{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:53:18Z","timestamp":1791323598583,"version":"4.3.1"},"reference-count":36,"publisher":"Institute of Mathematical Statistics","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ann. Appl. Stat."],"published-print":{"date-parts":[[2026,3,1]]},"abstract":"<jats:p>Disease progression prediction based on patients\u2019 evolving health information is challenging when true disease states are unknown due to diagnostic capabilities or high costs. For example, the absence of gold-standard neurological diagnoses hinders distinguishing Alzheimer\u2019s disease (AD) from related conditions such as AD-related dementias (ADRDs), including Lewy body dementia (LBD). Combining temporally dependent surrogate labels and health markers may improve disease prediction. However, existing literature models informative surrogate labels and observed variables that reflect the underlying states using purely generative approaches, often posing unrealistic assumptions on the outcomes and suffering from misspecification thereof. We propose integrating the conventional hidden Markov model as a generative model with a time-varying discriminative classification model to simultaneously handle potentially misspecified surrogate labels and incorporate important markers of disease progression. We develop an adaptive forward-backward algorithm with subjective labels for estimation and utilize the modified posterior and Viterbi algorithms to predict the progression of future states or new patients based on objective markers only. Importantly, the adaptation eliminates the need to model the marginal distribution of longitudinal markers, a requirement in traditional algorithms. Asymptotic properties are established, and significant improvements in finite samples are demonstrated via simulation studies. Analysis of the neuropathological dataset of the National Alzheimer\u2019s Coordinating Center (NACC) shows much improved accuracy in distinguishing LBD from AD.<\/jats:p>","DOI":"10.1214\/26-aoas2150","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:41:17Z","timestamp":1774017677000},"page":"641-662","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic classification of latent disease progression with auxiliary surrogate labels"],"prefix":"10.1214","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0253-8045","authenticated-orcid":false,"given":"Zexi","family":"Cai","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Columbia University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0843-9280","authenticated-orcid":false,"given":"Donglin","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen S.","family":"Marder","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Columbia University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9703-2265","authenticated-orcid":false,"given":"Lawrence S.","family":"Honig","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Columbia University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1510-3315","authenticated-orcid":false,"given":"Yuanjia","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Columbia University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"108","reference":[{"key":"21","doi-asserted-by":"crossref","unstructured":"<small>Prentice, R. L.<\/small> (1989). Surrogate endpoints in clinical trials: Definition and operational criteria. <i>Stat. Med.<\/i> <b>8<\/b> 431\u2013440.","DOI":"10.1002\/sim.4780080407"},{"key":"13","doi-asserted-by":"publisher","unstructured":"<small>JACKSON, C. H.<\/small>, <small>SHARPLES, L. D.<\/small>, <small>THOMPSON, S. G.<\/small>, <small>DUFFY, S. W.<\/small> and <small>COUTO, E.<\/small> (2003). Multistate Markov models for disease progression with classification error. <i>Statistician<\/i> <b>52<\/b> 193\u2013209.","DOI":"10.1111\/1467-9884.00351"},{"key":"1","doi-asserted-by":"publisher","unstructured":"<small>BAKK, Z.<\/small> and <small>KUHA, J.