{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T07:49:16Z","timestamp":1794383356930,"version":"4.9.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T00:00:00Z","timestamp":1786752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T00:00:00Z","timestamp":1786752000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005713","name":"Technische Universit\u00e4t M\u00fcnchen","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005713","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Cuffless blood pressure (BP) estimation via photoplethysmography (PPG) and machine learning has been widely studied, yet reported accuracy remains below clinically acceptable levels, limiting adoption in sport, ambient living, and telemedicine. This study systematically examines potential error sources underlying these performance gaps, with emphasis on: dataset selection, signal synchronization, subject-specific calibration, and data leakage. Three neural networks\u2014a multilayer perceptron (MLP_BP), residual network (Res_BP), and temporal convolutional network (TCN_BP)\u2014were evaluated on two curated public datasets derived from MIMIC III and VitalDB, differing primarily in signal synchronization. MLP_BP uses scalar features from ECG and PPG signals, including pulse arrival time, heart rate, and variability; Res_BP and TCN_BP additionally process PPG signals. Subject-wise splits prevent data leakage, and calibration is applied using three to nine initial reference measurements per subject. Models trained on VitalDB consistently outperform those trained on MIMIC III, particularly for systolic BP, underscoring the importance of synchronized signals. Subject-specific calibration improves performance, with diminishing returns beyond three measurements. Calibrated models reach clinically acceptable accuracy for diastolic BP, while systolic BP remains challenging using PPG alone. These findings suggest that dataset integrity and proper calibration may matter more than model architecture in cuffless BP estimation.<\/jats:p>","DOI":"10.1038\/s41598-026-66882-7","type":"journal-article","created":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T18:33:30Z","timestamp":1786818810000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The role of dataset integrity, calibration and signal quality in neural network-based blood pressure estimation"],"prefix":"10.1038","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0423-8361","authenticated-orcid":false,"given":"Christian","family":"Fritzsche","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Veit","family":"Senner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,15]]},"reference":[{"issue":"2","key":"66882_CR1","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1161\/HYPERTENSIONAHA.119.14240","volume":"75","author":"FD Fuchs","year":"2020","unstructured":"Fuchs, F. D. & Whelton, P. K. High blood pressure and cardiovascular disease. Hypertension 75(2), 285\u2013292. https:\/\/doi.org\/10.1161\/HYPERTENSIONAHA.119.14240 (2020).","journal-title":"Hypertension"},{"key":"66882_CR2","unstructured":"World Health Organization, \u201cGlobal report on hypertension: the race against a silent killer.\u201d Accessed: Nov. 07, 2025. [Online]. Available: https:\/\/www.who.int\/publications\/i\/item\/9789240081062"},{"issue":"1","key":"66882_CR3","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1038\/s41746-023-00835-6","volume":"6","author":"L Zhao","year":"2023","unstructured":"Zhao, L. et al. Emerging sensing and modeling technologies for wearable and cuffless blood pressure monitoring. NPJ Digit. Med. 6(1), 93. https:\/\/doi.org\/10.1038\/s41746-023-00835-6 (2023).","journal-title":"NPJ Digit. Med."