{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T21:41:00Z","timestamp":1791841260311,"version":"4.3.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"NSF","award":["SES-2316428"],"award-info":[{"award-number":["SES-2316428"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lifetime Data Anal"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Early identification of Parkinson\u2019s disease is critical for timely intervention. Disruptions in sleep architecture and changes in physical activity patterns have been reported years before motor symptom onset, yet prodromal behavioral changes spanning sleep and daytime activity patterns are subtle and difficult to detect with conventional clinical tools. Wearable sensors provide a scalable means of monitoring these behaviors in natural settings, but extracting meaningful, interpretable features from high-frequency, unlabeled time series remains a major challenge. We present an end-to-end framework for assessing Parkinson\u2019s disease risk from wrist-worn accelerometry via automated feature extraction and survival modeling of time to diagnosis. Behavioral states are derived from unlabeled data using pretrained models including random forests with hidden Markov models for physical activity classification and a self-supervised learning based sleep staging model. We jointly model both sleep stage and physical activity sequences using hierarchical nonstationary Markov chains stratified by time of day and temporal resolution, characterizing individual-level behavioral rhythms and transition dynamics. Gradient-boosted Cox proportional hazards models are then used to estimate Parkinson\u2019s disease risk from these transition-based features. Applied to accelerometer data from the UK Biobank, our approach outperforms baselines that exclude dynamic modeling or rely on traditional functional data analysis, while providing interpretable predictors from long sequences of wearable sensor data. This demonstrates the potential of integrating pretrained AI models, temporal sequence modeling, and survival analysis to detect early behavioral signatures of neurodegeneration.<\/jats:p>","DOI":"10.1007\/s10985-026-09721-1","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T13:47:52Z","timestamp":1785764872000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Transition dynamics modeling of pre-trained accelerometry representations for time to diagnosis of Parkinson\u2019s disease"],"prefix":"10.1007","volume":"32","author":[{"given":"Huiming","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6576-8019","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"9721_CR1","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.hlpt.2012.07.003","volume":"1","author":"N Allen","year":"2012","unstructured":"Allen N, Sudlow C, Downey P, Peakman T, Danesh J, Elliott P, Gallacher J, Green J, Matthews P, Pell J, Sprosen T, Collins R (2012) UK biobank: current status and what it means for epidemiology. Health Policy Technol 1:123\u2013126. https:\/\/doi.org\/10.1016\/j.hlpt.2012.07.003","journal-title":"Health Policy Technol"},{"issue":"12","key":"9721_CR2","doi-asserted-by":"publisher","first-page":"1600","DOI":"10.1002\/mds.26431","volume":"30","author":"D Berg","year":"2015","unstructured":"Berg D, Postuma RB, Adler CH, Bloem BR, Chan P, Dubois B, Gasser T, Goetz CG, Halliday G, Joseph L, Lang AE, Liepelt-Scarfone I, Litvan I, Marek K, Obeso J, Oertel W, Olanow CW, Poewe W, Stern M, Deuschl G (2015) MDS research criteria for prodromal Parkinson\u2019s disease. Mov Disord 30(12):1600\u20131611","journal-title":"Mov Disord"},{"issue":"2012","key":"9721_CR3","first-page":"7","volume":"176","author":"RB Berry","year":"2012","unstructured":"Berry RB, Brooks