<\/small> (2018). Two-step estimation of models between latent classes and external variables. <i>Psychometrika<\/i> <b>83<\/b> 871\u2013892.","DOI":"10.1007\/s11336-017-9592-7"},{"key":"28","doi-asserted-by":"publisher","unstructured":"<small>SONG, X.<\/small>, <small>XIA, Y.<\/small> and <small>ZHU, H.<\/small> (2017). Hidden Markov latent variable models with multivariate longitudinal data. <i>Biometrics<\/i> <b>73<\/b> 313\u2013323.","DOI":"10.1111\/biom.12536"},{"key":"22","doi-asserted-by":"publisher","unstructured":"<small>PROUST-LIMA, C.<\/small>, <small>S\u00c9NE, M.<\/small>, <small>TAYLOR, J. M. G.<\/small> and <small>JACQMIN-GADDA, H.<\/small> (2014). Joint latent class models for longitudinal and time-to-event data: A review. <i>Stat. Methods Med. Res.<\/i> <b>23<\/b> 74\u201390.","DOI":"10.1177\/0962280212445839"},{"key":"27","doi-asserted-by":"publisher","unstructured":"<small>SHEN, J.<\/small> and <small>HE, X.<\/small> (2015). Inference for subgroup analysis with a structured logistic-normal mixture model. <i>J. Amer. Statist. Assoc.<\/i> <b>110<\/b> 303\u2013312.","DOI":"10.1080\/01621459.2014.894763"},{"key":"8","doi-asserted-by":"publisher","unstructured":"<small>DERUITER, S. L.<\/small>, <small>LANGROCK, R.<\/small>, <small>SKIRBUTAS, T.<\/small>, <small>GOLDBOGEN, J. A.<\/small>, <small>CALAMBOKIDIS, J.<\/small>, <small>FRIEDLAENDER, A. S.<\/small> and <small>SOUTHALL, B. L.<\/small> (2017). A multivariate mixed hidden Markov model for blue whale behaviour and responses to sound exposure. <i>Ann. Appl. Stat.<\/i> <b>11<\/b> 362\u2013392.","DOI":"10.1214\/16-AOAS1008"},{"key":"23","doi-asserted-by":"crossref","unstructured":"<small>Rabiner, L. R.<\/small> (1989). A tutorial on hidden Markov models and selected applications in speech recognition. <i>Proc. IEEE<\/i> <b>77<\/b> 257\u2013286.","DOI":"10.1109\/5.18626"},{"key":"2","doi-asserted-by":"crossref","unstructured":"<small>BAKK, Z.<\/small> and <small>KUHA, J.<\/small> (2021). Relating latent class membership to external variables: An overview. <i>Br. J. Math. Stat. Psychol.<\/i> <b>74<\/b> 340\u2013362.","DOI":"10.1111\/bmsp.12227"},{"key":"3","doi-asserted-by":"publisher","unstructured":"<small>BENOIT, J. S.<\/small>, <small>CHAN, W.<\/small>, <small>LUO, S.<\/small>, <small>YEH, H.-W.<\/small> and <small>DOODY, R.<\/small> (2016). A hidden Markov model approach to analyze longitudinal ternary outcomes when some observed states are possibly misclassified. <i>Stat. Med.<\/i> <b>35<\/b> 1549\u20131557.","DOI":"10.1002\/sim.6861"},{"key":"4","unstructured":"<small>BESSER, L.<\/small>, <small>KUKULL, W.<\/small>, <small>KNOPMAN, D. S.<\/small>, <small>CHUI, H.<\/small>, <small>GALASKO, D.<\/small>, <small>WEINTRAUB, S.<\/small> et al. (2018). Version 3 of the National Alzheimer\u2019s Coordinating Center\u2019s uniform data set. <i>Alzheimer Dis. Assoc. Disord.<\/i> <b>32<\/b> 351."},{"key":"5","doi-asserted-by":"crossref","unstructured":"<small>BOLLEN, K. A.<\/small> and <small>CURRAN, P. J.<\/small> (2006). <i>Latent Curve Models<\/i>: <i>A Structural Equation Perspective<\/i>. <i>Wiley Series in Probability and Statistics<\/i>. Wiley-Interscience, Hoboken, NJ.","DOI":"10.1002\/0471746096"},{"key":"6","doi-asserted-by":"crossref","unstructured":"<small>CAI, Z.<\/small>, <small>ZENG, D.<\/small>, <small>MARDER, K. S.<\/small>, <small>HONIG, L. S.<\/small> and <small>WANG, Y.<\/small> (2026). Supplement to \u201cDynamic Classification of Latent Disease Progression with Auxiliary Surrogate Labels.\u201d <a href=\"https:\/\/doi.org\/10.1214\/26-AOAS2150SUPP\">https:\/\/doi.org\/10.1214\/26-AOAS2150SUPP<\/a>","DOI":"10.1214\/26-AOAS2150SUPP"},{"key":"7","doi-asserted-by":"crossref","unstructured":"<small>COLLINS, L. M.<\/small> and <small>LANZA, S. T.<\/small> (2009). <i>Latent Class and Latent Transition Analysis<\/i>: <i>With Applications in the Social, Behavioral, and Health Sciences<\/i>. Wiley, New York.","DOI":"10.1002\/9780470567333"},{"key":"9","unstructured":"<small>GUERREIRO, R.