{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T20:58:27Z","timestamp":1761253107058,"version":"3.37.3"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"3","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ACI-1544628"],"award-info":[{"award-number":["ACI-1544628"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Library of Medicine Biomedical Informatics Research Training","award":["NIH\/NLM 2T15 LM007092-22"],"award-info":[{"award-number":["NIH\/NLM 2T15 LM007092-22"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,5,1]]},"abstract":"<jats:p>Background: The widespread adoption of electronic health records allows us to ask evidence-based questions about the need for and benefits of specific clinical interventions in critical-care settings across large populations.<\/jats:p><jats:p>Objective: We investigated the prediction of vasopressor administration and weaning in the intensive care unit. Vasopressors are commonly used to control hypotension, and changes in timing and dosage can have a large impact on patient outcomes.<\/jats:p><jats:p>Materials and Methods: We considered a cohort of 15\u2009695 intensive care unit patients without orders for reduced care who were alive 30 days post-discharge. A switching-state autoregressive model (SSAM) was trained to predict the multidimensional physiological time series of patients before, during, and after vasopressor administration. The latent states from the SSAM were used as predictors of vasopressor administration and weaning.<\/jats:p><jats:p>Results: The unsupervised SSAM features were able to predict patient vasopressor administration and successful patient weaning. Features derived from the SSAM achieved areas under the receiver operating curve of 0.92, 0.88, and 0.71 for predicting ungapped vasopressor administration, gapped vasopressor administration, and vasopressor weaning, respectively. We also demonstrated many cases where our model predicted weaning well in advance of a successful wean.<\/jats:p><jats:p>Conclusion: Models that used SSAM features increased performance on both predictive tasks. These improvements may reflect an underlying, and ultimately predictive, latent state detectable from the physiological time series.<\/jats:p>","DOI":"10.1093\/jamia\/ocw138","type":"journal-article","created":{"date-parts":[[2016,10,6]],"date-time":"2016-10-06T01:49:54Z","timestamp":1475718594000},"page":"488-495","source":"Crossref","is-referenced-by-count":34,"title":["Understanding vasopressor intervention and weaning: risk prediction in a public heterogeneous clinical time series database"],"prefix":"10.1093","volume":"24","author":[{"given":"Mike","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Yale University, New Haven, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marzyeh","family":"Ghassemi","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengling","family":"Feng","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leo A","family":"Celi","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Szolovits","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Finale","family":"Doshi-Velez","sequence":"additional","affiliation":[{"name":"Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2016,10,5]]},"reference":[{"key":"2020110620012402100_ocw138-B1","doi-asserted-by":"crossref","first-page":"S2","DOI":"10.1186\/cc11500","article-title":"Critical care: where have we been and where are we going?","volume":"17","author":"Vincent","year":"2013","journal-title":"Crit Care."},{"key":"2020110620012402100_ocw138-B2","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1016\/S0140-6736(10)60575-2","article-title":"Critical care: advances and future perspectives","volume":"376","author":"Vincent","year":"2010","journal-title":"Lancet."},{"key":"2020110620012402100_ocw138-B3","doi-asserted-by":"crossref","first-page":"1311","DOI":"10.1097\/CCM.0b013e318168ea3e","article-title":"Multicenter, randomized controlled trials evaluating mortality in intensive care: doomed to fail?","volume":"36","author":"Ospina-Tasc\u00f3n","year":"2008","journal-title":"Crit Care Med."},{"key":"2020110620012402100_ocw138-B4","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1097\/CCM.0b013e31820a92c6","article-title":"Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II): a public-access intensive care unit database","volume":"39","author":"Saeed","year":"2011","journal-title":"Crit Care Med."},{"key":"2020110620012402100_ocw138-B5","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1145\/2783258.2783365","article-title":"Deep Computational Phenotyping","volume-title":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Che","year":"2015"},{"key":"2020110620012402100_ocw138-B6","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1145\/2783258.2783289","article-title":"Dynamically modeling patient\u2019s health state from electronic medical records: a time series approach","volume-title":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Caballero Barajas","year":"2015"},{"key":"2020110620012402100_ocw138-B7","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1145\/2623330.2623742","article-title":"Unfolding physiological state: Mortality modelling in intensive care units","volume-title":"Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Ghassemi","year":"2014"},{"key":"2020110620012402100_ocw138-B8","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1093\/jamia\/ocv024","article-title":"Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis","volume":"22","author":"Perotte","year":"2015","journal-title":"J Am Med Inform Assoc."},{"key":"2020110620012402100_ocw138-B9","article-title":"Vasopressors for shock","author":"M\u00fcllner","year":"2004","journal-title":"The Cochrane Library"},{"key":"2020110620012402100_ocw138-B10","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1097\/SHK.0000000000000348","article-title":"Blood pressure targets for vasopressor therapy: a systematic review","volume":"43","author":"D\u2019Aragon","year":"2015","journal-title":"Shock."},{"key":"2020110620012402100_ocw138-B11","doi-asserted-by":"crossref","first-page":"e66341","DOI":"10.1371\/journal.pone.0066341","article-title":"Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data","volume":"8","author":"Lasko","year":"2013","journal-title":"PLoS One."