{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T23:18:43Z","timestamp":1793143123897,"version":"4.5.0"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T00:00:00Z","timestamp":1694476800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"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":[[2023,10]]},"DOI":"10.1016\/j.artmed.2023.102659","type":"journal-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T03:27:40Z","timestamp":1694748460000},"page":"102659","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":25,"special_numbering":"C","title":["An interpretable deep learning model for time-series electronic health records: Case study of delirium prediction in critical care"],"prefix":"10.1016","volume":"144","author":[{"given":"Seyedmostafa","family":"Sheikhalishahi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anirban","family":"Bhattacharyya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leo Anthony","family":"Celi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Venet","family":"Osmani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.artmed.2023.102659_b1","series-title":"Proceedings of the conference on empirical methods in natural language processing. Conference on empirical methods in natural language processing, vol. 2016","first-page":"856","article-title":"Structured prediction models for RNN based sequence labeling in clinical text","author":"Jagannatha","year":"2016"},{"key":"10.1016\/j.artmed.2023.102659_b2","series-title":"2017 International conference on computer, communications and electronics (Comptelix)","first-page":"162","article-title":"Machine translation using deep learning: An overview","author":"Singh","year":"2017"},{"issue":"5","key":"10.1016\/j.artmed.2023.102659_b3","doi-asserted-by":"crossref","first-page":"1589","DOI":"10.1109\/JBHI.2017.2767063","article-title":"Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis","volume":"22","author":"Shickel","year":"2017","journal-title":"IEEE J Biomed Health Inform"},{"issue":"2","key":"10.1016\/j.artmed.2023.102659_b4","doi-asserted-by":"crossref","DOI":"10.2196\/12239","article-title":"Natural language processing of clinical notes on chronic diseases: systematic review","volume":"7","author":"Sheikhalishahi","year":"2019","journal-title":"JMIR Med Inform"},{"issue":"1","key":"10.1016\/j.artmed.2023.102659_b5","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s11747-019-00710-5","article-title":"Explainable AI: from black box to glass box","volume":"48","author":"Rai","year":"2020","journal-title":"J Acad Mark Sci"},{"key":"10.1016\/j.artmed.2023.102659_b6","doi-asserted-by":"crossref","unstructured":"Ahmad MA, Eckert C, Teredesai A. Interpretable machine learning in healthcare. In: Proceedings of the 2018 ACM international conference on bioinformatics, computational biology, and health informatics. 2018, p. 559\u201360.","DOI":"10.1145\/3233547.3233667"},{"key":"10.1016\/j.artmed.2023.102659_b7","series-title":"Understanding and interpreting machine learning in medical image computing applications","first-page":"133","article-title":"Towards complementary explanations using deep neural networks","author":"Silva","year":"2018"},{"issue":"5","key":"10.1016\/j.artmed.2023.102659_b8","doi-asserted-by":"crossref","first-page":"1726","DOI":"10.1016\/j.cor.2008.04.004","article-title":"Polynomial calculation of the Shapley value based on sampling","volume":"36","author":"Castro","year":"2009","journal-title":"Comput Oper Res"},{"key":"10.1016\/j.artmed.2023.102659_b9","series-title":"International conference on machine learning","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"Sundararajan","year":"2017"},{"key":"10.1016\/j.artmed.2023.102659_b10","series-title":"Striving for simplicity: The all convolutional net","author":"Springenberg","year":"2014"},{"issue":"2","key":"10.1016\/j.artmed.2023.102659_b11","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0211057","article-title":"An attention based deep learning model of clinical events in the intensive care unit","volume":"14","author":"Kaji","year":"2019","journal-title":"PLoS One"},{"key":"10.1016\/j.artmed.2023.102659_b12","series-title":"Hybrid self-attention network for machine translation","author":"Song","year":"2018"},{"key":"10.1016\/j.artmed.2023.102659_b13","series-title":"A deep reinforced model for abstractive summarization","author":"Paulus","year":"2017"},{"key":"10.1016\/j.artmed.2023.102659_b14","series-title":"A structured self-attentive sentence embedding","author":"Lin","year":"2017"},{"key":"10.1016\/j.artmed.2023.102659_b15","series-title":"Thirty-second AAAI conference on artificial intelligence","article-title":"Attend and diagnose: Clinical time series analysis using attention models","author":"Song","year":"2018"},{"key":"10.1016\/j.artmed.2023.102659_b16","series-title":"RETAIN: An interpretable predictive model for healthcare using reverse time attention mechanism","author":"Choi","year":"2016"},{"issue":"2","key":"10.1016\/j.artmed.2023.102659_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2020.100196","article-title":"An interpretable deep-learning model for early prediction of sepsis in the emergency department","volume":"2","author":"Zhang","year":"2021","journal-title":"Patterns"},{"key":"10.1016\/j.artmed.2023.102659_b18","series-title":"Advances in neural information processing systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.artmed.2023.102659_b19","series-title":"Effective