R, Gamaldo CE, Harding SM, Marcus CL, Vaughn BV (2012) The aasm manual for the scoring of sleep and associated events. Rules Terminol Tech Specif Darien Ill Am Acad Sleep Med 176(2012):7","journal-title":"Rules Terminol Tech Specif Darien Ill Am Acad Sleep Med"},{"issue":"4","key":"9721_CR4","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1053\/smrv.2001.0245","volume":"7","author":"MH Bonnet","year":"2003","unstructured":"Bonnet MH, Arand DL (2003) Clinical effects of sleep fragmentation versus sleep deprivation. Sleep Med Rev 7(4):297\u2013310","journal-title":"Sleep Med Rev"},{"issue":"7726","key":"9721_CR5","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","volume":"562","author":"C Bycroft","year":"2018","unstructured":"Bycroft C, Freeman C, Petkova D, Band G, Elliott LT, Sharp K, Motyer A, Vukcevic D, Delaneau O, O\u2019Connell J, Cortes A, Welsh S, Young A, Effingham M, McVean G, Leslie S, Allen N, Donnelly P, Marchini J (2018) The UK Biobank resource with deep phenotyping and genomic data. Nature 562(7726):203\u2013209","journal-title":"Nature"},{"issue":"1","key":"9721_CR6","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1038\/s41597-024-03960-3","volume":"11","author":"S Chan","year":"2024","unstructured":"Chan S, Hang Y, Tong C, Acquah A, Schonfeldt A, Gershuny J, Doherty A (2024) Capture-24: a large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition. Sci Data 11(1):1135","journal-title":"Sci Data"},{"key":"9721_CR7","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C (2016) Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. pp 785\u2013794","DOI":"10.1145\/2939672.2939785"},{"issue":"2","key":"9721_CR8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0169649","volume":"12","author":"A Doherty","year":"2017","unstructured":"Doherty A, Jackson D, Hammerla N, Pl\u00f6tz T, Olivier P, Granat MH, White T, van Hees VT, Trenell MI, Owen CG, Preece SJ, Gillions R, Sheard S, Peakman T, Brage S, Wareham NJ (2017) Large scale population assessment of physical activity using wrist worn accelerometers: the UK biobank study. PLoS One 12(2):e0169649","journal-title":"PLoS One"},{"issue":"2","key":"9721_CR9","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.jsmc.2009.01.004","volume":"4","author":"JF Duffy","year":"2009","unstructured":"Duffy JF, Czeisler CA (2009) Effect of light on human circadian physiology. Sleep Med Clin 4(2):165\u2013177","journal-title":"Sleep Med Clin"},{"issue":"6","key":"9721_CR10","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1249\/MSS.0b013e31820513be","volume":"43","author":"DW Esliger","year":"2011","unstructured":"Esliger DW, Rowlands AV, Hurst TL, Catt M, Murray P, Eston RG (2011) Validation of the genea accelerometer. Med Sci Sports Exerc 43(6):1085\u20131093","journal-title":"Med Sci Sports Exerc"},{"issue":"5","key":"9721_CR11","doi-asserted-by":"publisher","first-page":"2283","DOI":"10.1093\/brain\/114.5.2283","volume":"114","author":"JM Fearnley","year":"1991","unstructured":"Fearnley JM, Lees AJ (1991) Ageing and parkinson\u2019s disease: substantia nigra regional selectivity. Brain 114(5):2283\u20132301","journal-title":"Brain"},{"issue":"3","key":"9721_CR12","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1109\/PROC.1973.9030","volume":"61","author":"GD Forney","year":"2005","unstructured":"Forney GD (2005) The viterbi algorithm. Proc IEEE 61(3):268\u2013278","journal-title":"Proc IEEE"},{"issue":"3","key":"9721_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550299","volume":"6","author":"H Haresamudram","year":"2022","unstructured":"Haresamudram H, Essa I, Pl\u00f6tz T (2022) Assessing the state of self-supervised human activity recognition using wearables. Proc ACM Interact Mob Wearable Ubiquitous