{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T10:19:49Z","timestamp":1794565189978,"version":"4.9.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Swiss State Secretariat for Education, Research and lnnovation"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Monitoring of cardiac output (CO) is a mainstay of hemodynamic management in the acutely or critically ill patient. Invasive determination of CO using thermodilution, albeit regarded as the gold standard, is cumbersome and bears risks inherent to catheterization. In the pursuit of noninvasive methods, prediction of CO from arterial pressure waveforms (even uncalibrated) through AI has garnered increased attention. In the current study we investigate the effect of peripheral blood pressure measurements\u2019 (i) location, (ii) calibration and (iii) injected additive noise on the performance of AI-based CO estimation. A large previously generated virtual cohort of n\u2009=\u20093818 subjects with varied hemodynamic profiles served as data bank for arterial pulse waves and reference CO values. Two-layered convolutional neural networks (CNN) yielded CO estimates based on entire pressure traces from the radial, superficial temporal and common carotid arteries. The predictive ability of the CNN models was comparable across arterial locations (r \u2265 0.97, nRMSE\u2009 \u2264 4.4%) and only slightly compromised following pressure signal normalization from 0 to 1 (r\u2009 \u2265 0.93, nRMSE \u2264 7.8%). Following noise injection, model performance was preserved (r\u2009 \u2265 0.94, nRMSE \u2264 6.6%) yet became more sensitive to loss of calibration (r \u2265 0.78, nRMSE \u2264 12.2%). Our study highlights the interchangeability of potential blood pressure measurement locations in the quest for pressure-based CO estimation.<\/jats:p>","DOI":"10.1038\/s41598-025-10492-2","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T14:44:55Z","timestamp":1752590695000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Machine learning-enabled estimation of cardiac output from peripheral waveforms is independent of blood pressure measurement location in an in silico population"],"prefix":"10.1038","volume":"15","author":[{"given":"Lydia","family":"Aslanidou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Rovas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramin","family":"Mohammadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sokratis","family":"Anagnostopoulos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cemre","family":"\u00c7elikbudak Orhon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolaos","family":"Stergiopulos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"10492_CR1","doi-asserted-by":"publisher","first-page":"421","DOI":"10.21037\/atm.2019.07.06","volume":"7","author":"I Pour-Ghaz","year":"2019","unstructured":"Pour-Ghaz, I. et al. Accuracy of non-invasive and minimally invasive hemodynamic monitoring: where do we stand?. Ann. Transl. Med. 7, 421\u2013421 (2019).","journal-title":"Ann. Transl. Med."},{"key":"10492_CR2","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1093\/bja\/aeu447","volume":"114","author":"B Saugel","year":"2015","unstructured":"Saugel, B., Cecconi, M., Wagner, J. Y. & Reuter, D. A. Noninvasive continuous cardiac output monitoring in perioperative and intensive care medicine. Br. J. Anaesth. 114, 562\u2013575 (2015).","journal-title":"Br. J. Anaesth."},{"key":"10492_CR3","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1007\/s40140-017-0239-0","volume":"7","author":"PM Odor","year":"2017","unstructured":"Odor, P. M., Bampoe, S. & Cecconi, M. Cardiac output monitoring: Validation studies: How results should be presented. Curr. Anesthesiol. Rep. 7, 410\u2013415 (2017).","journal-title":"Curr. Anesthesiol. Rep."},{"key":"10492_CR4","doi-asserted-by":"publisher","first-page":"e12","DOI":"10.15420\/usc.2021.34","volume":"16","author":"AS Rali","year":"2022","unstructured":"Rali, A. S. et al. Contemporary review of hemodynamic monitoring in the critical care setting. US Cardiol. Rev. 16, e12 (2022).","journal-title":"US Cardiol. Rev."