{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T21:00:07Z","timestamp":1790715607896,"version":"4.1.0"},"reference-count":41,"publisher":"American Society of Clinical Oncology (ASCO)","issue":"3","content-domain":{"domain":["ascopubs.org"],"crossmark-restriction":true},"short-container-title":["JCO Clin Cancer Inform"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Conventional prognostic models for metastatic prostate cancer (mPC) typically rely on summary features like prostate-specific antigen (PSA) doubling time, often obscuring informative longitudinal dynamics. We developed TrajSurv-mPC, a flexible deep learning framework that analyzes full premetastasis patient trajectories\u2014including serial PSA and treatments\u2014to improve postmetastasis overall survival (OS) prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The TrajSurv-mPC framework was developed and evaluated using two independent cohorts: Memorial Sloan Kettering (MSK; n = 403) and Veterans Affairs (VA; n = 9,984). To demonstrate its architectural robustness, the framework's sequential modeling was implemented with both Long Short-Term Memory (LSTM) and Transformer backbones. The models used baseline characteristics alongside longitudinal PSA and treatment data to predict OS from the time of metastasis detection. Performance was compared against models using summary features. Generalizability was assessed via external validation (training on a harmonized VA subcohort; testing on MSK). Interpretability was explored through post hoc hidden state clustering, a simulation study, and a case study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Compared with summary-feature models (C-indices: 0.650-0.677 internally; 0.635-0.651 externally), the TrajSurv-mPC framework achieved C-indices of 0.723-0.747 (MSK) and 0.711-0.754 (VA) in internal validations, and 0.693 (LSTM,\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .02) and 0.708 (Transformer,\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .008) in cross-cohort external validations across both architectures. Clustering stratified distinct prognostic groups (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      &lt; .001). Furthermore, simulation and case studies showed that predicted risk varied in clinically plausible directions across different treatment response trajectories.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>By modeling the complete premetastasis PSA trajectory, the TrajSurv-mPC framework improves prognostic risk prediction in mPC. Its robust performance across different sequential backbones demonstrates the generalizable added value of dynamic patterns in distinct populations. Combining this framework with complementary measures based on imaging or genomics may enhance personalization of mPC management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1200\/cci-25-00328","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T20:00:06Z","timestamp":1790712006000},"update-policy":"https:\/\/doi.org\/10.1200\/crossmark","source":"Crossref","is-referenced-by-count":0,"title":["TrajSurv-mPC: Learning From Prostate-Specific Antigen Trajectories for Interpretable and Generalizable Survival Prediction in Metastatic Prostate Cancer"],"prefix":"10.1200","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2921-829X","authenticated-orcid":true,"given":"Sihang","family":"Zeng","sequence":"first","affiliation":[{"name":"Fred Hutch Cancer Center, Seattle, WA"},{"name":"Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA"},{"name":"VA Greater Los Angeles Healthcare System, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5149-5379","authenticated-orcid":true,"given":"Lukas","family":"Owens","sequence":"additional","affiliation":[{"name":"Fred Hutch Cancer Center, Seattle, WA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2890-9673","authenticated-orcid":true,"given":"Lucas J.","family":"Liu","sequence":"additional","affiliation":[{"name":"Fred Hutch Cancer Center, Seattle, WA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sigrid","family":"Carlsson","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7084-2743","authenticated-orcid":true,"given":"Jonathan S.","family":"Fainberg","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent P.","family":"Laudone","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6388-5553","authenticated-orcid":true,"given":"Martin W.","family":"Schoen","sequence":"additional","affiliation":[{"name":"Saint Louis Veterans Affairs Medical Center, Saint Louis, MO"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isla P.","family":"Garraway","sequence":"additional","affiliation":[{"name":"VA Greater Los Angeles Healthcare System, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9164-6370","authenticated-orcid":true,"given":"Ruth","family":"Etzioni","sequence":"additional","affiliation":[{"name":"Fred Hutch Cancer Center, Seattle, WA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"233","reference":[{"key":"e_1_3_6_2_2","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.32176"},{"key":"e_1_3_6_3_2","unstructured":"Mayo Clinic [Internet]: Metastatic prostate cancer\u2014Symptoms and causes. https:\/\/www.mayoclinic.org\/diseases-conditions\/metastatic-prostate-cancer\/symptoms-causes\/syc-20377966"},{"key":"e_1_3_6_4_2","doi-asserted-by":"publisher","DOI":"10.1200\/EDBK_390166"},{"key":"e_1_3_6_5_2","first-page":"243","article-title":"Metastatic castration-resistant prostate cancer: Insights on current therapy and promising experimental drugs","volume":"15","author":"Ferretti S","year":"2023","unstructured":"Ferretti S, Mercinelli C, Marandino L, et al: Metastatic castration-resistant prostate cancer: Insights on current therapy and promising experimental drugs. Res Rep Urol 15:243-259, 2023","journal-title":"Res Rep Urol"},{"key":"e_1_3_6_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2020.06.011"},{"key":"e_1_3_6_7_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1506859"},{"key":"e_1_3_6_8_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.37871"},{"key":"e_1_3_6_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)30314-7"},{"key":"e_1_3_6_10_2","volume-title":"Understanding