Technol 6(3):1\u201347","journal-title":"Proc ACM Interact Mob Wearable Ubiquitous Technol"},{"key":"9721_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: European conference on computer vision. Springer, pp 630\u2013645","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"9721_CR15","doi-asserted-by":"publisher","first-page":"147","DOI":"10.3389\/fnagi.2016.00147","volume":"8","author":"S Heinzel","year":"2016","unstructured":"Heinzel S, Roeben B, Ben-Shlomo Y, Lerche S, Alves G, Barone P, Behnke S, Berendse HW, Bloem BR, Burn D, Dodel R, Grosset DG, Hu M, Kasten M, Kr\u00fcger R, Moccia M, Mollenhauer B, Oertel W, Suenkel U, Walter U, Wirdefeldt K, Liepelt-Scarfone I, Maetzler W, Berg D (2016) Prodromal markers in parkinson\u2019s disease: limitations in longitudinal studies and lessons learned. Front Aging Neurosci 8:147","journal-title":"Front Aging Neurosci"},{"issue":"4","key":"9721_CR16","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1002\/mdc3.13687","volume":"10","author":"N Heng","year":"2023","unstructured":"Heng N, Malek N, Lawton MA, Nodehi A, Pitz V, Grosset KA, Ben-Shlomo Y, Grosset DG (2023) Striatal dopamine loss in early parkinson\u2019s disease: systematic review and novel analysis of dopamine transporter imaging. Mov Disord Clin Pr 10(4):539\u2013546","journal-title":"Mov Disord Clin Pr"},{"key":"9721_CR17","unstructured":"Huang Z, Xu W, Yu K (2015) Bidirectional lstm-crf models for sequence tagging.arXiv:1508.01991 arXiv preprint"},{"issue":"1","key":"9721_CR18","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s13024-021-00504-w","volume":"17","author":"J Hunt","year":"2022","unstructured":"Hunt J, Coulson EJ, Rajnarayanan R, Oster H, Videnovic A, Rawashdeh O (2022) Sleep and circadian rhythms in parkinson\u2019s disease and preclinical models. Mol Neurodegener 17(1):2","journal-title":"Mol Neurodegener"},{"key":"9721_CR19","doi-asserted-by":"crossref","unstructured":"Ishwaran H, Kogalur U, Blackstone E, Lauer M (2008) Random survival forests. Ann Appl Statist 2(3):841\u2013860, URL\u00a0https:\/\/arXiv.org\/abs\/0811.1645v1","DOI":"10.1214\/08-AOAS169"},{"issue":"1","key":"9721_CR20","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s12874-018-0482-1","volume":"18","author":"JL Katzman","year":"2018","unstructured":"Katzman JL, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y (2018) DeepSurv: personalized treatment recommender system using a cox proportional hazards deep neural network. BMC Med Res Methodol 18(1):24","journal-title":"BMC Med Res Methodol"},{"issue":"6","key":"9721_CR21","doi-asserted-by":"publisher","first-page":"1631","DOI":"10.1093\/bioinformatics\/btab869","volume":"38","author":"K Li","year":"2022","unstructured":"Li K, Yao S, Zhang Z, Cao B, Wilson CM, Kalos D, Kuan PF, Zhu R, Wang X (2022) Efficient gradient boosting for prognostic biomarker discovery. Bioinformatics 38(6):1631\u20131638","journal-title":"Bioinformatics"},{"issue":"12","key":"9721_CR22","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1001\/jamaneurol.2013.4215","volume":"70","author":"AS Lim","year":"2013","unstructured":"Lim AS, Yu L, Kowgier M, Schneider JA, Buchman AS, Bennett DA (2013) Modification of the relationship of the apolipoprotein e $$\\varepsilon$$4 allele to the risk of alzheimer disease and neurofibrillary tangle density by sleep. JAMA Neurol 70(12):1544\u20131551","journal-title":"JAMA Neurol"},{"issue":"1","key":"9721_CR23","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.neuron.2017.02.004","volume":"94","author":"BA Mander","year":"2017","unstructured":"Mander BA, Winer JR, Walker MP (2017) Sleep and human aging. Neuron 94(1):19\u201336","journal-title":"Neuron"},{"issue":"5","key":"9721_CR24","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.3945\/ajcn.116.135129","volume":"104","author":"CE