},{"key":"66882_CR4","doi-asserted-by":"publisher","DOI":"10.1080\/08037051.2024.2402368","author":"N Pilz","year":"2024","unstructured":"Pilz, N. et al. Cuff-based blood pressure measurement: Challenges and solutions. Blood Press. https:\/\/doi.org\/10.1080\/08037051.2024.2402368 (2024).","journal-title":"Blood Press."},{"issue":"3","key":"66882_CR5","doi-asserted-by":"publisher","first-page":"74","DOI":"10.5960\/dzsm.2023.560","volume":"74","author":"P M\u00fcller","year":"2023","unstructured":"M\u00fcller, P., Lechner, K., Halle, M. & Braun-Dullaeus, R. Physical activity and arterial hypertension. Dtsch. Z. Sportmed. 74(3), 74\u201379. https:\/\/doi.org\/10.5960\/dzsm.2023.560 (2023).","journal-title":"Dtsch. Z. Sportmed."},{"issue":"9","key":"66882_CR6","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1097\/HJH.0000000000001791","volume":"36","author":"A Pressler","year":"2018","unstructured":"Pressler, A., J\u00e4hnig, A., Halle, M. & Haller, B. Blood pressure response to maximal dynamic exercise testing in an athletic population. J. Hypertens. 36(9), 1803\u20131809. https:\/\/doi.org\/10.1097\/HJH.0000000000001791 (2018).","journal-title":"J. Hypertens."},{"issue":"8","key":"66882_CR7","doi-asserted-by":"publisher","first-page":"8095","DOI":"10.1007\/s10462-022-10353-8","volume":"56","author":"K Qin","year":"2023","unstructured":"Qin, K., Huang, W., Zhang, T. & Tang, S. Machine learning and deep learning for blood pressure prediction: A methodological review from multiple perspectives. Artif. Intell. Rev. 56(8), 8095\u20138196. https:\/\/doi.org\/10.1007\/s10462-022-10353-8 (2023).","journal-title":"Artif. Intell. Rev."},{"issue":"1","key":"66882_CR8","doi-asserted-by":"publisher","DOI":"10.3390\/diseases6010020","volume":"6","author":"M Elgendi","year":"2018","unstructured":"Elgendi, M., Liang, Y. & Ward, R. Toward generating more diagnostic features from photoplethysmogram waveforms. Diseases 6(1), 20. https:\/\/doi.org\/10.3390\/diseases6010020 (2018).","journal-title":"Diseases"},{"key":"66882_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107558","volume":"166","author":"S Sarkar","year":"2023","unstructured":"Sarkar, S. & Ghosh, A. Schr\u00f6dinger spectrum based continuous cuff-less blood pressure estimation using clinically relevant features from PPG signal and its second derivative. Comput. Biol. Med. 166, 107558. https:\/\/doi.org\/10.1016\/j.compbiomed.2023.107558 (2023).","journal-title":"Comput. Biol. Med."},{"key":"66882_CR10","doi-asserted-by":"publisher","first-page":"44963","DOI":"10.1109\/ACCESS.2021.3065576","volume":"9","author":"P Li","year":"2021","unstructured":"Li, P. & Laleg-Kirati, T.-M. Central blood pressure estimation from distal PPG measurement using semiclassical signal analysis features. IEEE Access 9, 44963\u201344973. https:\/\/doi.org\/10.1109\/ACCESS.2021.3065576 (2021).","journal-title":"IEEE Access"},{"issue":"1","key":"66882_CR11","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-01358-4","volume":"11","author":"E Finnegan","year":"2021","unstructured":"Finnegan, E. et al. Pulse arrival time as a surrogate of blood pressure. Sci. Rep. 11(1), 22767. https:\/\/doi.org\/10.1038\/s41598-021-01358-4 (2021).","journal-title":"Sci. Rep."},{"issue":"12","key":"66882_CR12","doi-asserted-by":"publisher","first-page":"3299","DOI":"10.1109\/TIM.2017.2745081","volume":"66","author":"A Esmaili","year":"2017","unstructured":"Esmaili, A., Kachuee, M. & Shabany, M. Nonlinear cuffless blood pressure estimation of healthy subjects using pulse transit time and arrival time. IEEE Trans. Instrum. Meas. 66(12), 3299\u20133308. https:\/\/doi.org\/10.1109\/TIM.2017.2745081 (2017).