Disparities in Access to Genomic Medicine: Proceedings of a Workshop","author":"National Academies of Sciences, Engineering, and Medicine; Health and Medicine Division; Board on Health Sciences Policy; Roundtable on Genomics and Precision Health","year":"2018","unstructured":"National Academies of Sciences, Engineering, and Medicine; Health and Medicine Division; Board on Health Sciences Policy; Roundtable on Genomics and Precision Health: Exploring the barriers to accessing genomic and genetic services, in Understanding Disparities in Access to Genomic Medicine: Proceedings of a Workshop. National Academies Press (US), 2018"},{"key":"e_1_3_6_11_2","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.120.251751"},{"key":"e_1_3_6_12_2","article-title":"TrajSurv: Learning continuous latent trajectories from electronic health records for trustworthy survival prediction","author":"Zeng S","unstructured":"Zeng S, Liu LJ, Wen J, et al: TrajSurv: Learning continuous latent trajectories from electronic health records for trustworthy survival prediction. arXiv http:\/\/arxiv.org\/abs\/2508.00657","journal-title":"arXiv"},{"key":"e_1_3_6_13_2","volume-title":"RETAIN: An Interpretable Predictive Model for Healthcare Using Reverse Time Attention Mechanism","author":"Choi E","unstructured":"Choi E, Bahadori MT, Kulas JA, et al: RETAIN: An Interpretable Predictive Model for Healthcare Using Reverse Time Attention Mechanism. arXiv http:\/\/arxiv.org\/abs\/1608.05745"},{"key":"e_1_3_6_14_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae028"},{"key":"e_1_3_6_15_2","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aao5333"},{"key":"e_1_3_6_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjmsu.2011.08.006"},{"key":"e_1_3_6_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00815-1"},{"key":"e_1_3_6_18_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2025.43.5_suppl.167"},{"key":"e_1_3_6_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(16)30633-7"},{"key":"e_1_3_6_20_2","doi-asserted-by":"publisher","unstructured":"Alba PR Gao A Lee KM et al: Ascertainment of veterans with metastatic prostate cancer in electronic health records: Demonstrating the case for natural language processing. JCO Clin Cancer Inform 10.1200\/CCI.21.00030","DOI":"10.1200\/CCI.21.00030"},{"key":"e_1_3_6_21_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_6_22_2","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, et al: Attention is all you need, in Advances in Neural Information Processing Systems. Curran Associates, 2017. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_6_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_6_24_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1972.tb00899.x"},{"key":"e_1_3_6_25_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-018-0482-1"},{"key":"e_1_3_6_26_2","first-page":"841","volume-title":"Random Survival Forests","author":"Ishwaran H","year":"2008","unstructured":"Ishwaran H, Kogalur UB, Blackstone EH, et al: Random Survival Forests. Ann Appl Stat 2:841-860, 2008"},{"key":"e_1_3_6_27_2","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_3_6_28_2","volume-title":"Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS","author":"Liashchynskyi P","unstructured":"Liashchynskyi P, Liashchynskyi P: Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS. arXiv http:\/\/arxiv.org\/abs\/1912.06059"},{"key":"e_1_3_6_29_2","first-page":"100","article-title":"Algorithm AS 136: A K-Means clustering algorithm","volume":"28","author":"Hartigan JA","year":"1979","unstructured":"Hartigan JA, Wong MA: Algorithm AS 136: A K-Means clustering algorithm. J R Stat Soc Ser C Appl Stat 28:100-108, 1979","journal-title":"J R Stat Soc Ser C Appl Stat"},{"key":"e_1_3_6_30_2","volume-title":"Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations","author":"Qiu G","unstructured":"Qiu G, Kuang D, Goel S: Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations. arXiv http:\/\/arxiv.org\/abs\/2403.03375"},{"key":"e_1_3_6_31_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2791"},{"key":"e_1_3_6_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_6_33_2","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djt280"},{"key":"e_1_3_6_34_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2002.11.021"},{"key":"e_1_3_6_35_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-016-2160-1"},{"key":"e_1_3_6_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00345-018-2236-4"},{"key":"e_1_3_6_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11255-025-04389-2"},{"key":"e_1_3_6_38_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2013.52.3696"},{"key":"e_1_3_6_39_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00613-w"},{"key":"e_1_3_6_40_2","doi-asserted-by":"publisher","DOI":"10.1056\/EVIDoa2300023"},{"key":"e_1_3_6_41_2","first-page":"1","article-title":"Contemporary role of the Decipher\u00ae test in prostate cancer management: Current practice and future perspectives","volume":"18","author":"Dalela D","year":"2016","unstructured":"Dalela D, L\u00f6ppenberg B, Sood A, et al: Contemporary role of the Decipher\u00ae test in prostate cancer management: Current practice and future perspectives. Rev Urol 18:1-9, 2016","journal-title":"Rev Urol"},{"key":"e_1_3_6_42_2","doi-asserted-by":"publisher","DOI":"10.2147\/OTT.S509285"}],"container-title":["JCO Clinical Cancer Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascopubs.org\/doi\/pdfdirect\/10.1200\/CCI-25-00328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T20:00:10Z","timestamp":1790712010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascopubs.org\/doi\/10.1200\/CCI-25-00328"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1200\/CCI-25-00328"],"URL":"https:\/\/doi.org\/10.1200\/cci-25-00328","relation":{},"ISSN":["2473-4276"],"issn-type":[{"value":"2473-4276","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"2025-10-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-26","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2500328"}}