attention sheds light on interpretability","author":"Sun","year":"2021"},{"issue":"2","key":"10.1016\/j.artmed.2023.102659_b20","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1093\/ageing\/afu173","article-title":"Preventing delirium: should non-pharmacological, multicomponent interventions be used? A systematic review and meta-analysis of the literature","volume":"44","author":"Martinez","year":"2015","journal-title":"Age Ageing"},{"key":"10.1016\/j.artmed.2023.102659_b21","doi-asserted-by":"crossref","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.2023.102659_b22","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data"},{"issue":"2","key":"10.1016\/j.artmed.2023.102659_b23","doi-asserted-by":"crossref","DOI":"10.1093\/jamiaopen\/ooac048","article-title":"Delirium prediction in the ICU: designing a screening tool for preventive interventions","volume":"5","author":"Bhattacharyya","year":"2022","journal-title":"JAMIA Open"},{"issue":"5","key":"10.1016\/j.artmed.2023.102659_b24","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1007\/s001340100909","article-title":"Intensive Care Delirium Screening Checklist: evaluation of a new screening tool","volume":"27","author":"Bergeron","year":"2001","journal-title":"Intensive Care Med"},{"issue":"9","key":"10.1016\/j.artmed.2023.102659_b25","doi-asserted-by":"crossref","first-page":"2196","DOI":"10.1097\/CCM.0b013e31829a6f1e","article-title":"Implementing delirium screening in the intensive care unit: secrets to success","volume":"41","author":"Brummel","year":"2013","journal-title":"Crit Care Med"},{"issue":"1","key":"10.1016\/j.artmed.2023.102659_b26","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1097\/01.ccm.0000619952.70488.fb","article-title":"400: Predicting delirium risk for the following 24 hours in critically ill patients using deep learning","volume":"48","author":"Bhattacharyya","year":"2020","journal-title":"Crit Care Med"},{"key":"10.1016\/j.artmed.2023.102659_b27","series-title":"Benchmarking machine learning models on multi-centre eICU critical care dataset","author":"Sheikhalishahi","year":"2019"},{"key":"10.1016\/j.artmed.2023.102659_b28","series-title":"Entity embeddings of categorical variables","author":"Guo","year":"2016"},{"key":"10.1016\/j.artmed.2023.102659_b29","series-title":"Machine learning applications in Intensive Care Unit","author":"Sheikhalishahi","year":"2022"},{"issue":"5\u20136","key":"10.1016\/j.artmed.2023.102659_b30","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw"},{"key":"10.1016\/j.artmed.2023.102659_b31","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley","year":"2010","journal-title":"J Mach Learn Res"},{"key":"10.1016\/j.artmed.2023.102659_b32","series-title":"On identifiability in transformers","author":"Brunner","year":"2019"},{"key":"10.1016\/j.artmed.2023.102659_b33","series-title":"Benchmarking deep learning interpretability in time series predictions","author":"Ismail","year":"2020"},{"issue":"1","key":"10.1016\/j.artmed.2023.102659_b34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12913-018-3345-x","article-title":"A hospital-wide evaluation of delirium prevalence and outcomes in acute care patients-a cohort study","volume":"18","author":"Schubert","year":"2018","journal-title":"BMC Health Serv Res"},{"key":"10.1016\/j.artmed.2023.102659_b35","series-title":"Explainable artificial intelligence: a systematic review","author":"Vilone","year":"2020"},{"key":"10.1016\/j.artmed.2023.102659_b36","series-title":"2019 IEEE International conference on fuzzy systems (FUZZ-IEEE)","first-page":"1","article-title":"Sepsis prediction: an attention-based interpretable approach","author":"Baghaei","year":"2019"},{"issue":"3","key":"10.1016\/j.artmed.2023.102659_b37","first-page":"1","article-title":"Interpretable clinical prediction via attention-based neural network","volume":"20","author":"Chen","year":"2020","journal-title":"BMC Med Inform Decis Mak"},{"key":"10.1016\/j.artmed.2023.102659_b38","series-title":"AMIA annual symposium proceedings, vol. 2020","first-page":"629","article-title":"A clinically practical and interpretable deep model for ICU mortality prediction with external validation","author":"Kang","year":"2020"},{"key":"10.1016\/j.artmed.2023.102659_b39","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"10.1016\/j.artmed.2023.102659_b40","series-title":"Advances in neural information processing systems 32","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"}],"container-title":["Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365723001732?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365723001732?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T15:18:56Z","timestamp":1760541536000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0933365723001732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":40,"alternative-id":["S0933365723001732"],"URL":"https:\/\/doi.org\/10.1016\/j.artmed.2023.102659","relation":{},"ISSN":["0933-3657"],"issn-type":[{"value":"0933-3657","type":"print"}],"subject":[],"published":{"date-parts":[[2023,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An interpretable deep learning model for time-series electronic health records: Case study of delirium prediction in critical care","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence in Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artmed.2023.102659","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"102659"}}