<\/small>, <small>ESCOTT-PRICE, V.<\/small>, <small>DARWENT, L.<\/small>, <small>PARKKINEN, L.<\/small>, <small>ANSORGE, O.<\/small>, <small>HERNANDEZ, D. G.<\/small> et al. (2016). Genome-wide analysis of genetic correlation in dementia with Lewy bodies, Parkinson\u2019s and Alzheimer\u2019s diseases. <i>Neurobiol. Aging<\/i> <b>38<\/b> 214\u2013e7."},{"key":"10","doi-asserted-by":"publisher","unstructured":"<small>GUO, X.<\/small>, <small>BOURGEOIS, F. T.<\/small> and <small>CAI, T.<\/small> (2024). Quantifying proportion of treatment effect by surrogate endpoint under heterogeneity. <i>Stat. Methods Med. Res.<\/i> <b>33<\/b> 1152\u20131162.","DOI":"10.1177\/09622802241247719"},{"key":"11","doi-asserted-by":"crossref","unstructured":"<small>HU, J.<\/small> and <small>SZYMCZAK, S.<\/small> (2023). A review on longitudinal data analysis with random forest. <i>Brief. Bioinform.<\/i> <b>24<\/b> bbad002.","DOI":"10.1093\/bib\/bbad002"},{"key":"12","doi-asserted-by":"crossref","unstructured":"<small>JACKSON, C. H.<\/small> and <small>SHARPLES, L. D.<\/small> (2002). Hidden Markov models for the onset and progression of bronchiolitis obliterans syndrome in lung transplant recipients. <i>Stat. Med.<\/i> <b>21<\/b> 113\u2013128.","DOI":"10.1002\/sim.886"},{"key":"14","doi-asserted-by":"crossref","unstructured":"<small>JAIN, L.<\/small>, <small>KHRESTIAN, M.<\/small>, <small>FORMICA, S.<\/small>, <small>TUASON, E. D.<\/small>, <small>PILLAI, J. A.<\/small>, <small>RAO, S.<\/small> et al. (2024). ATN cerebrospinal fluid biomarkers in dementia with Lewy bodies: Initial results from the United States dementia with Lewy bodies consortium. <i>Alzheimer\u2019s Dement.<\/i> <b>20<\/b> 549\u2013562.","DOI":"10.1002\/alz.13398"},{"key":"15","doi-asserted-by":"publisher","unstructured":"<small>LIU, H.<\/small>, <small>SONG, X.<\/small>, <small>TANG, Y.<\/small> and <small>ZHANG, B.<\/small> (2021). Bayesian quantile nonhomogeneous hidden Markov models. <i>Stat. Methods Med. Res.<\/i> <b>30<\/b> 112\u2013128.","DOI":"10.1177\/0962280220942802"},{"key":"16","doi-asserted-by":"publisher","unstructured":"<small>MARTINO, A.<\/small>, <small>GUATTERI, G.<\/small> and <small>PAGANONI, A. M.<\/small> (2020). Multivariate hidden Markov models for disease progression. <i>Stat. Anal. Data Min.<\/i> <b>13<\/b> 499\u2013507.","DOI":"10.1002\/sam.11479"},{"key":"17","doi-asserted-by":"crossref","unstructured":"<small>MARUOTTI, A.<\/small> (2011). Mixed hidden Markov models for longitudinal data: An overview. <i>Int. Stat. Rev.<\/i> <b>79<\/b> 427\u2013454.","DOI":"10.1111\/j.1751-5823.2011.00160.x"},{"key":"18","unstructured":"<small>MCDONNELL, E. I.<\/small> (2021). Dynamic Graphical Models and Curve Registration for High-dimensional Time Course Data. PhD thesis, Columbia Univ."},{"key":"19","unstructured":"<small>MCKEITH, I. G.<\/small>, <small>FERMAN, T. J.<\/small>, <small>THOMAS, A. J.<\/small>, <small>BLANC, F.<\/small>, <small>BOEVE, B. F.<\/small>, <small>FUJISHIRO, H.<\/small> et al. (2020). Research criteria for the diagnosis of prodromal dementia with Lewy bodies. <i>Neurology<\/i> <b>94<\/b> 743\u2013755."},{"key":"20","doi-asserted-by":"crossref","unstructured":"<small>MUTH\u00c9N, B.<\/small> (2004). Latent variable analysis: Growth mixture modeling and related techniques for longitudinal data. In <i>The Sage Handbook of Quantitative Methodology for the Social Sciences, Vol<\/i>. 345 106\u2013109.","DOI":"10.4135\/9781412986311.n19"},{"key":"24","doi-asserted-by":"publisher","unstructured":"<small>RUBIN, M. L.<\/small>, <small>CHAN, W.<\/small>, <small>YAMAL, J.-M.<\/small> and <small>ROBERTSON, C. S.<\/small> (2017). A joint logistic regression and covariate-adjusted continuous-time Markov chain model. <i>Stat. Med.<\/i> <b>36<\/b> 4570\u20134582.","DOI":"10.1002\/sim.7387"},{"key":"25","doi-asserted-by":"crossref","unstructured":"<small>SALMON, D. P.<\/small>, <small>GALASKO, D.