{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T23:59:40Z","timestamp":1784591980625,"version":"3.55.0"},"posted":{"date-parts":[[2026,1,7]]},"group-title":"In Review","reference-count":33,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,12,22]]},"abstract":"<title>Abstract<\/title>\n                <p>Irregular monitoring and missing data limit the utility of longitudinal biomarkers in real-world practice.  We developed a generalizable framework that combines interval-aligned preprocessing, localized multiple imputation, and machine-learning forecasting to generate complete trajectories and predict future biomarker values under routine clinical conditions. Using BCR::ABL1 monitoring in chronic myeloid leukemia as a case study, we aligned measurements to 90-day intervals, applied a windowed, uncertainty-propagating imputation strategy, and trained recurrent neural network (RNN) and XGBoost models to forecast values three and six months ahead. Full Information models achieved RMSEs of 1.22\u20131.24 for 3-month predictions\u2014well below the biomarker\u2019s observed variability\u2014and maintained accuracy even when the most recent visit was intentionally omitted, simulating extended follow-up. This framework preserves local temporal structure, supports individualized monitoring decisions, and is directly adaptable to other continuous biomarkers measured under irregular real-world schedules.<\/p>","DOI":"10.21203\/rs.3.rs-8420996\/v1","type":"posted-content","created":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T09:09:07Z","timestamp":1767776947000},"source":"Crossref","is-referenced-by-count":1,"title":["A Framework for Locally Imputing and Predicting Biomarker Trajectories Under Irregular Monitoring: Application to Chronic Myeloid Leukemia"],"prefix":"10.21203","author":[{"given":"Felipe","family":"Montano-Campos","sequence":"first","affiliation":[{"name":"University of Southern California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Heagerty","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Haupt","sequence":"additional","affiliation":[{"name":"Kaiser Permanente"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erin","family":"Hahn","sequence":"additional","affiliation":[{"name":"Kaiser Permanente"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jerald","family":"Radich","sequence":"additional","affiliation":[{"name":"Fred Hutchinson Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aasthaa","family":"Bansal","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"e2200246","DOI":"10.1200\/PO.22.00246","article-title":"Impact of clinical practice gaps on the implementation of personalized medicine in advanced non\u2013small-cell lung cancer","volume":"6","author":"Sadik H","year":"2022","unstructured":"H. Sadik et al., \u201cImpact of clinical practice gaps on the implementation of personalized medicine in advanced non\u2013small-cell lung cancer,\u201d JCO Precis Oncol, vol. 6, p. e2200246, 2022.","journal-title":"JCO Precis Oncol"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.8039","author":"Montano-Campos JF","year":"2025","unstructured":"J. F. Montano-Campos, E. E. Hahn, E. C. Haupt, J. Radich, and A. Bansal, \u201cOncologist-Patient Concordance and Treatment Adherence in Chronic Myeloid Leukemia,\u201d JAMA Netw Open, vol. 8, no. 4, p. e258039, Apr. 2025, doi: 10.1001\/jamanetworkopen.2025.8039."},{"key":"ref3","author":"Medsker LR","year":"2001","unstructured":"L. R. Medsker, L. Jain, and others, \u201cRecurrent neural networks,\u201d Design and Applications, vol. 5, no. 64\u201367, p. 2, 2001."},{"issue":"47","key":"ref4","first-page":"1","article-title":"Understanding recurrent neural networks using nonequilibrium response theory","volume":"22","author":"Lim SH","year":"2021","unstructured":"S. H. Lim, \u201cUnderstanding recurrent neural networks using nonequilibrium response theory,\u201d Journal of machine learning research, vol. 22, no. 47, pp. 1\u201348, 2021.","journal-title":"Journal of machine learning research"},{"key":"ref5","author":"Chen T","year":"2016","unstructured":"T. Chen and C. Guestrin, \u201cXgboost: A scalable tree boosting system,\u201d in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785\u2013794."