using a 5-fold cross-validation. The area under the receiver operating characteristic curve (AUC) was used to evaluate predictive performance. Results: Among the 706 patients, 114 (16.1%) reported a fall within 3 months postdischarge. The Extra Trees classifier demonstrated the best predictive performance, with an AUC of 0.73 on the test data. Important features included the Lawton Instrumental Activities of Daily Living scale, Clinical Frailty Scale (≥4 points), presence of urinary incontinence, 15-item Geriatric Depression Scale (≥5 points), and preadmission residence, all assessed at admission. Conclusions and Implications: To our knowledge, this is the first study to develop an ML model for predicting early postdischarge falls among older patients in acute care hospitals. The findings suggest that this model could assist in developing fall-prevention strategies to ensure seamless transition of care from hospitals to communities.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	100392
citation_title	Machine Learning Prediction for Postdischarge Falls in Older Adults: A Multicenter Prospective Study
citation_author	Takeshita, Yuko
	Onishi, Mai
	Masuda, Hirotada
	Katsuhisa, Mizuki
	Ikuta, Kasumi
	Saizen, Yuichiro
	Fujii, Misaki
	Kasamatsu, Misaki
	Inaizumi, Nobuyuki
	Maeizumi, Yuzuki
	Kishino, Yoshinobu
	Nakajima, Tsuneo
	Koujiya, Eriko
	Yamakawa, Miyae
	Takami, Yoichi
	Yamamoto, Koichi
	Umeda-Kameyama, Yumi
	Satake, Shosuke
	Umegaki, Hiroyuki
	Takeya, Yasushi
citation_publisher	Elsevier Inc.
citation_language	英語
citation_date	2025-02-01
citation_journal_title	Journal of the American Medical Directors Association
citation_volume	26
citation_issue	2
citation_firstpage	105414
citation_doi	https://doi.org/10.1016/j.jamda.2024.105414
citation_public_url	https://hdl.handle.net/11094/100392

Machine Learning Prediction for Postdischarge Falls in Older Adults: A Multicenter Prospective Study

閲覧可能ファイル

論文情報

論文詳細を表示