{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T14:13:46Z","timestamp":1776176026927,"version":"3.50.1"},"reference-count":69,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010676","name":"Horizon 2020 Societal Challenges","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010676","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Foundation for Science and Technology","doi-asserted-by":"publisher","award":["PTDC\/CCI-CIF\/4613\/2020"],"award-info":[{"award-number":["PTDC\/CCI-CIF\/4613\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence in Medicine"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.artmed.2026.103392","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T17:02:28Z","timestamp":1772557348000},"page":"103392","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["PatientFlow: Learning to generate mixed-type longitudinal clinical data with flow matching"],"prefix":"10.1016","volume":"176","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8126-8513","authenticated-orcid":false,"given":"Ruben","family":"Branco","sequence":"first","affiliation":[]},{"given":"Marta","family":"Gromicho","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7556-0158","authenticated-orcid":false,"given":"Mamede","family":"de Carvalho","sequence":"additional","affiliation":[]},{"given":"Piero","family":"Fariselli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1459-8096","authenticated-orcid":false,"given":"Sara","family":"C. Madeira","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.artmed.2026.103392_b1","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41551-021-00751-8","article-title":"Synthetic data in machine learning for medicine and healthcare","volume":"5","author":"Chen","year":"2021","journal-title":"Nat Biomed Eng"},{"key":"10.1016\/j.artmed.2026.103392_b2","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2021.747612","article-title":"Opportunities and challenges for machine learning in rare diseases","volume":"8","author":"Decherchi","year":"2021","journal-title":"Front Med"},{"issue":"3","key":"10.1016\/j.artmed.2026.103392_b3","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1093\/jamia\/ocy142","article-title":"Synthesizing electronic health records using improved generative adversarial networks","volume":"26","author":"Baowaly","year":"2019","journal-title":"J Am Med Informatics Assoc"},{"key":"10.1016\/j.artmed.2026.103392_b4","series-title":"Machine learning for healthcare conference","first-page":"286","article-title":"Generating multi-label discrete patient records using generative adversarial networks","author":"Choi","year":"2017"},{"issue":"1","key":"10.1016\/j.artmed.2026.103392_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01784-7","article-title":"The Health Gym: Synthetic health-related datasets for the development of reinforcement learning algorithms","volume":"9","author":"Kuo","year":"2022","journal-title":"Sci Data"},{"issue":"1","key":"10.1016\/j.artmed.2026.103392_b6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-023-00834-7","article-title":"Generating synthetic mixed-type longitudinal electronic health records for artificial intelligent applications","volume":"6","author":"Li","year":"2023","journal-title":"Npj Digit Med"},{"issue":"1","key":"10.1016\/j.artmed.2026.103392_b7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU collaborative research database, a freely available multi-center database for critical care research","volume":"5","author":"Pollard","year":"2018","journal-title":"Sci Data"},{"key":"10.1016\/j.artmed.2026.103392_b8","series-title":"Generative adversarial networks for electronic health records: A framework for exploring and evaluating methods for predicting drug-induced laboratory test trajectories","author":"Yahi","year":"2017"},{"key":"10.1016\/j.artmed.2026.103392_b9","series-title":"MedDiff: Generating electronic health records using accelerated denoising diffusion model","author":"He","year":"2023"},{"key":"10.1016\/j.artmed.2026.103392_b10","article-title":"EHRDiff : Exploring realistic EHR synthesis with diffusion models","author":"Yuan","year":"2024","journal-title":"Trans Mach Learn Res"},{"key":"10.1016\/j.artmed.2026.103392_b11","series-title":"The eleventh international conference on learning representations","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023"},{"key":"10.1016\/j.artmed.2026.103392_b12","series-title":"The thirty-eighth annual conference on neural information