{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T15:39:47Z","timestamp":1791646787072,"version":"4.3.4"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T00:00:00Z","timestamp":1681430400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>In maintenance hemodialysis patients, intradialytic hypotension (IDH) is a frequent complication that has been associated with poor clinical outcomes. Prediction of IDH may facilitate timely interventions and eventually reduce IDH rates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a machine learning model to predict IDH in in-center hemodialysis patients 15\u201375\u00a0min in advance. IDH was defined as systolic blood pressure (SBP) &amp;lt;90\u00a0mmHg. Demographic, clinical, treatment-related and laboratory data were retrieved from electronic health records and merged with intradialytic machine data that were sent in real-time to the cloud. For model development, dialysis sessions were randomly split into training (80%) and testing (20%) sets. The area under the receiver operating characteristic curve (AUROC) was used as a measure of the model's predictive performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We utilized data from 693 patients who contributed 42\u2009656 hemodialysis sessions and 355\u2009693 intradialytic SBP measurements. IDH occurred in 16.2% of hemodialysis treatments. Our model predicted IDH 15\u201375\u00a0min in advance with an AUROC of 0.89. Top IDH predictors were the most recent intradialytic SBP and IDH rate, as well as mean nadir SBP of the previous 10 dialysis sessions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Real-time prediction of IDH during an ongoing hemodialysis session is feasible and has a clinically actionable predictive performance. If and to what degree this predictive information facilitates the timely deployment of preventive interventions and translates into lower IDH rates and improved patient outcomes warrants prospective studies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ndt\/gfad070","type":"journal-article","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T22:17:11Z","timestamp":1681424231000},"page":"1761-1769","source":"Crossref","is-referenced-by-count":59,"title":["Real-time prediction of intradialytic hypotension using machine learning and cloud computing infrastructure"],"prefix":"10.1093","volume":"38","author":[{"given":"Hanjie","family":"Zhang","sequence":"first","affiliation":[{"name":"Renal Research Institute , New York, NY , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin-Chun","family":"Wang","sequence":"additional","affiliation":[{"name":"Renal Research Institute , New York, NY , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheetal","family":"Chaudhuri","sequence":"additional","affiliation":[{"name":"Fresenius Medical Care, Global Medical Office , Waltham, MA , USA"},{"name":"Maastricht University Medical Center , Maastricht , The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Pickering","sequence":"additional","affiliation":[{"name":"Fresenius Medical Care, Data Solutions , Berlin , Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Len","family":"Usvyat","sequence":"additional","affiliation":[{"name":"Fresenius Medical Care, Global Medical Office , Waltham, MA , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Larkin","sequence":"additional","affiliation":[{"name":"Fresenius Medical Care, Global Medical Office , Waltham, MA , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pete","family":"Waguespack","sequence":"additional","affiliation":[{"name":"Fresenius Medical Care, Digital Technology & Innovation , Waltham, MA , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuwen","family":"Kuang","sequence":"additional","affiliation":[{"name":"Fresenius Medical Care, Digital Technology & Innovation , Waltham, MA , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeroen P","family":"Kooman","sequence":"additional","affiliation":[{"name":"Maastricht University Medical Center , Maastricht , The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franklin W","family":"Maddux","sequence":"additional","affiliation":[{"name":"Fresenius Medical Care, Global Medical Office , Waltham, MA , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Kotanko","sequence":"additional","affiliation":[{"name":"Renal Research Institute , New York, NY , USA"},{"name":"Icahn School of Medicine at Mount Sinai , New York, NY , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"2023063001052242600_bib1","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1016\/j.kint.2021.01.018","article-title":"The time of onset of intradialytic hypotension during a hemodialysis session associates with clinical parameters and mortality","volume":"99","author":"Keane","year":"2021","journal-title":"Kidney Int"},{"key":"2023063001052242600_bib2","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1159\/000500877","article-title":"The prevalence of intradialytic hypotension in patients on conventional hemodialysis: a systematic review with meta-analysis","volume":"49","author":"Kuipers","year":"2019","journal-title":"Am J Nephrol"},{"key":"2023063001052242600_bib3","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1111\/hdi.12138","article-title":"Intradialytic hypotension: frequency, sources of variation and correlation with clinical outcome","volume":"18","author":"Sands","year":"2014","journal-title":"Hemodial Int"},{"key":"2023063001052242600_bib4","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1093\/ckj\/sfaa078","article-title":"An update review of intradialytic hypotension: concept, risk factors, clinical implications and management","volume":"13","author":"Kanbay","year":"2020","journal-title":"Clin Kidney J"},{"key":"2023063001052242600_bib5","doi-asserted-by":"crossref","first-page":"2656","DOI":"10.1093\/ndt\/gfq763","article-title":"Patients\u2019 perspective of haemodialysis-associated symptoms","volume":"26","author":"Caplin","year":"2011","journal-title":"Nephrol Dial Transplant"},{"key":"2023063001052242600_bib6","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1093\/ndt\/gfx037","article-title":"Intradialytic hypotension, blood pressure changes and mortality risk in incident hemodialysis patients","volume":"33","author":"Chou","year":"2018","journal-title":"Nephrol Dial Transplant"},{"key":"2023063001052242600_bib7","doi-asserted-by":"crossref","first-page":"1046","DOI":"10.1046\/j.1523-1755.2002.00505.x","article-title":"Predictors