},{"key":"2020110620012402100_ocw138-B12","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1145\/2110363.2110408","article-title":"Unsupervised pattern discovery in electronic health care data using probabilistic clustering models","volume-title":"Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium.","author":"Marlin","year":"2012"},{"key":"2020110620012402100_ocw138-B13","first-page":"261","article-title":"Healthcare data mining: predicting inpatient length of stay","volume-title":"The Proceedings of the 3rd International IEEE Conference on Intelligent Systems","author":"Liu","year":"2006"},{"key":"2020110620012402100_ocw138-B14","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/1471-2288-10-7","article-title":"Comparison of techniques for handling missing covariate data within prognostic modelling studies: a simulation study","volume":"10","author":"Marshall","year":"2010","journal-title":"BMC Med Res Methodol."},{"key":"2020110620012402100_ocw138-B15","first-page":"253","article-title":"An imputation-enhanced algorithm for ICU mortality prediction","volume-title":"2012 Computing in Cardiology","author":"Lee","year":"2012"},{"key":"2020110620012402100_ocw138-B16","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1016\/j.jclinepi.2009.12.008","article-title":"Missing covariate data in medical research: to impute is better than to ignore","volume":"63","author":"Janssen","year":"2010","journal-title":"J Clin Epidemiol."},{"key":"2020110620012402100_ocw138-B17","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1109\/JBHI.2014.2330827","article-title":"A physiological time series dynamics-based approach to patient monitoring and outcome prediction","volume":"19","author":"Lehman","year":"2015","journal-title":"IEEE J Biomed Heal Informatics."},{"key":"2020110620012402100_ocw138-B18","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1109\/TPAMI.2008.191","article-title":"Factorial switching linear dynamical systems applied to physiological condition monitoring","volume":"31","author":"Quinn","year":"2009","journal-title":"Pattern Anal Mach Intell IEEE Trans."},{"key":"2020110620012402100_ocw138-B19","first-page":"1276","article-title":"Prognostic physiology: modeling patient severity in intensive care units using radial domain folding","volume-title":"AMIA Annual Symposium Proceedings","author":"Joshi","year":"2012"},{"key":"2020110620012402100_ocw138-B20","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9209","article-title":"A multivariate timeseries modeling approach to severity of illness assessment and forecasting in ICU with sparse, heterogeneous clinical data","volume-title":"Proceedings of the\u2026 AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","author":"Ghassemi"},{"key":"2020110620012402100_ocw138-B21","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1097\/00003246-198411000-00012","article-title":"A simplified acute physiology score for ICU patients","volume":"12","author":"Le Gall","year":"1984","journal-title":"Crit Care Med."},{"key":"2020110620012402100_ocw138-B22","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1007\/BF01709751","article-title":"The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction\/failure","volume":"22","author":"Vincent","year":"1996","journal-title":"Intensive Care Med."},{"key":"2020110620012402100_ocw138-B23","first-page":"260","article-title":"ICU acuity: real-time models versus daily models","volume":"2009","author":"Hug","year":"2009","journal-title":"AMIA Annu Symp Proc."},{"key":"2020110620012402100_ocw138-B24","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1186\/1475-925X-9-62","article-title":"An investigation of patterns in hemodynamic data indicative of impending hypotension in intensive care","volume":"9","author":"Lee","year":"2010","journal-title":"Biomed Eng Online."},{"key":"2020110620012402100_ocw138-B25","first-page":"999","article-title":"Unsupervised similarity-based risk stratification for cardiovascular events using long-term time-series data","volume":"12","author":"Syed","year":"2011","journal-title":"J Mach Learn Res."},{"key":"2020110620012402100_ocw138-B26","first-page":"679","article-title":"A novel method for the efficient retrieval of similar multiparameter physiologic time series using wavelet-based symbolic representations","volume-title":"AMIA\u2026 Annual Symposium proceedings\/AMIA Symposium. AMIA Symposium.","author":"Saeed","year":"2005"},{"key":"2020110620012402100_ocw138-B27","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s10618-007-0064-z","article-title":"Experiencing SAX: a novel symbolic representation of time series","volume":"15","author":"Lin","year":"2007","journal-title":"Data Min Knowl Discov."},{"key":"2020110620012402100_ocw138-B28","doi-asserted-by":"crossref","first-page":"494","DOI":"10.3414\/ME12-01-0093","article-title":"Disease-based modeling to predict fluid response in intensive care units","volume":"52","author":"Fialho","year":"2013","journal-title":"Methods Inf Med."},{"key":"2020110620012402100_ocw138-B29","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1056\/NEJMoa0907118","article-title":"Comparison of dopamine and norepinephrine in the treatment of shock","volume":"362","author":"De Backer","year":"2010","journal-title":"N Engl J Med."},{"key":"2020110620012402100_ocw138-B30","doi-asserted-by":"crossref","DOI":"10.1126\/scitranslmed.aab3719","article-title":"A targeted real-time early warning score (TREWScore) for septic shock","volume":"7","author":"Henry","year":"2015","journal-title":"Sci Transl Med."},{"key":"2020110620012402100_ocw138-B31","first-page":"324","article-title":"A prospective study of indexes predicting the outcome of trials of weaning from mechanical ventilation","author":"Yang","year":"1991","journal-title":"N Engl J Med"},{"article-title":"Principles and practice of mechanical ventilation","year":"2006","author":"Tobin","key":"2020110620012402100_ocw138-B32"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/24\/3\/488\/34148222\/ocw138.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/24\/3\/488\/34148222\/ocw138.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T20:25:22Z","timestamp":1657398322000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/24\/3\/488\/2907906"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,5]]},"references-count":32,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2016,10,5]]},"published-print":{"date-parts":[[2017,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocw138","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"type":"print","value":"1067-5027"},{"type":"electronic","value":"1527-974X"}],"subject":[],"published-other":{"date-parts":[[2017,5]]},"published":{"date-parts":[[2016,10,5]]}}}