<\/small>, <small>HANSEN, L. A.<\/small>, <small>MASLIAH, E.<\/small>, <small>BUTTERS, N.<\/small>, <small>THAL, L. J.<\/small> and <small>KATZMAN, R.<\/small> (1996). Neuropsychological deficits associated with diffuse Lewy body disease. <i>Brain Cogn.<\/i> <b>31<\/b> 148\u2013165.","DOI":"10.1006\/brcg.1996.0039"},{"key":"26","unstructured":"<small>SCOTT, G. D.<\/small>, <small>ARNOLD, M. R.<\/small>, <small>BEACH, T. G.<\/small>, <small>GIBBONS, C. H.<\/small>, <small>KANTHASAMY, A. G.<\/small>, <small>LEBOVITZ, R. M.<\/small> et al. (2022). Fluid and tissue biomarkers of Lewy body dementia: Report of an LBDA symposium. <i>Front. Neurol.<\/i> <b>12<\/b> 805135."},{"key":"29","doi-asserted-by":"crossref","unstructured":"<small>STUTE, W.<\/small> (1986). On almost sure convergence of conditional empirical distribution functions. <i>Ann. Probab.<\/i> <b>14<\/b> 891\u2013901.","DOI":"10.1214\/aop\/1176992445"},{"key":"30","unstructured":"<small>UNIV. WASHINGTON<\/small> (2015). NACC UDS Researcher\u2019s Data Dictionary, version 3.0 ed. The National Alzheimer\u2019s Coordinating Center."},{"key":"31","doi-asserted-by":"publisher","unstructured":"<small>WANG, X.<\/small>, <small>PARAST, L.<\/small>, <small>TIAN, L.<\/small> and <small>CAI, T.<\/small> (2020). Model-free approach to quantifying the proportion of treatment effect explained by a surrogate marker. <i>Biometrika<\/i> <b>107<\/b> 107\u2013122.","DOI":"10.1093\/biomet\/asz065"},{"key":"32","doi-asserted-by":"publisher","unstructured":"<small>WANG, Y.<\/small>, <small>CHEN, H.<\/small>, <small>ZENG, D.<\/small>, <small>MAURO, C.<\/small>, <small>DUAN, N.<\/small> and <small>SHEAR, M. K.<\/small> (2013). Auxiliary marker-assisted classification in the absence of class identifiers. <i>J. Amer. Statist. Assoc.<\/i> <b>108<\/b> 553\u2013565.","DOI":"10.1080\/01621459.2013.775949"},{"key":"33","unstructured":"<small>WEINER, M. F.<\/small>, <small>RISSER, R. C.<\/small>, <small>MUNRO CULLUM, C.<\/small>, <small>HONIG, L.<\/small>, <small>WHITE, C.<\/small>, <small>SPECIALE, S.<\/small> et al. (1996). Alzheimer\u2019s disease and its Lewy body variant: A clinical analysis of postmortem verified cases. <i>Amer. J. Psychiatry<\/i> <b>153<\/b> 1269\u20131273."},{"key":"34","doi-asserted-by":"crossref","unstructured":"<small>YOSHIZAWA, H.<\/small>, <small>VONSATTEL, J. P. G.<\/small> and <small>HONIG, L. S.<\/small> (2013). Early neuropsychological discriminants for Lewy body disease: An autopsy series. <i>J. Neurol. Neurosurg. Psychiatry<\/i> <b>84<\/b> 1326\u20131330.","DOI":"10.1136\/jnnp-2012-304381"},{"key":"35","doi-asserted-by":"publisher","unstructured":"<small>ZHOU, J.<\/small>, <small>SONG, X.<\/small> and <small>SUN, L.<\/small> (2020). Continuous time hidden Markov model for longitudinal data. <i>J. Multivariate Anal.<\/i> <b>179<\/b> 104646,16.","DOI":"10.1016\/j.jmva.2020.104646"},{"key":"36","doi-asserted-by":"publisher","unstructured":"<small>ZOU, Y.<\/small>, <small>LIN, Y.<\/small> and <small>SONG, X.<\/small> (2024). Bayesian heterogeneous hidden Markov models with an unknown number of states. <i>J. Comput. Graph. Statist.<\/i> <b>33<\/b> 15\u201324.","DOI":"10.1080\/10618600.2023.2231055"}],"container-title":["The Annals of Applied Statistics"],"original-title":[],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:33:15Z","timestamp":1791322395000},"score":1,"resource":{"primary":{"URL":"https:\/\/projecteuclid.org\/journals\/annals-of-applied-statistics\/volume-20\/issue-1\/Dynamic-classification-of-latent-disease-progression-with-auxiliary-surrogate-labels\/10.1214\/26-AOAS2150.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,1]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,3,1]]}},"URL":"https:\/\/doi.org\/10.1214\/26-aoas2150","relation":{},"ISSN":["1932-6157","1941-7330"],"issn-type":[{"value":"1932-6157","type":"print"},{"value":"1941-7330","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,1]]}}}