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"66882_CR13","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1161\/01.CIR.101.23.e215","volume":"101","author":"AL Goldberger","year":"2000","unstructured":"Goldberger, A. L. et al. PhysioBank, PhysioToolkit, and PhysioNet. Circulation 101, 23. https:\/\/doi.org\/10.1161\/01.CIR.101.23.e215 (2000).","journal-title":"Circulation"},{"issue":"5","key":"66882_CR14","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1109\/JBHI.2021.3128383","volume":"26","author":"W Wang","year":"2022","unstructured":"Wang, W., Mohseni, P., Kilgore, K. L. & Najafizadeh, L. Cuff-less blood pressure estimation from photoplethysmography via visibility graph and transfer learning. IEEE J. Biomed. Health Inform. 26(5), 2075\u20132085. https:\/\/doi.org\/10.1109\/JBHI.2021.3128383 (2022).","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"1","key":"66882_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-23350-y","volume":"15","author":"S Subramanian","year":"2025","unstructured":"Subramanian, S., Mishra, S., Patil, S., Kolekar, M. H. & Ortiz-Rodriguez, F. Integrating transfer learning with scalogram analysis for blood pressure estimation from PPG signals. Sci. Rep. 15(1), 39647. https:\/\/doi.org\/10.1038\/s41598-025-23350-y (2025).","journal-title":"Sci. Rep."},{"key":"66882_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103719","volume":"120","author":"J Esmaelpoor","year":"2020","unstructured":"Esmaelpoor, J., Moradi, M. H. & Kadkhodamohammadi, A. A multistage deep neural network model for blood pressure estimation using photoplethysmogram signals. Comput. Biol. Med. 120, 103719. https:\/\/doi.org\/10.1016\/j.compbiomed.2020.103719 (2020).","journal-title":"Comput. Biol. Med."},{"issue":"19","key":"66882_CR17","doi-asserted-by":"publisher","DOI":"10.3390\/s20195668","volume":"20","author":"Y-C Hsu","year":"2020","unstructured":"Hsu, Y.-C., Li, Y.-H., Chang, C.-C. & Harfiya, L. N. Generalized deep neural network model for cuffless blood pressure estimation with photoplethysmogram signal only. Sensors 20(19), 5668. https:\/\/doi.org\/10.3390\/s20195668 (2020).","journal-title":"Sensors"},{"key":"66882_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106741","volume":"99","author":"Z Tian","year":"2025","unstructured":"Tian, Z., Liu, A., Zhu, G. & Chen, X. A paralleled CNN and transformer network for PPG-based cuff-less blood pressure estimation. Biomed. Signal Process. Control 99, 106741. https:\/\/doi.org\/10.1016\/j.bspc.2024.106741 (2025).","journal-title":"Biomed. Signal Process. Control"},{"key":"66882_CR19","doi-asserted-by":"publisher","unstructured":"Darbhasayanam, S. H., Noorjahan, H. A., Mohammad, A. & Komalla, A. R. Photoplethysmogram (PPG)-based blood pressure estimation using vision transformer networks: A deep learning approach. In 2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT) 1\u20136 (IEEE 2024). https:\/\/doi.org\/10.1109\/AIIoT58432.2024.10574539","DOI":"10.1109\/AIIoT58432.2024.10574539"},{"key":"66882_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102301","volume":"65","author":"C El-Hajj","year":"2021","unstructured":"El-Hajj, C. & Kyriacou, P. Deep learning models for cuffless blood pressure monitoring from PPG signals using attention mechanism. Biomed. Signal Process. Control 65, 102301. https:\/\/doi.org\/10.1016\/j.bspc.2020.102301 (2021).","journal-title":"Biomed. Signal Process. Control"},{"issue":"3","key":"66882_CR21","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1161\/HYPERTENSIONAHA.117.10237","volume":"71","author":"GS Stergiou","year":"2018","unstructured":"Stergiou, G. S. et al. A universal standard for the validation of blood pressure