Matthews","year":"2016","unstructured":"Matthews CE, Keadle SK, Troiano RP, Kahle L, Koster A, Brychta R, Van Domelen D, Caserotti P, Chen KY, Harris TB, Berrigan D (2016) Accelerometer-measured dose-response for physical activity, sedentary time, and mortality in us adults. Am J Clin Nutr 104(5):1424\u20131432","journal-title":"Am J Clin Nutr"},{"issue":"1","key":"9721_CR25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0084483","volume":"9","author":"A Mayr","year":"2014","unstructured":"Mayr A, Schmid M (2014) Boosting the concordance index for survival data-a unified framework to derive and evaluate biomarker combinations. PLoS ONE 9(1):e84483","journal-title":"PLoS ONE"},{"key":"9721_CR26","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2022.927994","volume":"13","author":"EN Minakawa","year":"2022","unstructured":"Minakawa EN (2022) Bidirectional relationship between sleep disturbances and parkinson\u2019s disease. Front Neurol 13:927994","journal-title":"Front Neurol"},{"issue":"3","key":"9721_CR27","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1017\/S1464793103006353","volume":"79","author":"RE Mistlberger","year":"2004","unstructured":"Mistlberger RE, Skene DJ (2004) Social influences on mammalian circadian rhythms: animal and human studies. Biol Rev 79(3):533\u2013556","journal-title":"Biol Rev"},{"issue":"5","key":"9721_CR28","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1002\/mds.27670","volume":"34","author":"RB Postuma","year":"2019","unstructured":"Postuma RB, Berg D (2019) Prodromal parkinson\u2019s disease: the decade past, the decade to come. Mov Disord 34(5):665\u2013675","journal-title":"Mov Disord"},{"issue":"2","key":"9721_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3328932","volume":"3","author":"A Saeed","year":"2019","unstructured":"Saeed A, Ozcelebi T, Lukkien J (2019) Multi-task self-supervised learning for human activity detection. Proc ACM Interact Mob Wearable Ubiquitous Technol 3(2):1\u201330","journal-title":"Proc ACM Interact Mob Wearable Ubiquitous Technol"},{"issue":"8","key":"9721_CR30","doi-asserted-by":"publisher","first-page":"2048","DOI":"10.1038\/s41591-023-02440-2","volume":"29","author":"AK Schalkamp","year":"2023","unstructured":"Schalkamp AK, Peall KJ, Harrison NA, Sandor C (2023) Wearable movement-tracking data identify parkinson\u2019s disease years before clinical diagnosis. Nat Med 29(8):2048\u20132056","journal-title":"Nat Med"},{"issue":"2","key":"9721_CR31","doi-asserted-by":"publisher","DOI":"10.3390\/jpm7020003","volume":"7","author":"A Shcherbina","year":"2017","unstructured":"Shcherbina A, Mattsson CM, Waggott D, Salisbury H, Christle JW, Hastie T, Wheeler MT, Ashley EA (2017) Accuracy in wrist-worn, sensor-based measurements of heart rate and energy expenditure in a diverse cohort. J Pers Med 7(2):3","journal-title":"J Pers Med"},{"issue":"3","key":"9721_CR32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1001779","volume":"12","author":"C Sudlow","year":"2015","unstructured":"Sudlow C, Gallacher J, Allen N, Beral V, Burton P, Danesh J, Downey P, Elliott P, Green J, Landray M, Liu B, Matthews P, Ong G, Pell J, Silman A, Young A, Sprosen T, Peakman T, Collins R (2015) UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLoS Med 12(3):e1001779","journal-title":"PLoS Med"},{"key":"9721_CR33","doi-asserted-by":"publisher","DOI":"10.2196\/63105","volume":"27","author":"JM Templeton","year":"2025","unstructured":"Templeton JM, Poellabauer C, Schneider S, Rahimi M, Braimoh T, Tadamarry F, Margolesky J, Burke S, Al Masry Z (2025) Modernizing the staging of parkinson disease using digital health technology. J Med Internet Res 