{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T23:45:15Z","timestamp":1793663115190,"version":"4.5.1"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["IITP-2024-RS-2024-00441407"],"award-info":[{"award-number":["IITP-2024-RS-2024-00441407"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Real-time prediction of intradialytic hypotension (IDH) using deep learning has shown high accuracy; however, existing models typically treat all IDH events equally, without distinguishing between initial and recurrent occurrences within a dialysis session. This conventional approach neglects the distinct underlying physiological mechanisms and clinical intervention requirements of each occurrence type. This study aimed to systematically examine IDH recurrence patterns to evaluate their impact on model performance and to identify methodological improvements.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed 12,767 hemodialysis sessions from 66 patients. Recurrent IDH was defined as an event occurring \u226530\u2005min after the initial IDH. Deep learning models, including ConvMixer, temporal convolutional network, and long short-term memory with attention, were compared with a rule-based na\u00efve baseline that predicted IDH solely from prior occurrence. Modeling strategies explicitly incorporating recurrence information were implemented. Model robustness across systolic blood pressure subgroups was evaluated and enhanced using adversarial training.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The probability of IDH increased markedly from 0.7\u201310.4% before initial events to 11.7\u201365.7% thereafter. Conventional evaluation that aggregated all IDH events overestimated performance, with particularly large gaps in F1 score and AUPRC between initial and recurrent IDH predictions. The na\u00efve baseline achieved an area under the receiver operating characteristic (AUROC) curve of 0.798 without training, highlighting the strong influence of recurrence patterns on predictive performance. Incorporating recurrence-aware features and loss weighting improved AUROC by up to 8.0 percentage points across architectures. Adversarial training further reduced subgroup disparities while preserving overall model performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Incorporating recurrence patterns into IDH prediction models demonstrated improvements in accuracy, robustness, and comparability across studies. We recommend standardized evaluation protocols that explicitly account for recurrence to enhance clinical applicability and reliability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdgth.2026.1804788","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:45:04Z","timestamp":1783403104000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Intra-Session recurrence in intradialytic hypotension prediction: evaluation implications and recurrence-aware modeling"],"prefix":"10.3389","volume":"8","author":[{"given":"Siun","family":"Kim","sequence":"first","affiliation":[{"name":"Biomedical Research Institute, Seoul National University Hospital","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiwon","family":"Ryu","sequence":"additional","affiliation":[{"name":"Seoul National University Bundang Hospital","place":["Seongnam-si, Republic of Korea"]},{"name":"Department of Internal Medicine, Seoul National University College of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sejoong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Seoul National University College of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Su Hwan","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Information Statistics, Gyeongsang National University","place":["Jinju, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myeongju","family":"Kim","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence in Healthcare, Seoul National University Bundang Hospital","place":["Seongnam, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyung-Jin","family":"Yoon","sequence":"additional","affiliation":[{"name":"Department of Human Systems Medicine, Seoul National University College of Medicine","place":["Seoul, Republic of Korea"]},{"name":"Medical Bigdata Research Center, Seoul National University College of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.2215\/CJN.12141017","article-title":"Mechanisms, clinical implications, and treatment of intradialytic hypotension","volume":"13","author":"Reeves","year":"2018","journal-title":"Clin J Am Soc Nephrol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1186\/s12882-023-03263-6","article-title":"Impact of frequent intradialytic hypotension on quality of life in patients undergoing hemodialysis","volume":"24","author":"Wang","year":"2023","journal-title":"BMC Nephrol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2601","DOI":"10.1093\/ndt\/gfg450","article-title":"The effect of frequent or occasional dialysis-associated hypotension on survival of patients on maintenance haemodialysis","volume":"18","author":"Tisl\u00e9r","year":"2003","journal-title":"Nephrol Dial Transplant"},{"key":"B4","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1111\/sdi.12627","article-title":"A brief review of intradialytic hypotension with a focus on survival","volume":"30","author":"Chou","year":"2017","journal-title":"Semin Dial"},{"key":"B5","doi-asserted-by":"publisher","first-page":"77","DOI":"10.23876\/j.krcp.23.188","article-title":"Intradialytic hypotension and worse outcomes in patients with acute kidney injury requiring intermittent hemodialysis","volume":"45","author":"Park","year":"2024","journal-title":"Kidney Res Clin Pract"},{"key":"B6","doi-asserted-by":"publisher","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":"B7","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.2215\/CJN.10150818","article-title":"Beware intradialytic hypotension: how low is too low?","volume":"13","author":"Inrig","year":"2018","journal-title":"Clin J Am Soc Nephrol"},{"key":"B8","doi-asserted-by":"publisher","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":"B9","doi-asserted-by":"publisher","first-page":"00368504241308982","DOI":"10.1177\/00368504241308982","article-title":"Prevalence of cardiovascular instability during hemodialysis therapy in hospitalized patients: a systematic review and meta-analysis","volume":"107","author":"Arcentales-Vera","year":"2024","journal-title":"Sci