measuring devices. Hypertension 71(3), 368\u2013374. https:\/\/doi.org\/10.1161\/HYPERTENSIONAHA.117.10237 (2018).","journal-title":"Hypertension"},{"issue":"7285","key":"66882_CR22","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1136\/bmj.322.7285.531","volume":"322","author":"E O\u2019Brien","year":"2001","unstructured":"O\u2019Brien, E., Waeber, B., Parati, G., Staessen, J. & Myers, M. G. Blood pressure measuring devices: recommendations of the European Society of Hypertension. BMJ 322(7285), 531\u2013536. https:\/\/doi.org\/10.1136\/bmj.322.7285.531 (2001).","journal-title":"BMJ"},{"key":"66882_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103581","volume":"75","author":"M Yu","year":"2022","unstructured":"Yu, M., Huang, Z., Zhu, Y., Zhou, P. & Zhu, J. Attention-based residual improved U-Net model for continuous blood pressure monitoring by using photoplethysmography signal. Biomed. Signal Process. Control 75, 103581. https:\/\/doi.org\/10.1016\/j.bspc.2022.103581 (2022).","journal-title":"Biomed. Signal Process. Control"},{"issue":"1","key":"66882_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-68862-1","volume":"14","author":"S Mehta","year":"2024","unstructured":"Mehta, S., Kwatra, N., Jain, M. & McDuff, D. Examining the challenges of blood pressure estimation via photoplethysmogram. Sci. Rep. 14(1), 18318. https:\/\/doi.org\/10.1038\/s41598-024-68862-1 (2024).","journal-title":"Sci. Rep."},{"issue":"18","key":"66882_CR25","doi-asserted-by":"publisher","DOI":"10.3390\/s21186022","volume":"21","author":"F Schrumpf","year":"2021","unstructured":"Schrumpf, F., Frenzel, P., Aust, C., Osterhoff, G. & Fuchs, M. Assessment of non-invasive blood pressure prediction from PPG and rPPG signals using deep learning. Sensors 21(18), 6022. https:\/\/doi.org\/10.3390\/s21186022 (2021).","journal-title":"Sensors"},{"issue":"1","key":"66882_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-04041-1","volume":"11","author":"I Sanches","year":"2024","unstructured":"Sanches, I. et al. MIMIC-BP: A curated dataset for blood pressure estimation. Sci. Data 11(1), 1233. https:\/\/doi.org\/10.1038\/s41597-024-04041-1 (2024).","journal-title":"Sci. Data"},{"key":"66882_CR27","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2022.1090854","author":"W Wang","year":"2023","unstructured":"Wang, W., Mohseni, P., Kilgore, K. L. & Najafizadeh, L. PulseDB: A large, cleaned dataset based on MIMIC-III and VitalDB for benchmarking cuff-less blood pressure estimation methods. Front. Digit. Health https:\/\/doi.org\/10.3389\/fdgth.2022.1090854 (2023).","journal-title":"Front. Digit. Health"},{"key":"66882_CR28","doi-asserted-by":"publisher","unstructured":"Moody, B., Moody, G., Villaroel, M., Clifford, G. D. & Silva, I. MIMIC-III Waveform Database Matched Subset (version 1.0), 2020. Accessed: Nov. 21, 2025. [Online]. Available: https:\/\/doi.org\/10.13026\/c2294b","DOI":"10.13026\/c2294b"},{"key":"66882_CR29","doi-asserted-by":"publisher","unstructured":"Moody, B., Moody, G., Villarroel, M., Clifford, G. D. & Silva, I. MIMIC-III Waveform Database (version 1.0), PhysioNet, 2020, Accessed: Jan. 12, 2026. [Online]. Available: https:\/\/doi.org\/10.13026\/c2607m","DOI":"10.13026\/c2607m"},{"key":"66882_CR30","unstructured":"\u201cVitalDB.\u201d Accessed: Jan. 12, 2026. [Online]. Available: https:\/\/vitaldb.net\/dataset\/"},{"issue":"8","key":"66882_CR31","doi-asserted-by":"publisher","first-page":"1879","DOI":"10.1109\/TBME.2015.2441951","volume":"62","author":"R Mukkamala","year":"1879","unstructured":"Mukkamala, R. et al. Toward ubiquitous blood pressure monitoring via pulse transit time: Theory and practice.. IEEE Trans. Biomed. Eng. 62(8), 1879\u20131901. https:\/\/doi.org\/10.1109\/TBME.2015.2441951 (1879).","journal-title":"IEEE Trans. Biomed. Eng."