{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T02:54:23Z","timestamp":1784256863720,"version":"3.55.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T00:00:00Z","timestamp":1603929600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T00:00:00Z","timestamp":1603929600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The broad adoption of electronic health records (EHRs) provides great opportunities to conduct health care research and solve various clinical problems in medicine. With recent advances and success, methods based on machine learning and deep learning have become increasingly popular in medical informatics. However, while many research studies utilize temporal structured data on predictive modeling, they typically neglect potentially valuable information in unstructured clinical notes. Integrating heterogeneous data types across EHRs through deep learning techniques may help improve the performance of prediction models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this research, we proposed 2 general-purpose multi-modal neural network architectures to enhance patient representation learning by combining sequential unstructured notes with structured data. The proposed fusion models leverage document embeddings for the representation of long clinical note documents and either convolutional neural network or long short-term memory networks to model the sequential clinical notes and temporal signals, and one-hot encoding for static information representation. The concatenated representation is the final patient representation which is used to make predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We evaluate the performance of proposed models on 3 risk prediction tasks (i.e. in-hospital mortality, 30-day hospital readmission, and long length of stay prediction) using derived data from the publicly available Medical Information Mart for Intensive Care III dataset. Our results show that by combining unstructured clinical notes with structured data, the proposed models outperform other models that utilize either unstructured notes or structured data only.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed fusion models learn better patient representation by combining structured and unstructured data. Integrating heterogeneous data types across EHRs helps improve the performance of prediction models and reduce errors.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-020-01297-6","type":"journal-article","created":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T10:03:51Z","timestamp":1603965831000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":236,"title":["Combining structured and unstructured data for predictive models: a deep learning approach"],"prefix":"10.1186","volume":"20","author":[{"given":"Dongdong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changchang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jucheng","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4601-0779","authenticated-orcid":false,"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"key":"1297_CR1","first-page":"1","volume":"35","author":"J Henry","year":"2016","unstructured":"Henry J, Pylypchuk Y, Searcy T, Patel V. Adoption of electronic health record systems among US non-federal acute care hospitals: 2008\u20132015. ONC Data Brief. 2016;35:1\u20139.","journal-title":"ONC Data Brief"},{"issue":"7","key":"1297_CR2","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1016\/j.resuscitation.2014.03.302","volume":"85","author":"M Bisbal","year":"2014","unstructured":"Bisbal M, Jouve E, Papazian L, de Bourmont S, Perrin G, Eon B, et al. Effectiveness of SAPS III to predict hospital mortality for post-cardiac arrest patients. Resuscitation. 2014;85(7):939\u201344.","journal-title":"Resuscitation"},{"issue":"5","key":"1297_CR3","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1097\/01.CCM.0000215112.84523.F0","volume":"34","author":"JE Zimmerman","year":"2006","unstructured":"Zimmerman JE, Kramer AA, McNair DS, Malila FM. Acute Physiology and Chronic Health Evaluation (APACHE) IV: hospital mortality assessment for today\u2019s critically ill patients. Crit Care Med. 2006;34(5):1297\u2013310.","journal-title":"Crit Care Med"},{"issue":"6","key":"1297_CR4","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1503\/cmaj.091117","volume":"182","author":"C van Walraven","year":"2010","unstructured":"van Walraven C, Dhalla IA, Bell C, Etchells E, Stiell IG, Zarnke K, et al. Derivation and validation of an index to predict early death or unplanned readmission after discharge from hospital to the community. CMAJ. 2010;182(6):551\u20137.","journal-title":"CMAJ"},{"issue":"8","key":"1297_CR5","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1001\/jamainternmed.2013.3023","volume":"173","author":"J Donz\u00e9","year":"2013","unstructured":"Donz\u00e9 J, Aujesky D, Williams D, Schnipper JL. Potentially avoidable 30-day hospital readmissions in medical patients: derivation and validation of a prediction model. JAMA Internal Med. 2013;173(8):632\u20138.","journal-title":"JAMA Internal Med"},{"key":"1297_CR6","doi-asserted-by":"crossref","unstructured":"Caruana R, Lou Y, Gehrke J, Koch P, Sturm M, Elhadad N. Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. In: Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining. ACM; 2015. p. 1721\u20131730.","DOI":"10.1145\/2783258.2788613"},{"issue":"1","key":"1297_CR7","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1093\/jamiaopen\/ooy011","volume":"1","author":"F Tang","year":"2018","unstructured":"Tang F, Xiao C, Wang F, Zhou J. Predictive modeling in urgent care: a comparative study of machine learning approaches. JAMIA Open. 2018;1(1):87\u201398.","journal-title":"JAMIA Open."},{"issue":"1","key":"1297_CR8","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","volume":"1","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, et al. Scalable and accurate deep learning with electronic health records. NPJ Digital Med. 2018;1(1):18.","journal-title":"NPJ Digital Med."},{"issue":"1","key":"1297_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","volume":"9","author":"X Min","year":"2019","unstructured":"Min X, Yu B, Wang F. Predictive modeling of the hospital readmission risk from patients\u2019 claims data using machine learning: a case study on COPD. Sci Rep. 2019;9(1):1\u201310.","journal-title":"Sci Rep"},{"key":"1297_CR10","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.jbi.2018.04.007","volume":"83","author":"S Purushotham","year":"2018","unstructured":"Purushotham S, Meng C, Che Z, Liu Y. Benchmarking deep learning models on large healthcare datasets. J Biomed Inform. 2018;83:112\u201334.","journal-title":"J Biomed Inform"},{"issue":"1","key":"1297_CR11","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1038\/s41597-019-0103-9","volume":"6","author":"H Harutyunyan","year":"2019","unstructured":"Harutyunyan H, Khachatrian H, Kale DC, Ver Steeg G, Galstyan A. Multitask learning and benchmarking with clinical time series data. Sci Data. 2019;6(1):96.","journal-title":"Sci Data"},{"key":"1297_CR12","unstructured":"Grnarova P, Schmidt F, Hyland SL, Eickhoff C. Neural document embeddings for intensive care patient mortality prediction. arXiv preprint \n                  arXiv:161200467\n                  \n                . 2016."},{"key":"1297_CR13","unstructured":"Ghassemi M, Naumann T, Joshi R, Rumshisky A. Topic models for mortality modeling in intensive care units. In: ICML machine learning for clinical data analysis workshop; 2012. p. 1\u20134."},{"key":"1297_CR14","first-page":"26","volume":"2018","author":"W Boag","year":"2018","unstructured":"Boag W, Doss D, Naumann T, Szolovits P. What\u2019s in a note? Unpacking predictive value in clinical note representations. AMIA Summi Transl Sci Proc. 2018;2018:26.","journal-title":"AMIA Summi Transl Sci Proc"},{"key":"1297_CR15","unstructured":"Liu J, Zhang Z, Razavian N. Deep EHR: chronic disease prediction using medical notes. J Mach Learn Res (JMLR). 2018"},{"key":"1297_CR16","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.jbi.2018.06.016","volume":"84","author":"M Sushil","year":"2018","unstructured":"Sushil M, \u0160uster S, Luyckx K, Daelemans W. Patient representation learning and interpretable evaluation using clinical notes. J Biomed Inform. 2018;84:103\u201313.","journal-title":"J Biomed Inform"},{"key":"1297_CR17","unstructured":"Jin M, Bahadori MT, Colak A, Bhatia P, Celikkaya B, Bhakta R, et al. Improving hospital mortality prediction with medical named entities and multimodal learning. arXiv preprint \n                  arXiv:181112276\n                  \n                . 2018"},{"issue":"7553","key":"1297_CR18","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436\u201344.","journal-title":"Nature"},{"key":"1297_CR19","doi-asserted-by":"crossref","unstructured":"Wan J, Wang D, Hoi SCH, Wu P, Zhu J, Zhang Y, et al. Deep learning for content-based image retrieval: A comprehensive study. In: Proceedings of the 22nd ACM international conference on multimedia. ACM; 2014. p. 157\u2013166.","DOI":"10.1145\/2647868.2654948"},{"key":"1297_CR20","doi-asserted-by":"crossref","unstructured":"Deng L, Hinton G, Kingsbury B. New types of deep neural network learning for speech recognition and related applications: an overview. In: 2013 IEEE international conference on acoustics, speech and signal processing. IEEE; 2013. p. 8599\u20138603.","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"1297_CR21","doi-asserted-by":"crossref","unstructured":"Collobert