of the rate of decline of residual renal function in incident dialysis patients","volume":"62","author":"Jansen","year":"2002","journal-title":"Kidney Int"},{"key":"2023063001052242600_bib8","doi-asserted-by":"crossref","first-page":"2124","DOI":"10.2215\/CJN.02680314","article-title":"Intradialytic hypotension and risk of cardiovascular disease","volume":"9","author":"Stefansson","year":"2014","journal-title":"Clin J Am Soc Nephrol"},{"key":"2023063001052242600_bib9","doi-asserted-by":"crossref","first-page":"e0185846","DOI":"10.1371\/journal.pone.0185846","article-title":"The relationship between intradialytic hypotension and vascular calcification in hemodialysis patients","volume":"12","author":"Cho","year":"2017","journal-title":"PLoS One"},{"key":"2023063001052242600_bib10","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1097\/MNH.0000000000000271","article-title":"Intradialytic hypotension","volume":"25","author":"Gul","year":"2016","journal-title":"Curr Opin Nephrol Hypertens"},{"key":"2023063001052242600_bib11","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1159\/000493479","article-title":"Development of an artificial intelligence model to guide the management of blood pressure, fluid volume, and dialysis dose in end-stage kidney disease patients: proof of concept and first clinical assessment","volume":"5","author":"Barbieri","year":"2019","journal-title":"Kidney Dis"},{"key":"2023063001052242600_bib12","doi-asserted-by":"crossref","first-page":"396","DOI":"10.2215\/CJN.09280620","article-title":"Deep learning model for real-time prediction of intradialytic hypotension","volume":"16","author":"Lee","year":"2021","journal-title":"Clin J Am Soc Nephrol"},{"key":"2023063001052242600_bib13","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1016\/j.jfma.2018.05.023","article-title":"Intelligent system to predict intradialytic hypotension in chronic hemodialysis","volume":"117","author":"Lin","year":"2018","journal-title":"J Formos Med Assoc"},{"key":"2023063001052242600_bib14","doi-asserted-by":"crossref","first-page":"2833","DOI":"10.3390\/s18092833","article-title":"Artificial-intelligence-based prediction of clinical events among hemodialysis patients using non-contact sensor data","volume":"18","author":"Thakur","year":"2018","journal-title":"Sensors"},{"key":"2023063001052242600_bib15","author":"Amazon","journal-title":"What is AWS"},{"key":"2023063001052242600_bib16","author":"Amazon","journal-title":"AWS HIPAA eligible services"},{"key":"2023063001052242600_bib17","author":"HP Enterprise","journal-title":"Edge device"},{"key":"2023063001052242600_bib18","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1681\/ASN.2014020222","article-title":"Association of mortality risk with various definitions of intradialytic hypotension","volume":"26","author":"Flythe","year":"2015","journal-title":"J Am Soc Nephrol"},{"key":"2023063001052242600_bib19","article-title":"SageMaker","author":"Amazon","year":"2020"},{"key":"2023063001052242600_bib20","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"2023063001052242600_bib21","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/978-3-319-43742-2_29","article-title":"Hyperparameter selection","volume-title":"Secondary analysis of electronic health records","author":"Dernoncourt","year":"2016"},{"key":"2023063001052242600_bib22","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"from local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2023063001052242600_bib23","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023063001052242600_bib24","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1038\/ki.2013.237","article-title":"A comparative effectiveness research study of the change in blood pressure during hemodialysis treatment and survival","volume":"84","author":"Park","year":"2013","journal-title":"Kidney Int"},{"key":"2023063001052242600_bib25","doi-asserted-by":"crossref","first-page":"103271","DOI":"10.1016\/j.jbi.2019.103271","article-title":"Pattern recognition and prognostic analysis of longitudinal blood pressure records in hemodialysis treatment based on a convolutional neural network","volume":"98","author":"Wang","year":"2019","journal-title":"J Biomed Inform"},{"key":"2023063001052242600_bib26","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1186\/s12882-021-02481-0","article-title":"Real-time prediction of intradialytic relative blood volume: a proof-of-concept for integrated cloud computing infrastructure","volume":"22","author":"Chaudhuri","year":"2021","journal-title":"BMC Nephrol"},{"key":"2023063001052242600_bib27","doi-asserted-by":"crossref","first-page":"2075","DOI":"10.1093\/ndt\/gfv316","article-title":"Impact of extracorporeal blood flow rate on blood pressure, pulse rate and cardiac output during haemodialysis","volume":"30","author":"Schytz","year":"2015","journal-title":"Nephrol Dial Transplant"},{"key":"2023063001052242600_bib28","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1111\/sdi.12486","article-title":"We lower blood flow for intradialytic hypotension","volume":"29","author":"Sherman","year":"2016","journal-title":"Semin Dial"},{"key":"2023063001052242600_bib29","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1159\/000355958","article-title":"Dialysis dose and intradialytic hypotension: results from the HEMO study","volume":"38","author":"Mc Causland","year":"2013","journal-title":"Am J Nephrol"}],"container-title":["Nephrology Dialysis Transplantation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ndt\/advance-article-pdf\/doi\/10.1093\/ndt\/gfad070\/50435132\/gfad070.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ndt\/article-pdf\/38\/7\/1761\/50701758\/gfad070.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ndt\/article-pdf\/38\/7\/1761\/50701758\/gfad070.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T21:05:39Z","timestamp":1688072739000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ndt\/article\/38\/7\/1761\/7117966"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,13]]},"references-count":29,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,4,13]]},"published-print":{"date-parts":[[2023,6,30]]}},"URL":"https:\/\/doi.org\/10.1093\/ndt\/gfad070","relation":{},"ISSN":["0931-0509","1460-2385"],"issn-type":[{"value":"0931-0509","type":"print"},{"value":"1460-2385","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,7]]},"published":{"date-parts":[[2023,4,13]]}}}