Publicação

Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications

Ver documento

Detalhes bibliográficos
Resumo:Reliable quantification of treatment benefit in late-phase clinical trials increasingly requires modeling patient histories that include progression, adverse events, and treat ment switches. Conventional multi-state analyses often invoke the Markov property and assume independent right censoring— conditions rarely satisfied in oncology, immunology, or cell-therapy programs, where intermediate events and informative dropout are common. This article presents a systematic review and bibliometric synthesis of 48 peer reviewed studies published through 11 June 2025 that (i) relax the Markov assumption and (ii) address complex observation schemes such as left truncation, interval censoring, or informative censoring, identified through Web of Science and Scopus searches following preferred reporting items for systematic reviews and meta-analyses 2020 guidelines. A recurring set of methodological strategies emerges across the literature, including semi-Markov transition-intensity models, illness–death and semi-competing risks frameworks, landmarking for dynamic prediction, and inverse-probability-of-censoring weighting. Estimation approaches range from nonparametric product integrals to semiparametric weighted likelihoods and Bayesian Markov chain Monte Carlo, with recent contributions exploring saddle-point approximations and subsampling for large-scale electronic health records. To complement this synthesis, we include a compact simulation contrasting baseline and landmark Aalen–Johansen estimators under semi-Markov dynamics with history-dependent censoring, and a bibliometric network analysis mapping collaboration patterns, thematic clusters, and structural gaps. The findings highlight the need for scalable, auditable software, robust diagnostics aligned with the International Council for Harmonization E9(R1) estimand framework (which links clinical trial objectives to precise statistical targets), and better integration of high-dimensional biomarkers; limitations include the English-language restriction and reliance on bibliometric metadata. Addressing these priorities may enhance both the methodological robustness and regulatory applicability of non-Markov survival models.
Autores principais:Azevedo, Marta Vasconcelos Castro
Outros Autores:Machado, Luís Meira; Moreira, Carla Maria Gonçalves Macedo
Assunto:History-dependent censoring Interval/panel observation Left truncation Non-Markov inference PRISMA Pseudo-observations
Ano:2025
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
_version_ 1866878289327423488
author Azevedo, Marta Vasconcelos Castro
author2 Machado, Luís Meira
Moreira, Carla Maria Gonçalves Macedo
author2_role author
author
author_facet Azevedo, Marta Vasconcelos Castro
Machado, Luís Meira
Moreira, Carla Maria Gonçalves Macedo
author_role author
contributor_name_str_mv Universidade do Minho
country_str PT
creators_json_txt [{\"Person.name\":\"Azevedo, Marta Vasconcelos Castro\"},{\"Person.name\":\"Machado, Luís Meira\"},{\"Person.name\":\"Moreira, Carla Maria Gonçalves Macedo\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Universidade do Minho
datacite.creators.creator.creatorName.fl_str_mv Azevedo, Marta Vasconcelos Castro
Machado, Luís Meira
Moreira, Carla Maria Gonçalves Macedo
datacite.date.Accepted.fl_str_mv 2025-01-01T00:00:00Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv History-dependent censoring
Interval/panel observation
Left truncation
Non-Markov inference
PRISMA
Pseudo-observations
datacite.titles.title.fl_str_mv Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications
dc.contributor.none.fl_str_mv Universidade do Minho
dc.creator.none.fl_str_mv Azevedo, Marta Vasconcelos Castro
Machado, Luís Meira
Moreira, Carla Maria Gonçalves Macedo
dc.date.Accepted.fl_str_mv 2025-01-01T00:00:00Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://hdl.handle.net/1822/99211
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv Chilean Statistical Society
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.rights.rights.copyright.fl_str_mv openAccess
dc.subject.none.fl_str_mv History-dependent censoring
Interval/panel observation
Left truncation
Non-Markov inference
PRISMA
