{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T02:33:29Z","timestamp":1784169209899,"version":"3.55.0"},"reference-count":39,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T00:00:00Z","timestamp":1580428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Comput. Healthcare"],"published-print":{"date-parts":[[2020,1,31]]},"abstract":"<jats:p>Using electronic medical records to learn personalized risk trajectories poses significant challenges because often very few samples are available in a patient\u2019s history, and, when available, their information content is highly diverse. In this article, we consider how to integrate sparsely sampled longitudinal data, missing measurements informative of the underlying health status, and static information to estimate (dynamically, as new information becomes available) personalized survival distributions. We achieve this by developing a nonparametric probabilistic model that generates survival trajectories, and corresponding uncertainty estimates, from an ensemble of Bayesian trees in which time is incorporated explicitly to learn variable interactions over time, without needing to specify the longitudinal process beforehand. As such, the changing influence on survival of variables over time is inferred from the data directly, which we analyze with post-processing statistics derived from our model.<\/jats:p>","DOI":"10.1145\/3377164","type":"journal-article","created":{"date-parts":[[2020,3,2]],"date-time":"2020-03-02T18:50:15Z","timestamp":1583175015000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Flexible Modelling of Longitudinal Medical Data"],"prefix":"10.1145","volume":"1","author":[{"given":"Alexis","family":"Bellot","sequence":"first","affiliation":[{"name":"University of Cambridge and the Alan Turing Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mihaela Van Der","family":"Schaar","sequence":"additional","affiliation":[{"name":"University of Cambridge, the Alan Turing Institute, and University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,3,2]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"DPSCREEN: Dynamic personalized screening. In Advances in Neural Information Processing Systems 30 (NIPS\u201917). 1321--1332.","author":"Ahuja Kartik","year":"2017"},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of theInternational Conference of Machine Learning.","author":"Alaa Ahmed M."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1993.10476321"},{"key":"e_1_2_1_4_1","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1016\/j.athoracsur.2012.02.049","article-title":"An introduction to mixed models and joint modeling: Analysis of valve function over time","volume":"93","author":"Andrinopoulou Eleni-Rosalina","year":"2012","journal-title":"Annals of Thoracic Surgery"},{"key":"e_1_2_1_5_1","doi-asserted-by":"crossref","first-page":"3946","DOI":"10.1002\/sim.5452","article-title":"Generating survival times to simulate Cox proportional hazards models with time-varying covariates","volume":"31","author":"Austin Peter C.","year":"2012","journal-title":"Statistics in Medicine"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0004-1"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-118"},{"key":"e_1_2_1_8_1","volume-title":"Proceedings of the Machine Learning for Healthcare Conference. 2--16","author":"Bellot Alexis"},{"key":"e_1_2_1_9_1","unstructured":"Alexis Bellot and Mihaela van der Schaar. 2018. Multitask boosting for survival analysis with competing risks. In Advances in Neural Information Processing Systems 31 (NIPS\u201918). 1390--1399.  Alexis Bellot and Mihaela van der Schaar. 2018. Multitask boosting for survival analysis with competing risks. In Advances in Neural Information Processing Systems 31 (NIPS\u201918). 1390--1399."},{"key":"e_1_2_1_10_1","doi-asserted-by":"crossref","first-page":"e003389","DOI":"10.1136\/bmjopen-2013-003389","article-title":"Representativeness and optimal use of body mass index (BMI) in the UK clinical practice research datalink (CPRD)","volume":"3","author":"Bhaskaran Krishnan","year":"2013","journal-title":"BMJ Open"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1214\/09-AOAS285"},{"key":"e_1_2_1_12_1","volume-title":"Proceedings of the Machine Learning for Healthcare Conference. 301--318","author":"Choi Edward","year":"2016"},{"key":"e_1_2_1_13_1","unstructured":"Tamara Fern\u00e1ndez Nicol\u00e1s Rivera and Yee Whye Teh. 2016. Gaussian processes for survival analysis. In Advances in Neural Information Processing Systems. 5021--5029.  Tamara Fern\u00e1ndez Nicol\u00e1s Rivera and Yee Whye Teh. 2016. Gaussian processes for survival analysis. In Advances in Neural Information Processing Systems. 5021--5029."},{"key":"e_1_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Lo\u00efc Ferrer Hein Putter and C\u00e9cile Proust-Lima. 2017. Individual dynamic predictions using landmarking and joint modelling: Validation of estimators and robustness assessment. arXiv:1707.03706.  Lo\u00efc Ferrer Hein Putter and C\u00e9cile Proust-Lima. 2017. Individual dynamic predictions using landmarking and joint modelling: Validation of estimators and robustness assessment. arXiv:1707.03706.","DOI":"10.1177\/0962280218811837"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_2_1_16_1","doi-asserted-by":"crossref","first-page":"2173","DOI":"10.1002\/sim.5681","article-title":"Estimating a time-dependent concordance index for survival prediction models with covariate dependent censoring","volume":"32","author":"Gerds Thomas A.","year":"2013","journal-title":"Statistics in Medicine"},{"key":"e_1_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Yanzhang Gong S. L. Klingenberg and C. Gluud. 2006. Systematic review and meta-analysis: D-Penicillamine vs. placebo\/no intervention in patients with primary biliary cirrhosis\u2014Cochrane Hepato-Biliary Group. Alimentary Pharmacology 8 Therapeutics 24 11--12 (2006) 1535--1544.  