{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/long-term-blood-pressure-prediction-with-deep","title":"Long-term Blood Pressure Prediction with Deep Recurrent Neural Networks","arxiv_id":"1705.04524","date":"2017-05-12","proceeding":null,"authors":["Peng Su","Xiao-Rong Ding","Yuan-Ting Zhang","Jing Liu","Fen Miao","Ni Zhao"],"abstract":"Existing methods for arterial blood pressure (BP) estimation directly map the\ninput physiological signals to output BP values without explicitly modeling the\nunderlying temporal dependencies in BP dynamics. As a result, these models\nsuffer from accuracy decay over a long time and thus require frequent\ncalibration. In this work, we address this issue by formulating BP estimation\nas a sequence prediction problem in which both the input and target are\ntemporal sequences. We propose a novel deep recurrent neural network (RNN)\nconsisting of multilayered Long Short-Term Memory (LSTM) networks, which are\nincorporated with (1) a bidirectional structure to access larger-scale context\ninformation of input sequence, and (2) residual connections to allow gradients\nin deep RNN to propagate more effectively. The proposed deep RNN model was\ntested on a static BP dataset, and it achieved root mean square error (RMSE) of\n3.90 and 2.66 mmHg for systolic BP (SBP) and diastolic BP (DBP) prediction\nrespectively, surpassing the accuracy of traditional BP prediction models. On a\nmulti-day BP dataset, the deep RNN achieved RMSE of 3.84, 5.25, 5.80 and 5.81\nmmHg for the 1st day, 2nd day, 4th day and 6th month after the 1st day SBP\nprediction, and 1.80, 4.78, 5.0, 5.21 mmHg for corresponding DBP prediction,\nrespectively, which outperforms all previous models with notable improvement.\nThe experimental results suggest that modeling the temporal dependencies in BP\ndynamics significantly improves the long-term BP prediction accuracy.","url_abs":"http://arxiv.org/abs/1705.04524v3","url_pdf":"http://arxiv.org/pdf/1705.04524v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"long-term-blood-pressure-prediction-with-deep","repo_url":"https://github.com/psu1/DeepRNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"long-term-blood-pressure-prediction-with-deep","repo_url":"https://github.com/akrlowicz/ppg-blood-pressure-estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"blood-pressure-estimation","task_name":"Blood pressure estimation"},{"task_slug":"electrocardiography-ecg","task_name":"Electrocardiography (ECG)"},{"task_slug":"photoplethysmography-ppg","task_name":"Photoplethysmography (PPG)"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"temporal-sequences","task_name":"Temporal Sequences"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/blood-pressure-estimation-on-mimic-iii","task":"Blood pressure estimation","dataset":"MIMIC-III","model":"Deep RNN","rank_in_archive_order":1,"of":4,"metrics":{"MAE for DBP [mmHg]":"6.7","MAE for SBP [mmHg]":"8.54"},"uses_additional_data":false},{"leaderboard":"/sota/blood-pressure-estimation-on-multi-day-1","task":"Blood pressure estimation","dataset":"Multi-day Continuous BP Prediction","model":"Deep RNN","rank_in_archive_order":1,"of":1,"metrics":{"RMSE":"3.73"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}