Pseudo-observations
dc.title.fl_str_mv Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description Reliable quantification of treatment benefit in late-phase clinical trials increasingly requires modeling patient histories that include progression, adverse events, and treat ment switches. Conventional multi-state analyses often invoke the Markov property and assume independent right censoring— conditions rarely satisfied in oncology, immunology, or cell-therapy programs, where intermediate events and informative dropout are common. This article presents a systematic review and bibliometric synthesis of 48 peer reviewed studies published through 11 June 2025 that (i) relax the Markov assumption and (ii) address complex observation schemes such as left truncation, interval censoring, or informative censoring, identified through Web of Science and Scopus searches following preferred reporting items for systematic reviews and meta-analyses 2020 guidelines. A recurring set of methodological strategies emerges across the literature, including semi-Markov transition-intensity models, illness–death and semi-competing risks frameworks, landmarking for dynamic prediction, and inverse-probability-of-censoring weighting. Estimation approaches range from nonparametric product integrals to semiparametric weighted likelihoods and Bayesian Markov chain Monte Carlo, with recent contributions exploring saddle-point approximations and subsampling for large-scale electronic health records. To complement this synthesis, we include a compact simulation contrasting baseline and landmark Aalen–Johansen estimators under semi-Markov dynamics with history-dependent censoring, and a bibliometric network analysis mapping collaboration patterns, thematic clusters, and structural gaps. The findings highlight the need for scalable, auditable software, robust diagnostics aligned with the International Council for Harmonization E9(R1) estimand framework (which links clinical trial objectives to precise statistical targets), and better integration of high-dimensional biomarkers; limitations include the English-language restriction and reliance on bibliometric metadata. Addressing these priorities may enhance both the methodological robustness and regulatory applicability of non-Markov survival models.
dirty 0
eu_rights_str_mv openAccess
format article
fulltext.url.fl_str_mv https://repositorium.uminho.pt/bitstreams/20c9dd07-6a0b-4ba1-89c0-e0f5da755739/download
funding.funder.alternateName_str_mv other
other
funding.funder.identifier_str_mv urn:openaire:fct_________::FCT
urn:openaire:fct_________::FCT
funding.funder.name_str_mv Fundação para a Ciência e a Tecnologia, I.P.
Fundação para a Ciência e a Tecnologia, I.P.
funding.identifier_str_mv UID/00013/2025
2023.14897.PEX
funding.name_str_mv Avaliação UID 2023/2024
Concurso de Projetos Exploratórios em Todos os Domínios Científicos 2023
funding_str_mv UID/00013/2025
https://hdl.handle.net/1822/98696
2023.14897.PEX
https://hdl.handle.net/1822/99238
id rum_c19e19a16aebd6aff13c2ec95d9f80c7
identifier.url.fl_str_mv https://hdl.handle.net/1822/99211
instacron_str repositorium
institution Universidade do Minho
instname_str Universidade do Minho
language eng
network_acronym_str rum
network_name_str RepositóriUM - Universidade do Minho
oai_identifier_str oai:repositorium.uminho.pt:1822/99211
organization_str_mv urn:organizationAcronym:repositorium
person_str_mv Azevedo, Marta Vasconcelos Castro
Machado, Luís Meira
Moreira, Carla Maria Gonçalves Macedo
publishDate 2025
publisher.none.fl_str_mv Chilean Statistical Society
reponame_str RepositóriUM - Universidade do Minho
repository_id_str urn:repositoryAcronym:rum
service_str_mv urn:repositoryAcronym:rum