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"91","DOI":"10.2147\/CLEP.S72247","article-title":"Using multiple imputation to deal with missing data and attrition in longitudinal studies with repeated measures of patient-reported outcomes","author":"Biering K","year":"2015","unstructured":"K. Biering, N. H. Hjollund, and M. Frydenberg, \u201cUsing multiple imputation to deal with missing data and attrition in longitudinal studies with repeated measures of patient-reported outcomes,\u201d Clin Epidemiol, p. 91, Jan. 2015, doi: 10.2147\/CLEP.S72247.","journal-title":"Clin Epidemiol"},{"issue":"1","key":"ref7","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1186\/s12874-023-01968-8","article-title":"\u201cA wide range of missing imputation approaches in longitudinal data: a simulation study and real data analysis","volume":"23","author":"Jahangiri M","year":"2023","unstructured":"M. Jahangiri et al., \u201cA wide range of missing imputation approaches in longitudinal data: a simulation study and real data analysis,\u201d BMC Med Res Methodol, vol. 23, no. 1, p. 161, Jul. 2023, doi: 10.1186\/s12874-023-01968-8.","journal-title":"BMC Med Res Methodol"},{"issue":"9","key":"ref8","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.6004\/jnccn.2018.0071","article-title":"Chronic myeloid leukemia, version 1.2019, NCCN clinical practice guidelines in oncology","volume":"16","author":"Radich JP","year":"2018","unstructured":"J. P. Radich et al., \u201cChronic myeloid leukemia, version 1.2019, NCCN clinical practice guidelines in oncology,\u201d Journal of the National Comprehensive Cancer Network, vol. 16, no. 9, pp. 1108\u20131135, 2018.","journal-title":"Journal of the National Comprehensive Cancer Network"},{"issue":"2","key":"ref9","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1158\/1078-0432.CCR-06-1888","article-title":"Prospective early response imaging biomarker for neoadjuvant breast cancer chemotherapy","volume":"13","author":"Lee KC","year":"2007","unstructured":"K. C. Lee et al., \u201cProspective early response imaging biomarker for neoadjuvant breast cancer chemotherapy,\u201d Clinical cancer research, vol. 13, no. 2, pp. 443\u2013450, 2007.","journal-title":"Clinical cancer research"},{"issue":"5","key":"ref10","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1517\/14728222.2013.768234","article-title":"Immediate early response gene X-1, a potential prognostic biomarker in cancers","volume":"17","author":"Wu MX","year":"2013","unstructured":"M. X. Wu, I. V Ustyugova, L. Han, and O. E. Akilov, \u201cImmediate early response gene X-1, a potential prognostic biomarker in cancers,\u201d Expert Opin Ther Targets, vol. 17, no. 5, pp. 593\u2013606, 2013.","journal-title":"Expert Opin Ther Targets"},{"issue":"12","key":"ref11","doi-asserted-by":"crossref","first-page":"2327","DOI":"10.3324\/haematol.2019.231753","article-title":"Are we ready to use precision medicine in chronic myeloid leukemia practice?","volume":"104","author":"Kim DDH","year":"2019","unstructured":"D. D. H. Kim, \u201cAre we ready to use precision medicine in chronic myeloid leukemia practice?,\u201d Haematologica, vol. 104, no. 12, p. 2327, 2019.","journal-title":"Haematologica"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1007\/s11899-019-00546-4","article-title":"Towards a personalized treatment of patients with chronic myeloid leukemia","volume":"14","author":"Rabian F","year":"2019","unstructured":"F. Rabian, E. Lengline, and D. Rea, \u201cTowards a personalized treatment of patients with chronic myeloid leukemia,\u201d Curr Hematol Malig Rep, vol. 14, pp. 492\u2013500, 2019.","journal-title":"Curr Hematol Malig Rep"},{"issue":"3","key":"ref13","doi-asserted-by":"crossref","first-page":"37","DOI":"10.7812\/TPP\/12-031","article-title":"Sociodemographic characteristics of members of a large, integrated health care system: comparison with US Census Bureau data","volume":"16","author":"Koebnick C","year":"2012","unstructured":"C. Koebnick et al., \u201cSociodemographic characteristics of members of a large, integrated health care system: comparison with US Census Bureau data,\u201d Perm J, vol. 16, no. 3, p. 37, 2012.","journal-title":"Perm J"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.7812\/TPP\/22.172","author":"Davis AC","year":"2023","unstructured":"A. C. Davis, J. L. Voelkel, C. L. Remmers, J. L. Adams, and E. A. McGlynn, \u201cComparing Kaiser Permanente Members to the General Population: Implications for Generalizability of Research,\u201d Perm J, vol. 27, no. 2, pp. 87\u201398, Jun. 2023, doi: 10.7812\/TPP\/22.172."