processing systems","article-title":"Trajectory flow matching with applications to clinical time series modelling","author":"Zhang","year":"2024"},{"key":"10.1016\/j.artmed.2026.103392_b13","series-title":"Sequential models in the synthetic data vault","author":"Zhang","year":"2022"},{"key":"10.1016\/j.artmed.2026.103392_b14","series-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"issue":"5786","key":"10.1016\/j.artmed.2026.103392_b15","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"10.1016\/j.artmed.2026.103392_b16","series-title":"2019 international conference of artificial intelligence and information technology","first-page":"1","article-title":"A comparative study on variational autoencoders and generative adversarial networks","author":"Sami","year":"2019"},{"key":"10.1016\/j.artmed.2026.103392_b17","series-title":"International conference on learning representations","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021"},{"key":"10.1016\/j.artmed.2026.103392_b18","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","year":"2024","journal-title":"Trans Mach Learn Res"},{"key":"10.1016\/j.artmed.2026.103392_b19","series-title":"Generative adversarial networks","author":"Goodfellow","year":"2014"},{"key":"10.1016\/j.artmed.2026.103392_b20","article-title":"Generative adversarial network in medical imaging: A review","volume":"58","author":"Yi","year":"2018","journal-title":"Med Image Anal"},{"key":"10.1016\/j.artmed.2026.103392_b21","series-title":"International conference on machine learning","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"Arjovsky","year":"2017"},{"key":"10.1016\/j.artmed.2026.103392_b22","series-title":"International conference on learning representations","article-title":"Boundary seeking GANs","author":"Hjelm","year":"2018"},{"issue":"1","key":"10.1016\/j.artmed.2026.103392_b23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12874-020-00977-1","article-title":"Generation and evaluation of synthetic patient data","volume":"20","author":"Goncalves","year":"2020","journal-title":"BMC Med Res Methodol"},{"key":"10.1016\/j.artmed.2026.103392_b24","series-title":"2017 IEEE international conference on data mining","first-page":"787","article-title":"Boosting deep learning risk prediction with generative adversarial networks for electronic health records","author":"Che","year":"2017"},{"key":"10.1016\/j.artmed.2026.103392_b25","series-title":"Proceedings of the 27th international conference on artificial intelligence and statistics","first-page":"1288","article-title":"Generating and imputing tabular data via diffusion and flow-based gradient-boosted trees","volume":"vol. 238","author":"Jolicoeur-Martineau","year":"2024"},{"key":"10.1016\/j.artmed.2026.103392_b26","series-title":"Generating tabular data using heterogeneous sequential feature forest flow matching","author":"Akazan","year":"2024"},{"key":"10.1016\/j.artmed.2026.103392_b27","first-page":"11735","article-title":"Variational flow matching for graph generation","volume":"37","author":"Eijkelboom","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2026.103392_b28","series-title":"Forty-second international conference on machine learning","article-title":"Exponential family variational flow matching for tabular data generation","author":"Guzm\u00e1n-Cordero","year":"2025"},{"key":"10.1016\/j.artmed.2026.103392_b29","series-title":"Timevae: A variational auto-encoder for multivariate time series generation","author":"Desai","year":"2021"},{"key":"10.1016\/j.artmed.2026.103392_b30","article-title":"Time-series generative adversarial networks","volume":"32","author":"Yoon","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2026.103392_b31","series-title":"Generating high-fidelity, synthetic time series datasets with doppelganger","author":"Lin","year":"2019"},{"key":"10.1016\/j.artmed.2026.103392_b32","series-title":"The twelfth international conference on learning representations","article-title":"Diffusion-TS: Interpretable diffusion for general time series generation","author":"Yuan","year":"2024"},{"key":"10.1016\/j.artmed.2026.103392_b33","series-title":"International conference on learning representations","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2021"},{"key":"10.1016\/j.artmed.2026.103392_b34","series-title":"Thirty-seventh conference on neural information processing systems","article-title":"On the constrained time-series generation