spelling engChilean Statistical SocietyengReliable quantification of treatment benefit in late-phase clinical trials increasingly requires modeling patient histories that include progression, adverse events, and treat ment switches. Conventional multi-state analyses often invoke the Markov property and assume independent right censoring— conditions rarely satisfied in oncology, immunology, or cell-therapy programs, where intermediate events and informative dropout are common. This article presents a systematic review and bibliometric synthesis of 48 peer reviewed studies published through 11 June 2025 that (i) relax the Markov assumption and (ii) address complex observation schemes such as left truncation, interval censoring, or informative censoring, identified through Web of Science and Scopus searches following preferred reporting items for systematic reviews and meta-analyses 2020 guidelines. A recurring set of methodological strategies emerges across the literature, including semi-Markov transition-intensity models, illness–death and semi-competing risks frameworks, landmarking for dynamic prediction, and inverse-probability-of-censoring weighting. Estimation approaches range from nonparametric product integrals to semiparametric weighted likelihoods and Bayesian Markov chain Monte Carlo, with recent contributions exploring saddle-point approximations and subsampling for large-scale electronic health records. To complement this synthesis, we include a compact simulation contrasting baseline and landmark Aalen–Johansen estimators under semi-Markov dynamics with history-dependent censoring, and a bibliometric network analysis mapping collaboration patterns, thematic clusters, and structural gaps. The findings highlight the need for scalable, auditable software, robust diagnostics aligned with the International Council for Harmonization E9(R1) estimand framework (which links clinical trial objectives to precise statistical targets), and better integration of high-dimensional biomarkers; limitations include the English-language restriction and reliance on bibliometric metadata. Addressing these priorities may enhance both the methodological robustness and regulatory applicability of non-Markov survival models.application/pdfengNon-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applicationsAzevedo, Marta Vasconcelos CastroMachado, Luís MeiraMoreira, Carla Maria Gonçalves MacedoHostingInstitutionOrganizationalUniversidade do Minhoe-mailmailto:repositorium@usdb.uminho.ptrepositorium@usdb.uminho.ptISSNIsPartOf0718-7912DOIIsPartOf10.32372/ChJS.16-02-0220252025-01-01T00:00:00ZHandlehttps://hdl.handle.net/1822/99211http://purl.org/coar/access_right/c_abf2open accessHistory-dependent censoringInterval/panel observationLeft truncationNon-Markov inferencePRISMAPseudo-observations1313176 bytesFundação para a Ciência e a Tecnologia, I.P.Center of Mathematics of the University of Minho (UID/00013/2025)Avaliação UID 2023/2024https://hdl.handle.net/1822/98696UID/00013/2025Crossref Funder IDurn:openaire:fct_________::FCTFundação para a Ciência e a Tecnologia, I.P.Complex Time-to-Event Analysis: Multistate Models and Cohort-Based Studies (2023.14897.PEX)Concurso de Projetos Exploratórios em Todos os Domínios Científicos 2023https://hdl.handle.net/1822/992382023.14897.PEXCrossref Funder IDurn:openaire:fct_________::FCTliteraturehttp://purl.org/coar/resource_type/c_6501journal article2025http://creativecommons.org/licenses/by-nc-sa/4.0/openAccesshttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorium.uminho.pt/bitstreams/20c9dd07-6a0b-4ba1-89c0-e0f5da755739/download162125177
spellingShingle Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications
Azevedo, Marta Vasconcelos Castro
History-dependent censoring
Interval/panel observation
Left truncation
Non-Markov inference
PRISMA
Pseudo-observations
status SINGLETON
subject.fl_str_mv History-dependent censoring
Interval/panel observation
Left truncation
Non-Markov inference
PRISMA
Pseudo-observations
title Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications
title_full Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications
title_fullStr Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications
title_full_unstemmed Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications
title_short Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications
title_sort Non-Markov multi-state survival analysis with complex censoring: a structured synthesis of models, estimators, and applications
topic History-dependent censoring
Interval/panel observation
Left truncation
Non-Markov inference
PRISMA
Pseudo-observations
topic_facet History-dependent censoring
Interval/panel observation
Left truncation
Non-Markov inference
PRISMA
Pseudo-observations
url https://hdl.handle.net/1822/99211
visible 1

Atividades financiadas

Carregando projetos financiados...