},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1472-6963-12-155","article-title":"Comparison of pharmacy-based measures of medication adherence","volume":"12","author":"Vollmer WM","year":"2012","unstructured":"W. M. Vollmer, M. Xu, A. Feldstein, D. Smith, A. Waterbury, and C. Rand, \u201cComparison of pharmacy-based measures of medication adherence,\u201d BMC Health Serv Res, vol. 12, pp. 1\u20138, 2012.","journal-title":"BMC Health Serv Res"},{"issue":"9","key":"ref16","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.6004\/jnccn.2018.0071","article-title":"Chronic myeloid leukemia, version 1.2019, NCCN clinical practice guidelines in oncology","volume":"16","author":"Radich JP","year":"2018","unstructured":"J. P. Radich et al., \u201cChronic myeloid leukemia, version 1.2019, NCCN clinical practice guidelines in oncology,\u201d Journal of the National Comprehensive Cancer Network, vol. 16, no. 9, pp. 1108\u20131135, 2018.","journal-title":"Journal of the National Comprehensive Cancer Network"},{"issue":"12","key":"ref17","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.3390\/jpm11121356","article-title":"Imputing Biomarker Status from RWE Datasets\u2014A Comparative Study","volume":"11","author":"Traynor C","year":"2021","unstructured":"C. Traynor, T. Sahota, H. Tomkinson, I. Gonzalez-Garcia, N. Evans, and M. Chappell, \u201cImputing Biomarker Status from RWE Datasets\u2014A Comparative Study,\u201d J Pers Med, vol. 11, no. 12, p. 1356, Dec. 2021, doi: 10.3390\/jpm11121356.","journal-title":"J Pers Med"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316696","volume-title":"Multiple Imputation for Nonresponse in Surveys","author":"Rubin DB","year":"1987","unstructured":"D. B. Rubin, Multiple Imputation for Nonresponse in Surveys. Wiley, 1987. doi: 10.1002\/9780470316696."},{"issue":"2","key":"ref19","doi-asserted-by":"publisher","DOI":"10.1214\/18-STS646","article-title":"Multiple Imputation for Multilevel Data with Continuous and Binary Variables","volume":"33","author":"Audigier V","year":"2018","unstructured":"V. Audigier et al., \u201cMultiple Imputation for Multilevel Data with Continuous and Binary Variables,\u201d Statistical Science, vol. 33, no. 2, May 2018, doi: 10.1214\/18-STS646.","journal-title":"Statistical Science"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/sim.3731","author":"Nevalainen J","year":"2009","unstructured":"J. Nevalainen, M. G. Kenward, and S. M. Virtanen, \u201cMissing values in longitudinal dietary data: A multiple imputation approach based on a fully conditional specification,\u201d Stat Med, vol. 28, no. 29, pp. 3657\u20133669, Dec. 2009, doi: 10.1002\/sim.3731."},{"issue":"3","key":"ref21","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1200\/JCO.2011.38.6565","article-title":"\u201cAssessment of BCR-ABL1 transcript levels at 3 months is the only requirement for predicting outcome for patients with chronic myeloid leukemia treated with tyrosine kinase inhibitors","volume":"30","author":"Marin D","year":"2012","unstructured":"D. Marin et al., \u201cAssessment of BCR-ABL1 transcript levels at 3 months is the only requirement for predicting outcome for patients with chronic myeloid leukemia treated with tyrosine kinase inhibitors,\u201d Journal of Clinical Oncology, vol. 30, no. 3, pp. 232\u2013238, 2012.","journal-title":"Journal of Clinical Oncology"},{"key":"ref22","author":"Afshar S","year":"2011","unstructured":"S. Afshar, F. Abdolrahmani, T. F. VAKILI, S. M. ZOHDI, K. Taheri, and others, \u201cRecognition and prediction of leukemia with Artificial Neural Network (ANN),\u201d 2011."},{"issue":"3","key":"ref23","doi-asserted-by":"crossref","first-page":"2191","DOI":"10.1007\/s11277-021-08798-1","article-title":"Autonomous leukemia detection scheme based on hybrid convolutional neural network model using learning algorithm","volume":"126","author":"Sakthiraj FSK","year":"2022","unstructured":"F. S. K. Sakthiraj, \u201cAutonomous leukemia detection scheme based on hybrid convolutional neural network model using learning algorithm,\u201d Wirel Pers Commun, vol. 126, no. 3, pp. 2191\u20132206, 2022.","journal-title":"Wirel Pers Commun"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"104722","DOI":"10.1016\/j.bspc.2023.104722","article-title":"Automated detection and classification of leukemia on a subject-independent test dataset using deep transfer learning supported by Grad-CAM visualization","volume":"83","author":"Abhishek A","year":"2023","unstructured":"A. Abhishek, R. K. Jha, R. Sinha, and K. Jha, \u201cAutomated detection and classification of leukemia on a subject-independent test dataset using deep transfer learning supported by Grad-CAM visualization,\u201d Biomed Signal Process Control, vol. 83, p. 104722, 2023.","journal-title":"Biomed Signal Process Control"},{"issue":"2","key":"ref25","doi-asserted-by":"crossref","first-page":"2039","DOI":"10.32604\/csse.2023.036985","article-title":"\u201cMayGAN: Mayfly Optimization with Generative Adversarial Network-Based Deep Learning Method to Classify Leukemia Form Blood Smear Images","volume":"46","author":"Veeraiah N","year":"2023","unstructured":"N. Veeraiah, Y. Alotaibi, and A. F. Subahi, \u201cMayGAN: Mayfly Optimization with Generative Adversarial Network-Based Deep Learning Method to Classify Leukemia Form Blood Smear Images.,\u201d Comput. Syst. Sci. Eng., vol. 46, no. 2, pp. 2039\u20132058, 2023.","journal-title":"Comput. Syst. Sci. Eng."