R, Weston J. A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th international conference on machine learning. ACM; 2008. p. 160\u2013167.","DOI":"10.1145\/1390156.1390177"},{"key":"1297_CR22","doi-asserted-by":"publisher","first-page":"160035","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson AE, Pollard TJ, Shen L, Li-wei HL, Feng M, Ghassemi M, et al. MIMIC-III, a freely accessible critical care database. Sci Data. 2016;3:160035.","journal-title":"Sci Data"},{"key":"1297_CR23","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.jbi.2017.03.009","volume":"68","author":"Z Hu","year":"2017","unstructured":"Hu Z, Melton GB, Arsoniadis EG, Wang Y, Kwaan MR, Simon GJ. Strategies for handling missing clinical data for automated surgical site infection detection from the electronic health record. J Biomed Inform. 2017;68:112\u201320.","journal-title":"J Biomed Inform"},{"key":"1297_CR24","unstructured":"Luo YF, Rumshisky A. Interpretable topic features for post-icu mortality prediction. In: AMIA annual symposium proceedings. vol. 2016. American medical informatics association; 2016. p. 827."},{"issue":"15","key":"1297_CR25","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1001\/jama.2011.1515","volume":"306","author":"D Kansagara","year":"2011","unstructured":"Kansagara D, Englander H, Salanitro A, Kagen D, Theobald C, Freeman M, et al. Risk prediction models for hospital readmission: a systematic review. JAMA. 2011;306(15):1688\u201398.","journal-title":"JAMA"},{"issue":"5","key":"1297_CR26","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1093\/bja\/aen069","volume":"100","author":"AJ Campbell","year":"2008","unstructured":"Campbell AJ, Cook JA, Adey G, Cuthbertson BH. Predicting death and readmission after intensive care discharge. Br J Anaesth. 2008;100(5):656\u201362.","journal-title":"Br J Anaesth"},{"key":"1297_CR27","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.jbi.2015.05.016","volume":"56","author":"J Futoma","year":"2015","unstructured":"Futoma J, Morris J, Lucas J. A comparison of models for predicting early hospital readmissions. J Biomed Inform. 2015;56:229\u201338.","journal-title":"J Biomed Inform"},{"key":"1297_CR28","doi-asserted-by":"crossref","unstructured":"Liu V, Kipnis P, Gould MK, Escobar GJ. Length of stay predictions: improvements through the use of automated laboratory and comorbidity variables. Med Care. 2010; p. 739\u2013744.","DOI":"10.1097\/MLR.0b013e3181e359f3"},{"key":"1297_CR29","volume-title":"Report to the congress: promoting greater efficiency in medicare","author":"G Hackbarth","year":"2007","unstructured":"Hackbarth G, Reischauer R, Miller M. Report to the congress: promoting greater efficiency in medicare. Washington, DC: MedPAC; 2007."},{"key":"1297_CR30","unstructured":"Le Q, Mikolov T. Distributed representations of sentences and documents. In: International conference on machine learning; 2014. p. 1188\u20131196."},{"key":"1297_CR31","unstructured":"Rehurek R, Sojka P. Software framework for topic modelling with large corpora. In: In Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks. Citeseer; 2010."},{"issue":"Oct","key":"1297_CR32","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12(Oct):2825\u201330.","journal-title":"J Mach Learn Res"},{"key":"1297_CR33","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. PyTorch: An imperative style, high-performance deep learning library. In: Advances in neural information processing systems; 2019. p. 8024\u20138035."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01297-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12911-020-01297-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01297-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T11:05:57Z","timestamp":1604228757000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-020-01297-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,29]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["1297"],"URL":"https:\/\/doi.org\/10.1186\/s12911-020-01297-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.08.10.20172122","asserted-by":"object"}]},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,29]]},"assertion":[{"value":"4 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Research use of MIMIC-III has been approved by the Institutional Review Board of Beth Israel Deaconess Medical Center and Massachusetts Institute of Technology [\n                      \n                      ].","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"PZ is the member of the editorial board of BMC Medical Informatics and Decision Making. The authors declare that they have no other competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"280"}}