Yanzhang Gong S. L. Klingenberg and C. Gluud. 2006. Systematic review and meta-analysis: D-Penicillamine vs. placebo\/no intervention in patients with primary biliary cirrhosis\u2014Cochrane Hepato-Biliary Group. Alimentary Pharmacology 8 Therapeutics 24 11--12 (2006) 1535--1544.","DOI":"10.1111\/j.1365-2036.2006.03164.x"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1009212815"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/1.4.465"},{"key":"e_1_2_1_20_1","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1186\/s12874-016-0212-5","article-title":"Joint modelling of time-to-event and multivariate longitudinal outcomes: Recent developments and issues","volume":"16","author":"Hickey Graeme L.","year":"2016","journal-title":"BMC Medical Research Methodology"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOAS169"},{"key":"e_1_2_1_22_1","unstructured":"Adam Kapelner and Justin Bleich. 2013. bartMachine: Machine learning with Bayesian additive regression trees. arXiv:1312.2171.  Adam Kapelner and Justin Bleich. 2013. bartMachine: Machine learning with Bayesian additive regression trees. arXiv:1312.2171."},{"key":"e_1_2_1_23_1","doi-asserted-by":"crossref","first-page":"e1002741","DOI":"10.1371\/journal.pmed.1002741","article-title":"Lifetime risk and multimorbidity of non-communicable diseases and disease-free life expectancy in the general population: A population-based cohort study","volume":"16","author":"Licher Silvan","year":"2019","journal-title":"PLoS Medicine"},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the Machine Learning for Healthcare Conference.","author":"Lim Bryan"},{"key":"e_1_2_1_25_1","unstructured":"Zachary C. Lipton. 2016. The mythos of model interpretability. arXiv:1606.03490.  Zachary C. Lipton. 2016. The mythos of model interpretability. arXiv:1606.03490."},{"key":"e_1_2_1_26_1","unstructured":"Zachary C. Lipton. 2017. The doctor just won\u2019t accept that! arXiv:1711.08037.  Zachary C. Lipton. 2017. The doctor just won\u2019t accept that! arXiv:1711.08037."},{"key":"e_1_2_1_27_1","volume-title":"Rubin","author":"Little Roderick J. A.","year":"2014"},{"key":"e_1_2_1_28_1","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1186\/1745-6215-15-237","article-title":"A review of the handling of missing longitudinal outcome data in clinical trials","volume":"15","author":"Powney Matthew","year":"2014","journal-title":"Trials"},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the Machine Learning for Healthcare Conference. 101--114","author":"Ranganath Rajesh","year":"2016"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2010.01546.x"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1177\/1536867X0400400301"},{"key":"e_1_2_1_32_1","first-page":"155","article-title":"It\u2019s about time: Using discrete-time survival analysis to study duration and the timing of events","volume":"18","author":"Singer Judith D.","year":"1993","journal-title":"Journal of Educational Statistics"},{"key":"e_1_2_1_33_1","doi-asserted-by":"crossref","first-page":"1948","DOI":"10.1109\/TPAMI.2017.2742504","article-title":"Scalable joint models for reliable uncertainty-aware event prediction","volume":"40","author":"Soleimani Hossein","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_1_34_1","doi-asserted-by":"crossref","first-page":"2741","DOI":"10.1002\/sim.6893","article-title":"Nonparametric survival analysis using Bayesian additive regression trees (BART)","volume":"35","author":"Sparapani Rodney A.","year":"2016","journal-title":"Statistics in Medicine"},{"key":"e_1_2_1_35_1","doi-asserted-by":"crossref","first-page":"S292","DOI":"10.1111\/j.1532-5415.2010.02936.x","article-title":"A review of selected longitudinal studies on aging: Past findings and future directions","volume":"58","author":"Stanziano Damian C.","year":"2010","journal-title":"Journal of the American Geriatrics Society"},{"key":"e_1_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Terry M. Therneau and P. M. Grambsch. 2000. Modeling Survival Data: Extending the Cox Model P. Bickel P. Diggle S. Fienberg et al. (Eds.). Statistics for Biology and Health. Springer.  Terry M. Therneau and P. M. Grambsch. 2000. Modeling Survival Data: Extending the Cox Model P. Bickel P. Diggle S. Fienberg et al. (Eds.). Statistics for Biology and Health. Springer.","DOI":"10.1007\/978-1-4757-3294-8"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.01.010"},{"key":"e_1_2_1_38_1","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1111\/j.1467-9469.2006.00529.x","article-title":"Dynamic prediction by landmarking in event history analysis","volume":"34","author":"Van Houwelingen Hans C.","year":"2007","journal-title":"Scandinavian Journal of Statistics"},{"key":"e_1_2_1_39_1","doi-asserted-by":"crossref","first-page":"e1000440","DOI":"10.1371\/journal.pmed.1000440","article-title":"Life course trajectories of systolic blood pressure using longitudinal data from eight UK cohorts","volume":"8","author":"Wills Andrew K.","year":"2011","journal-title":"PLoS Medicine"}],"container-title":["ACM Transactions on Computing for Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377164","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3377164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:38Z","timestamp":1750202618000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377164"}},"subtitle":["A Bayesian Nonparametric Approach"],"short-title":[],"issued":{"date-parts":[[2020,1,31]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,1,31]]}},"alternative-id":["10.1145\/3377164"],"URL":"https:\/\/doi.org\/10.1145\/3377164","relation":{},"ISSN":["2691-1957","2637-8051"],"issn-type":[{"value":"2691-1957","type":"print"},{"value":"2637-8051","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,31]]},"assertion":[{"value":"2019-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-03-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}