{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T20:38:31Z","timestamp":1793392711489,"version":"4.5.0"},"reference-count":42,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T00:00:00Z","timestamp":1708300800000},"content-version":"vor","delay-in-days":18,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Int J Geriat Psychiatry"],"published-print":{"date-parts":[[2024,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Geriatric depression and anxiety have been identified as mood disorders commonly associated with the onset of dementia. Currently, the diagnosis of geriatric depression and anxiety relies on self\u2010reported assessments for primary screening purposes, which is uncomfortable for older adults and can be prone to misreporting. When a more precise diagnosis is needed, additional methods such as in\u2010depth interviews or functional magnetic resonance imaging are used. However, these methods can not only be time\u2010consuming and costly but also require systematic and cost\u2010effective approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The main objective of this study was to investigate the feasibility of training an end\u2010to\u2010end deep learning (DL) model by directly inputting time\u2010series activity tracking and sleep data obtained from consumer\u2010grade wrist\u2010worn activity trackers to identify comorbid depression and anxiety.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To enhance accuracy, the input of the DL model consisted of step counts and sleep stages as time series data, along with minimal depression and anxiety assessment scores as non\u2010time\u2010series data. The basic structure of the DL model was designed to process mixed\u2010input data and perform multi\u2010label\u2010based classification for depression and anxiety. Various DL models, including the convolutional neural network (CNN) and long short\u2010term memory (LSTM), were applied to process the time\u2010series data, and model selection was conducted by comparing the performances of the hyperparameters.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>This study achieved significant results in the multi\u2010label classification of depression and anxiety, with a Hamming loss score of 0.0946 in the Residual Network (ResNet), by applying a mixed\u2010input DL model based on activity tracking data. The comparison of hyper\u2010parameter performance and the development of various DL models, such as CNN, LSTM, and ResNet contributed to the optimization of time series data processing and achievement of meaningful results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study can be considered as the first to develop a mixed\u2010input DL model based on activity tracking data for the multi\u2010label identification of late\u2010life depression and anxiety. The findings of the study demonstrate the feasibility and potential of using consumer\u2010grade wrist\u2010worn activity trackers in conjunction with DL models to improve the identification of comorbid mental health conditions in older adults. The study also established a multi\u2010label classification framework for identifying the complex symptoms of depression and anxiety.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/gps.6071","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T11:04:16Z","timestamp":1708340656000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Geriatric depression and anxiety screening via deep learning using activity tracking and sleep data"],"prefix":"10.1002","volume":"39","author":[{"given":"Tae\u2010Rim","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence Sungkyunkwan University  Suwon Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geon Ha","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Neurology EWHA Womans University Mokdong Hospital EWHA Womans University College of Medicine  Seoul Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2676-5728","authenticated-orcid":false,"given":"Mun\u2010Taek","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Intelligent Robotics Sungkyunkwan University  Suwon Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,2,19]]},"reference":[{"key":"e_1_2_10_2_1","unstructured":"World Health Organization.Towards a Dementia\u2010Inclusive Society: WHO Toolkit for Dementia\u2010Friendly Initiatives (DFIs);2021."},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1056\/nejmcp1502514"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2016.06.2361"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpr.2008.02.008"},{"key":"e_1_2_10_6_1","article-title":"Geriatric Depression Scale (GDS): recent evidence and development of a shorter version","author":"Sheikh JI","year":"1986","journal-title":"Clin Gerontol J Ag Ment Health"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532\u20105415.1999.tb03848.x"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1017\/s1041610210001237"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SEGAH54908.2022.9978305"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2019.2922178"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2010.12.001"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/app12052488"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2021.12.005"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103610"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0231995"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0280330"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.archger.2007.08.012"},{"key":"e_1_2_10_18_1","article-title":"The Global Deterioration Scale for assessment of primary degenerative dementia","author":"Reisberg B","year":"1982","journal-title":"Am J Psychiatr"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.5953\/jmjh.2014.21.1.75"},{"key":"e_1_2_10_20_1","volume-title":"Web API Reference","author":"Fitbit, Inc."},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/da.22355"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618\u2010018\u20100596\u20104"},{"key":"e_1_2_10_23_1","first-page":"298","volume-title":"Springer","author":"Zheng Y","year":"2014"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42452\u2010020\u20102506\u20109"},{"key":"e_1_2_10_25_1","unstructured":"YuanZ JiangY LiJ HuangH.Hybrid\u2010DNNs: hybrid deep neural networks for mixed inputs. arXiv preprint arXiv:2005.08419.2020."},{"key":"e_1_2_10_26_1","volume-title":"Perceptrons, Reissue of the 1988 Expanded Edition with a New Foreword by L\u00e9on Bottou: An Introduction to Computational Geometry","author":"Minsky M","year":"2017"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.30534\/ijatcse\/2020\/175942020"},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","unstructured":"KimY.Convolutional Neural Networks for Sentence Classification;2014. arXiv preprint arXiv:1408.5882.","DOI":"10.3115\/v1\/D14-1181"},{"issue":"2","key":"e_1_2_10_32_1","article-title":"Random search for hyper\u2010parameter optimization","volume":"13","author":"Bergstra J","year":"2012","journal-title":"J Mach Learn Res"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2020.04.010"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/1131\/1\/012007"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIS.2019.00025"},{"key":"e_1_2_10_36_1","first-page":"2825","article-title":"Scikit\u2010learn: machine learning in Python","volume":"12","author":"Pedregosa F","year":"2011","journal-title":"J Mach Learn Res"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371\u2010019\u201001630\u20109"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101"},{"key":"e_1_2_10_39_1","unstructured":"ZhangH CisseM DauphinYN Lopez\u2010PazD.Mixup: Beyond Empirical Risk Minimization;2017. arXiv preprint arXiv:1710.09412."},{"key":"e_1_2_10_40_1","unstructured":"MiyatoT DaiAM GoodfellowI.Adversarial Training Methods for Semi\u2010Supervised Text Classification;2016. arXiv preprint arXiv:1605.07725."},{"issue":"1","key":"e_1_2_10_41_1","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N","year":"2014","journal-title":"J Mach Learn Res"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2013.09.029"},{"key":"e_1_2_10_43_1","unstructured":"ReadJ Perez\u2010CruzF.Deep Learning for Multi\u2010Label Classification;2014. arXiv preprint arXiv:1502.05988."}],"container-title":["International Journal of Geriatric Psychiatry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/gps.6071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,24]],"date-time":"2024-02-24T08:22:18Z","timestamp":1708762938000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/gps.6071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["10.1002\/gps.6071"],"URL":"https:\/\/doi.org\/10.1002\/gps.6071","archive":["Portico"],"relation":{},"ISSN":["0885-6230","1099-1166"],"issn-type":[{"value":"0885-6230","type":"print"},{"value":"1099-1166","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]},"assertion":[{"value":"2023-09-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-06","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e6071"}}