problem","author":"Coletta","year":"2023"},{"key":"10.1016\/j.artmed.2026.103392_b35","series-title":"TimeAutoDiff: Combining autoencoder and diffusion model for time series tabular data synthesizing","author":"Suh","year":"2024"},{"key":"10.1016\/j.artmed.2026.103392_b36","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2026.103392_b37","series-title":"ICML 2024 workshop on structured probabilistic inference & generative modeling","article-title":"Conditional flow matching for time series modelling","author":"Tamir","year":"2024"},{"key":"10.1016\/j.artmed.2026.103392_b38","series-title":"FlowTS: Time series generation via rectified flow","author":"Hu","year":"2024"},{"key":"10.1016\/j.artmed.2026.103392_b39","series-title":"The eleventh international conference on learning representations","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2023"},{"key":"10.1016\/j.artmed.2026.103392_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127063","article-title":"Roformer: Enhanced transformer with rotary position embedding","volume":"568","author":"Su","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.artmed.2026.103392_b41","series-title":"Real-valued (medical) time series generation with recurrent conditional gans","author":"Esteban","year":"2017"},{"key":"10.1016\/j.artmed.2026.103392_b42","series-title":"Heterogeneous data management, polystores, and analytics for healthcare: VLDB workshops, poly 2021 and DMAH 2021, virtual event, August 20, 2021, revised selected papers 7","first-page":"153","article-title":"Generating longitudinal synthetic ehr data with recurrent autoencoders and generative adversarial networks","author":"Sun","year":"2021"},{"key":"10.1016\/j.artmed.2026.103392_b43","series-title":"NeurIPS 2023 workshop on synthetic data generation with generative AI","article-title":"Synthetic health-related longitudinal data with mixed-type variables generated using diffusion models","author":"Kuo","year":"2023"},{"key":"10.1016\/j.artmed.2026.103392_b44","series-title":"Proceedings of the 24th international conference on artificial intelligence and statistics","first-page":"3898","article-title":"Longitudinal variational autoencoder","volume":"vol. 130","author":"Ramchandran","year":"2021"},{"issue":"1","key":"10.1016\/j.artmed.2026.103392_b45","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1186\/s12874-023-01869-w","article-title":"A method for generating synthetic longitudinal health data","volume":"23","author":"Mosquera","year":"2023","journal-title":"BMC Med Res Methodol"},{"issue":"1","key":"10.1016\/j.artmed.2026.103392_b46","doi-asserted-by":"crossref","first-page":"14412","DOI":"10.1038\/s41598-024-62102-2","article-title":"Synthetic data generation for a longitudinal cohort study\u2013evaluation, method extension and reproduction of published data analysis results","volume":"14","author":"K\u00fchnel","year":"2024","journal-title":"Sci Rep"},{"key":"10.1016\/j.artmed.2026.103392_b47","doi-asserted-by":"crossref","first-page":"16","DOI":"10.3389\/fdata.2020.00016","article-title":"Variational autoencoder modular Bayesian networks for simulation of heterogeneous clinical study data","volume":"3","author":"Gootjes-Dreesbach","year":"2020","journal-title":"Front Big Data"},{"key":"10.1016\/j.artmed.2026.103392_b48","doi-asserted-by":"crossref","DOI":"10.1177\/1756286419857040","article-title":"Non-invasive ventilation in amyotrophic lateral sclerosis","volume":"12","author":"Dorst","year":"2019","journal-title":"Ther Adv Neurol Disord"},{"issue":"1\u20132","key":"10.1016\/j.artmed.2026.103392_b49","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/S0022-510X(99)00210-5","article-title":"The ALSFRS-R: A revised ALS functional rating scale that incorporates assessments of respiratory function","volume":"169","author":"Cedarbaum","year":"1999","journal-title":"J Neurol Sci"},{"key":"10.1016\/j.artmed.2026.103392_b50","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.jbi.2015.09.021","article-title":"Prognostic models based on patient snapshots and time windows: Predicting disease progression to assisted ventilation in amyotrophic lateral sclerosis","volume":"58","author":"Carreiro","year":"2015","journal-title":"J Biomed Informatics"},{"issue":"1","key":"10.1016\/j.artmed.2026.103392_b51","doi-asserted-by":"crossref","first-page":"6182","DOI":"10.1038\/s41598-023-33223-x","article-title":"Triclustering-based classification of longitudinal data for prognostic prediction: Targeting relevant clinical endpoints in amyotrophic