{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:09:01Z","timestamp":1791911341478,"version":"4.3.4"},"reference-count":27,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"10","content-domain":{"domain":["www.ahajournals.org"],"crossmark-restriction":true},"short-container-title":["Circ: Cardiovascular Quality and Outcomes"],"published-print":{"date-parts":[[2019,10]]},"abstract":"<jats:sec>\n            <jats:title>Background:<\/jats:title>\n            <jats:p>We determined the impact of data volume and diversity and training conditions on recurrent neural network methods compared with traditional machine learning methods.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods and Results:<\/jats:title>\n            <jats:p>Using longitudinal electronic health record data, we assessed the relative performance of machine learning models trained to detect a future diagnosis of heart failure in primary care patients. Model performance was assessed in relation to data parameters defined by the combination of different data domains (data diversity), the number of patient records in the training data set (data quantity), the number of encounters per patient (data density), the prediction window length, and the observation window length (ie, the time period before the prediction window that is the source of features for prediction). Data on 4370 incident heart failure cases and 30\u2009132 group-matched controls were used. Recurrent neural network model performance was superior under a variety of conditions that included (1) when data were less diverse (eg, a single data domain like medication or vital signs) given the same training size; (2) as data quantity increased; (3) as density increased; (4) as the observation window length increased; and (5) as the prediction window length decreased. When all data domains were used, the performance of recurrent neural network models increased in relation to the quantity of data used (ie, up to 100% of the data). When data are sparse (ie, fewer features or low dimension), model performance is lower, but a much smaller training set size is required to achieve optimal performance compared with conditions where data are more diverse and includes more features.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions:<\/jats:title>\n            <jats:p>Recurrent neural networks are effective for predicting a future diagnosis of heart failure given sufficient training set size. Model performance appears to continue to improve in direct relation to training set size.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1161\/circoutcomes.118.005114","type":"journal-article","created":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T09:00:59Z","timestamp":1571130059000},"update-policy":"https:\/\/doi.org\/10.1161\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":66,"title":["Recurrent Neural Networks for Early Detection of Heart Failure From Longitudinal Electronic Health Record Data"],"prefix":"10.1161","volume":"12","author":[{"given":"Robert","family":"Chen","sequence":"first","affiliation":[{"name":"Research, Sutter Health Research, Walnut Creek, CA (R.C., X.Y.)."},{"name":"School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, (R.C., J.S.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Walter F.","family":"Stewart","sequence":"additional","affiliation":[{"name":"Step2Works, Orinda, CA (W.F.S.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jimeng","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, (R.C., J.S.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenney","family":"Ng","sequence":"additional","affiliation":[{"name":"Center for Computational Health, IBM Research, T.J. Watson Research Center, Yorktown Heights, NY (K.N.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Yan","sequence":"additional","affiliation":[{"name":"Research, Sutter Health Research, Walnut Creek, CA (R.C., X.Y.)."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hfc.2014.04.008"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.114.010637"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.09.006"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCHEARTFAILURE.112.000043"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1097\/MLR.0b013e3181de9e17"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.116.002797"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.17294\/2330-0698.1344"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2014.07.009"},{"key":"e_1_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Pakbin A Rafi P Hurley N Schulz W Krumholz MH Mortazavi JB. Prediction of ICU readmissions using data at patient discharge. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Honolulu HI; 2018.","DOI":"10.1109\/EMBC.2018.8513181"},{"key":"e_1_3_3_11_2","unstructured":"Feng Z Mo L Li M. A random forest-based ensemble method for activity recognition. In: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Milan Italy; 2015."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.2196\/11201"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocw112"},{"key":"e_1_3_3_14_2","unstructured":"Choi E Bahadori MT Kulas JA Schuetz A Stewart WF Sun J. RETAIN: an interpretable predictive model for healthcare using reverse time attention mechanism. In Proc. of Neural Information Processing Systems (NIPS); Barcelona Spain. 2016:3504\u20133512."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjmed.2012.10.022"},{"key":"e_1_3_3_16_2","first-page":"33","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop CM","year":"2006","unstructured":"Bishop, CM. Pattern Recognition and Machine Learning. New York, NY: Springer Science + Business Media; 2006:33."},{"key":"e_1_3_3_17_2","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso.","volume":"58","author":"Tibshirani R","year":"1994","unstructured":"Tibshirani, R. Regression shrinkage and selection via the lasso. J R Stat Soc Ser B. 1994;58:267\u2013288.","journal-title":"J R Stat Soc Ser B"},{"key":"e_1_3_3_18_2","first-page":"2825","article-title":"Scikit-learn: machine learning in python.","volume":"12","author":"Pedregosa F","year":"2011","unstructured":"Pedregosa, F, Varoquaux, G, Gramfort, A, Michel, V, Thirion, B, Grisel, O, Blondel, M, Prettenhofer, P, Weiss, R, Dubourg, V, Vanderplas, J. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12:2825\u20132830.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_3_19_2","first-page":"5","volume-title":"Machine learning","author":"Breiman L","year":"2001","unstructured":"Breiman, L. Random forests. Machine learning. 2001;45:5\u201332."},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0895-4356(96)00236-3"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwk052"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-218X(98)00014-6"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.8960"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4067"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2013-002162"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_3_27_2","unstructured":"Pardoe D Stone P. Boosting for Regression Transfer. In: Proceedings of the 27th International Conference on International Conference on Machine Learning (ICML\u201910).Haifa Israel: Omnipress; 2010:863\u2013870."},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-014-0389-3"}],"container-title":["Circulation: Cardiovascular Quality and Outcomes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ahajournals.org\/doi\/full\/10.1161\/CIRCOUTCOMES.118.005114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T03:28:55Z","timestamp":1715570935000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ahajournals.org\/doi\/10.1161\/CIRCOUTCOMES.118.005114"}},"subtitle":["Implications for Temporal Modeling With Respect to Time Before Diagnosis, Data Density, Data Quantity, and Data Type"],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":27,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["10.1161\/CIRCOUTCOMES.118.005114"],"URL":"https:\/\/doi.org\/10.1161\/circoutcomes.118.005114","relation":{},"ISSN":["1941-7713","1941-7705"],"issn-type":[{"value":"1941-7713","type":"print"},{"value":"1941-7705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10]]},"assertion":[{"value":"2019-08-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-08-30","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e005114"}}