27:e63105","journal-title":"J Med Internet Res"},{"issue":"1","key":"9721_CR34","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1249\/mss.0b013e31815a51b3","volume":"40","author":"RP Troiano","year":"2008","unstructured":"Troiano RP, Berrigan D, Dodd KW, Masse LC, Tilert T, McDowell M (2008) Physical activity in the United States measured by accelerometer. Med Sci Sports Exerc 40(1):181","journal-title":"Med Sci Sports Exerc"},{"issue":"11","key":"9721_CR35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0142533","volume":"10","author":"VT Van Hees","year":"2015","unstructured":"Van Hees VT, Sabia S, Anderson KN, Denton SJ, Oliver J, Catt M, Abell JG, Kivim\u00e4ki M, Trenell MI, Singh-Manoux A (2015) A novel, open access method to assess sleep duration using a wrist-worn accelerometer. PLoS One 10(11):e0142533","journal-title":"PLoS One"},{"issue":"18","key":"9721_CR36","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1136\/bjsports-2021-104050","volume":"56","author":"R Walmsley","year":"2022","unstructured":"Walmsley R, Chan S, Smith-Byrne K, Ramakrishnan R, Woodward M, Rahimi K, Dwyer T, Bennett D, Doherty A (2022) Reallocation of time between device-measured movement behaviours and risk of incident cardiovascular disease. Br J Sports Med 56(18):1008\u20131017","journal-title":"Br J Sports Med"},{"issue":"2","key":"9721_CR37","doi-asserted-by":"publisher","first-page":"85","DOI":"10.22283\/qbs.2017.36.2.85","volume":"36","author":"H Wang","year":"2017","unstructured":"Wang H, Li G (2017) A selective review on random survival forests for high dimensional data. Quant Bio-Sci 36(2):85","journal-title":"Quant Bio-Sci"},{"issue":"1","key":"9721_CR38","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-26174-1","volume":"8","author":"M Willetts","year":"2018","unstructured":"Willetts M, Hollowell S, Aslett L, Holmes C, Doherty A (2018) Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants. Sci Rep 8(1):7961","journal-title":"Sci Rep"},{"issue":"1","key":"9721_CR39","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1038\/s41746-024-01062-3","volume":"7","author":"H Yuan","year":"2024","unstructured":"Yuan H, Chan S, Creagh AP, Tong C, Acquah A, Clifton DA, Doherty A (2024a) Self-supervised learning for human activity recognition using 700,000 person-days of wearable data. NPJ Digit Med 7(1):91","journal-title":"NPJ Digit Med"},{"issue":"1","key":"9721_CR40","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1038\/s41746-024-01065-0","volume":"7","author":"H Yuan","year":"2024","unstructured":"Yuan H, Plekhanova T, Walmsley R, Reynolds AC, Maddison KJ, Bucan M, Gehrman P, Rowlands A, Ray DW, Bennett D, McVeigh J, Straker L, Eastwood P, Kyle SD, Doherty A (2024b) Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality. NPJ Digit Med 7(1):86","journal-title":"NPJ Digit Med"},{"key":"9721_CR41","unstructured":"Zafar S, Yaddanapudi SS (2023) Parkinson disease. In: StatPearls [Internet], StatPearls Publishing,\u00a0Treasure Island"}],"container-title":["Lifetime Data Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10985-026-09721-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10985-026-09721-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10985-026-09721-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T08:02:24Z","timestamp":1789977744000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10985-026-09721-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["9721"],"URL":"https:\/\/doi.org\/10.1007\/s10985-026-09721-1","relation":{},"ISSN":["1380-7870","1572-9249"],"issn-type":[{"value":"1380-7870","type":"print"},{"value":"1572-9249","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"17 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"45"}}