Prog"},{"key":"B10","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1111\/j.1542-4758.2008.00242.x","article-title":"Oral intake during hemodialysis: is there an association with intradialytic hypotension?","volume":"12","author":"Benaroia","year":"2008","journal-title":"Hemodial Int"},{"key":"B11","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1681\/ASN.2004070581","article-title":"Effect of sodium balance and the combination of ultrafiltration profile during sodium profiling hemodialysis on the maintenance of the quality of dialysis and sodium and fluid balances","volume":"16","author":"Song","year":"2005","journal-title":"J Am Soc Nephrol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1111\/j.1542-4758.2011.00560.x","article-title":"Associations of endothelial dysfunction and arterial stiffness with intradialytic hypotension and hypertension","volume":"15","author":"Dubin","year":"2011","journal-title":"Hemodial Int"},{"key":"B13","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1053\/j.ajkd.2005.01.019","article-title":"K\/DOQI clinical practice guidelines for cardiovascular disease in dialysis patients","volume":"45","year":"2005","journal-title":"Am J Kidney Dis"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1056\/NEJMoa021583","article-title":"Effect of dialysis dose and membrane flux in maintenance hemodialysis","volume":"347","author":"Eknoyan","year":"2002","journal-title":"N Engl J Med"},{"key":"B15","doi-asserted-by":"publisher","first-page":"107698","DOI":"10.1016\/j.cmpb.2023.107698","article-title":"Machine learning-based intradialytic hypotension prediction of patients undergoing hemodialysis: a multicenter retrospective study","volume":"240","author":"Dong","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"key":"B16","doi-asserted-by":"publisher","first-page":"2310","DOI":"10.1093\/ndt\/gfad064","article-title":"Prediction of intradialytic hypotension using pre-dialysis features-a deep learning\u2013based artificial intelligence model","volume":"38","author":"Lee","year":"2023","journal-title":"Nephrol Dial Transplant"},{"key":"B17","doi-asserted-by":"publisher","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":"B18","doi-asserted-by":"publisher","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":"B19","doi-asserted-by":"publisher","first-page":"18054","DOI":"10.1038\/s41598-023-45282-1","article-title":"Real-time dual prediction of intradialytic hypotension and hypertension using an explainable deep learning model","volume":"13","author":"Yun","year":"2023","journal-title":"Sci Rep"},{"key":"B20","doi-asserted-by":"publisher","first-page":"878858","DOI":"10.3389\/fmed.2022.878858","article-title":"Deep learning model for predicting intradialytic hypotension without privacy infringement: a retrospective two-center study","volume":"9","author":"Kim","year":"2022","journal-title":"Front Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"82382","DOI":"10.1109\/ACCESS.2020.2988993","article-title":"Deep learning for intradialytic hypotension prediction in hemodialysis patients","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"B22","first-page":"69","article-title":"The new method of feature selection for intradialytic hypotension prediction using machine learning","author":"Hu","year":"2021"},{"key":"B23","doi-asserted-by":"publisher","first-page":"10373","DOI":"10.3390\/ijerph191610373","article-title":"Multi-layer perceptron-based real-time intradialytic hypotension prediction using patient baseline information and heart-rate variation","volume":"19","author":"Bae","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"B24","author":"Nie","year":"2023"},{"key":"B25","author":"Wu","year":"2023"},{"key":"B26","author":"Bai","year":"2018"},{"key":"B27","author":"Trockman","year":"2022"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1093\/ije\/dyz274","article-title":"Reflection on modern methods: revisiting the area under the ROC curve","volume":"49","author":"Janssens","year":"2020","journal-title":"Int J Epidemiol"},{"key":"B29","author":"Sundararajan","year":"2017"},{"key":"B30","doi-asserted-by":"publisher","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":"B31","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1159\/000503776","article-title":"Intradialytic hypotension: mechanisms and outcome","volume":"49","author":"Sars","year":"2020","journal-title":"Blood Purif"},{"key":"B32","doi-asserted-by":"publisher","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":"B33","doi-asserted-by":"publisher","first-page":"e18605","DOI":"10.7717\/peerj.18605","article-title":"Risk factors and prediction models for recurrent acute ischemic stroke: a retrospective analysis","volume":"12","author":"Ke","year":"2024","journal-title":"PeerJ"},{"key":"B34","doi-asserted-by":"publisher","first-page":"kxaf007","DOI":"10.1093\/biostatistics\/kxaf007","article-title":"Random forest for dynamic risk prediction of recurrent events: a pseudo-observation approach","volume":"26","author":"Loe","year":"2025","journal-title":"Biostatistics"},{"key":"B35","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1177\/19322968231185796","article-title":"Development and validation of binary classifiers to predict nocturnal hypoglycemia in adults with type 1 diabetes","volume":"19","author":"Afentakis","year":"2025","journal-title":"J Diabetes Sci Technol"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1883","DOI":"10.1093\/ndt\/gfl126","article-title":"A systematic review of the clinical effects of reducing dialysate fluid temperature","volume":"21","author":"Selby","year":"2006","journal-title":"Nephrol Dial Transplant"},{"key":"B37","doi-asserted-by":"publisher","first-page":"S11","DOI":"10.1053\/ajkd.2001.28090","article-title":"Pathophysiology of dialysis hypotension: an update","volume":"38","author":"Daugirdas","year":"2001","journal-title":"Am J Kidney Dis"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1804788\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:45:05Z","timestamp":1783403105000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1804788\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":37,"alternative-id":["10.3389\/fdgth.2026.1804788"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1804788","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]},"article-number":"1804788"}}