lateral sclerosis","volume":"13","author":"Soares","year":"2023","journal-title":"Sci Rep"},{"key":"10.1016\/j.artmed.2026.103392_b52","series-title":"Forty-first international conference on machine learning","article-title":"Dirichlet flow matching with applications to DNA sequence design","author":"Stark","year":"2024"},{"key":"10.1016\/j.artmed.2026.103392_b53","series-title":"Flow matching in latent space","author":"Dao","year":"2023"},{"issue":"6","key":"10.1016\/j.artmed.2026.103392_b54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10994-025-06778-1","article-title":"One transformer for all time series: Representing and training with time-dependent heterogeneous tabular data","volume":"114","author":"Luetto","year":"2025","journal-title":"Mach Learn"},{"key":"10.1016\/j.artmed.2026.103392_b55","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2026.103392_b56","series-title":"Proceedings of the 2015 conference on empirical methods in natural language processing","first-page":"1412","article-title":"Effective approaches to attention-based neural machine translation","author":"Luong","year":"2015"},{"key":"10.1016\/j.artmed.2026.103392_b57","first-page":"24804","article-title":"Csdi: Conditional score-based diffusion models for probabilistic time series imputation","volume":"34","author":"Tashiro","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2026.103392_b58","series-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"10.1016\/j.artmed.2026.103392_b59","series-title":"Torchdiffeq","author":"Chen","year":"2018"},{"key":"10.1016\/j.artmed.2026.103392_b60","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1214\/aoms\/1177728190","article-title":"Remarks on some nonparametric estimates of a density function","author":"Rosenblatt","year":"1956","journal-title":"Ann Math Stat"},{"issue":"3","key":"10.1016\/j.artmed.2026.103392_b61","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1214\/aoms\/1177704472","article-title":"On estimation of a probability density function and mode","volume":"33","author":"Parzen","year":"1962","journal-title":"Ann Math Stat"},{"key":"10.1016\/j.artmed.2026.103392_b62","volume":"vol. 43","author":"Cram\u00e9r","year":"1999"},{"issue":"3","key":"10.1016\/j.artmed.2026.103392_b63","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1111\/j.1751-5823.2002.tb00178.x","article-title":"On choosing and bounding probability metrics","volume":"70","author":"Gibbs","year":"2002","journal-title":"Int Stat Rev"},{"key":"10.1016\/j.artmed.2026.103392_b64","series-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"issue":"11","key":"10.1016\/j.artmed.2026.103392_b65","doi-asserted-by":"crossref","DOI":"10.2196\/23139","article-title":"Evaluating identity disclosure risk in fully synthetic health data: model development and validation","volume":"22","author":"El Emam","year":"2020","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.artmed.2026.103392_b66","series-title":"External guidance on the implementation of the European medicines agency policy on the publication of clinical data for medicinal products for human use","author":"European Medicines Agency","year":"2018"},{"key":"10.1016\/j.artmed.2026.103392_b67","series-title":"Guidance document on public release of clinical information","author":"Canada","year":"2019"},{"key":"10.1016\/j.artmed.2026.103392_b68","series-title":"International conference on learning representations","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"Higgins","year":"2017"},{"key":"10.1016\/j.artmed.2026.103392_b69","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"container-title":["Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365726000448?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365726000448?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T13:38:31Z","timestamp":1776173911000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0933365726000448"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":69,"alternative-id":["S0933365726000448"],"URL":"https:\/\/doi.org\/10.1016\/j.artmed.2026.103392","relation":{},"ISSN":["0933-3657"],"issn-type":[{"value":"0933-3657","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PatientFlow: Learning to generate mixed-type longitudinal clinical data with flow matching","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence in Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artmed.2026.103392","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103392"}}