},{"issue":"1","key":"ref26","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1186\/s12911-022-01980-w","article-title":"Comparing machine learning algorithms to predict 5-year survival in patients with chronic myeloid leukemia","volume":"22","author":"Shanbehzadeh M","year":"2022","unstructured":"M. Shanbehzadeh, M. R. Afrash, N. Mirani, and H. Kazemi-Arpanahi, \u201cComparing machine learning algorithms to predict 5-year survival in patients with chronic myeloid leukemia,\u201d BMC Med Inform Decis Mak, vol. 22, no. 1, p. 236, 2022.","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1200\/CCI-25-00003","article-title":"Using Early Biomarker Change and Treatment Adherence to Predict Risk of Relapse Among Patients With Chronic Myeloid Leukemia Who Are in Remission","volume":"9","author":"Montano-Campos JF","year":"2025","unstructured":"J. F. Montano-Campos, E. Hahn, E. Haupt, J. Radich, and A. Bansal, \u201cUsing Early Biomarker Change and Treatment Adherence to Predict Risk of Relapse Among Patients With Chronic Myeloid Leukemia Who Are in Remission,\u201d JCO Clin Cancer Inform, no. 9, Jul. 2025, doi: 10.1200\/CCI-25-00003.","journal-title":"JCO Clin Cancer Inform"},{"issue":"2","key":"ref28","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1002\/ajh.26047","article-title":"The LEukemia Artificial Intelligence Program (LEAP) in chronic myeloid leukemia in chronic phase: A model to improve patient outcomes","volume":"96","author":"Sasaki K","year":"2021","unstructured":"K. Sasaki et al., \u201cThe LEukemia Artificial Intelligence Program (LEAP) in chronic myeloid leukemia in chronic phase: A model to improve patient outcomes,\u201d Am J Hematol, vol. 96, no. 2, pp. 241\u2013250, 2021.","journal-title":"Am J Hematol"},{"issue":"11","key":"ref29","doi-asserted-by":"crossref","first-page":"e903","DOI":"10.1016\/j.clml.2021.06.025","article-title":"Accurate machine-learning-based classification of leukemia from blood smear images","volume":"21","author":"Dese K","year":"2021","unstructured":"K. Dese et al., \u201cAccurate machine-learning-based classification of leukemia from blood smear images,\u201d Clin Lymphoma Myeloma Leuk, vol. 21, no. 11, pp. e903\u2013e914, 2021.","journal-title":"Clin Lymphoma Myeloma Leuk"},{"key":"ref30","author":"Khosla E","year":"2018","unstructured":"E. Khosla and D. Ramesh, \u201cPhase classification of chronic myeloid leukemia using convolution neural networks,\u201d in 2018 4th International Conference on Recent Advances in Information Technology (RAIT), 2018, pp. 1\u20136."},{"issue":"9","key":"ref31","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1016\/j.compbiomed.2013.06.004","article-title":"Discrimination of malignant neutrophils of chronic myelogenous leukemia from normal neutrophils by support vector machine","volume":"43","author":"Ni W","year":"2013","unstructured":"W. Ni, X. Tong, W. Qian, J. Jin, and H. Zhao, \u201cDiscrimination of malignant neutrophils of chronic myelogenous leukemia from normal neutrophils by support vector machine,\u201d Comput Biol Med, vol. 43, no. 9, pp. 1192\u20131195, 2013.","journal-title":"Comput Biol Med"},{"issue":"1","key":"ref32","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1186\/s12935-023-02905-x","article-title":"Molecular subtypes predict therapeutic responses and identifying and validating diagnostic signatures based on machine learning in chronic myeloid leukemia","volume":"23","author":"Zhong F-M","year":"2023","unstructured":"F.-M. Zhong et al., \u201cMolecular subtypes predict therapeutic responses and identifying and validating diagnostic signatures based on machine learning in chronic myeloid leukemia,\u201d Cancer Cell Int, vol. 23, no. 1, p. 61, 2023.","journal-title":"Cancer Cell Int"},{"issue":"1","key":"ref33","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1186\/s12885-024-12764-y","article-title":"Application of artificial intelligence in chronic myeloid leukemia (CML) disease prediction and management: a scoping review","volume":"24","author":"Ram M","year":"2024","unstructured":"M. Ram et al., \u201cApplication of artificial intelligence in chronic myeloid leukemia (CML) disease prediction and management: a scoping review,\u201d BMC Cancer, vol. 24, no. 1, p. 1026, 2024.","journal-title":"BMC Cancer"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-8420996\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-8420996\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T22:38:49Z","timestamp":1768084729000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-8420996\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-8420996\/v1","relation":{},"subject":[],"published":{"date-parts":[[2026,1,7]]},"subtype":"preprint"}}