},{"issue":"7","key":"66882_CR32","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1097\/00004872-199007000-00004","volume":"8","author":"E O\u2019Brien","year":"1990","unstructured":"O\u2019Brien, E. et al. The British Hypertension Society protocol for the evaluation of automated and semi-automated blood pressure measuring devices with special reference to ambulatory systems. J. Hypertens. 8(7), 607\u2013619. https:\/\/doi.org\/10.1097\/00004872-199007000-00004 (1990).","journal-title":"J. Hypertens."},{"key":"66882_CR33","doi-asserted-by":"publisher","DOI":"10.3390\/jcm8030337","author":"Y Liang","year":"2019","unstructured":"Liang, Y. et al. How effective is pulse arrival time for evaluating blood pressure? Challenges and recommendations from a study using the MIMIC database.. J. Clin. Med. https:\/\/doi.org\/10.3390\/jcm8030337 (2019).","journal-title":"J. Clin. Med."},{"key":"66882_CR34","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2018.01848","author":"B Escobar-Restrepo","year":"2018","unstructured":"Escobar-Restrepo, B., Torres-Villa, R. & Kyriacou, P. A. Evaluation of the linear relationship between pulse arrival time and blood pressure in ICU patients: Potential and limitations. Front. Physiol. https:\/\/doi.org\/10.3389\/fphys.2018.01848 (2018).","journal-title":"Front. Physiol."},{"key":"66882_CR35","doi-asserted-by":"publisher","DOI":"10.3390\/jcm8111773","author":"J Lee","year":"2019","unstructured":"Lee, J., Yang, S., Lee, S. & Kim, H. C. Analysis of pulse arrival time as an indicator of blood pressure in a large surgical biosignal database: Recommendations for developing ubiquitous blood pressure monitoring methods. J. Clin. Med. https:\/\/doi.org\/10.3390\/jcm8111773 (2019).","journal-title":"J. Clin. Med."},{"key":"66882_CR36","doi-asserted-by":"publisher","DOI":"10.1093\/ckj\/sfaf255","author":"M Wunderle","year":"2025","unstructured":"Wunderle, M. et al. Continuous measurement of pulse arrival time for identification of blood pressure changes in patients undergoing hemodialysis\u2014A feasibility study. Clin. Kidney J. https:\/\/doi.org\/10.1093\/ckj\/sfaf255 (2025).","journal-title":"Clin. Kidney J."},{"key":"66882_CR37","doi-asserted-by":"publisher","unstructured":"Yan, C. et al., Novel deep convolutional neural network for cuff-less blood pressure measurement using ECG and PPG signals. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 1917\u20131920 (IEEE, 2019). https:\/\/doi.org\/10.1109\/EMBC.2019.8857108","DOI":"10.1109\/EMBC.2019.8857108"},{"issue":"1","key":"66882_CR38","doi-asserted-by":"publisher","first-page":"18318","DOI":"10.1038\/s41598-024-68862-1","volume":"14","author":"S Mehta","year":"2024","unstructured":"Mehta, S., Kwatra, N., Jain, M. & McDuff, D. Examining the challenges of blood pressure estimation via photoplethysmogram. Sci. Rep. 14(1), 18318. https:\/\/doi.org\/10.1038\/s41598-024-68862-1 (2024).","journal-title":"Sci. Rep."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-66882-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-66882-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-66882-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T18:39:35Z","timestamp":1786819175000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-66882-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,15]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["66882"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-66882-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,15]]},"assertion":[{"value":"19 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"25524"}}