},{"key":"10492_CR5","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.1097\/ALN.0b013e3181ee3130","volume":"113","author":"PJ Peyton","year":"2010","unstructured":"Peyton, P. J. & Chong, S. W. Minimally invasive measurement of cardiac output during surgery and critical care: A meta-analysis of accuracy and precision. Anesthesiology 113, 1220\u20131235 (2010).","journal-title":"Anesthesiology"},{"key":"10492_CR6","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1097\/ALN.0000000000003483","volume":"133","author":"B Saugel","year":"2020","unstructured":"Saugel, B., Thiele, R. H., Hapfelmeier, A. & Cannesson, M. Technological assessment and objective evaluation of minimally invasive and noninvasive cardiac output monitoring systems. Anesthesiology 133, 921\u2013928 (2020).","journal-title":"Anesthesiology"},{"key":"10492_CR7","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1093\/bja\/aew461","volume":"118","author":"A Joosten","year":"2017","unstructured":"Joosten, A. et al. Accuracy and precision of non-invasive cardiac output monitoring devices in perioperative medicine: A systematic review and meta-analysis. Br. J. Anaesth. 118, 298\u2013310 (2017).","journal-title":"Br. J. Anaesth."},{"key":"10492_CR8","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1016\/j.echo.2021.05.012","volume":"34","author":"HN Patel","year":"2021","unstructured":"Patel, H. N. et al. Normal values of cardiac output and stroke volume according to measurement technique, age, sex, and ethnicity: Results of the world alliance of societies of echocardiography study. J. Am. Soc. Echocardiogr. 34, 1077-1085.e1 (2021).","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"10492_CR9","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1007\/s00134-016-4258-y","volume":"42","author":"M Wetterslev","year":"2016","unstructured":"Wetterslev, M., M\u00f8ller-S\u00f8rensen, H., Johansen, R. R. & Perner, A. Systematic review of cardiac output measurements by echocardiography versus thermodilution: The techniques are not interchangeable. Intensive Care Med. 42, 1223\u20131233 (2016).","journal-title":"Intensive Care Med."},{"key":"10492_CR10","doi-asserted-by":"publisher","first-page":"894308","DOI":"10.1155\/2012\/894308","volume":"2012","author":"SJ Huang","year":"2012","unstructured":"Huang, S. J. & McLean, A. S. Appreciating the strengths and weaknesses of transthoracic echocardiography in hemodynamic assessments. Cardiol. Res. Pract. 2012, 894308 (2012).","journal-title":"Cardiol. Res. Pract."},{"key":"10492_CR11","doi-asserted-by":"publisher","first-page":"839","DOI":"10.3390\/diagnostics13050839","volume":"13","author":"M Keller","year":"2023","unstructured":"Keller, M., Magunia, H., Rosenberger, P. & Koeppen, M. Echocardiography as a tool to assess cardiac function in critical care: A review. Diagnostics (Basel) 13, 839 (2023).","journal-title":"Diagnostics (Basel)"},{"key":"10492_CR12","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s12968-015-0172-7","volume":"17","author":"KS Nayak","year":"2015","unstructured":"Nayak, K. S. et al. Cardiovascular magnetic resonance phase contrast imaging. J. Cardiovasc. Magn. Reson. 17, 71 (2015).","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"10492_CR13","doi-asserted-by":"publisher","first-page":"1014","DOI":"10.1038\/s41598-018-19457-0","volume":"8","author":"P Tavallali","year":"2018","unstructured":"Tavallali, P., Razavi, M. & Pahlevan, N. M. Artificial intelligence estimation of carotid-femoral pulse wave velocity using carotid waveform. Sci. Rep. 8, 1014 (2018).","journal-title":"Sci. Rep."},{"key":"10492_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0245026","volume":"16","author":"W Jin","year":"2021","unstructured":"Jin, W., Chowienczyk, P. & Alastruey, J. Estimating pulse wave velocity from the radial pressure wave using machine learning algorithms. PLoS ONE 16, 1\u201316 (2021).","journal-title":"PLoS ONE"},{"key":"10492_CR15","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1161\/HYPERTENSIONAHA.123.21638","volume":"81","author":"GF Mitchell","year":"2024","unstructured":"Mitchell, G. F. et al. Vascular age assessed from an uncalibrated, noninvasive pressure waveform by using a deep learning approach: The AI-VascularAge model. Hypertension 81, 193\u2013201 (2024).","journal-title":"Hypertension"},{"key":"10492_CR16","doi-asserted-by":"publisher","first-page":"e2416006122","DOI":"10.1073\/pnas.2416006122","volume":"122","author":"A Tamborini","year":"2025","unstructured":"Tamborini, A., Aghilinejad, A. & Gharib, M. A spectral machine learning approach to derive central aortic pressure waveforms from a brachial cuff. Proc. Natl. Acad. Sci. 122, e2416006122 (2025).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10492_CR17","doi-asserted-by":"publisher","first-page":"1199726","DOI":"10.3389\/fbioe.2023.1199726","volume":"11","author":"V Bikia","year":"2023","unstructured":"Bikia, V., Rovas, G. & Stergiopulos, N. Cardiac output estimated from an uncalibrated radial blood pressure waveform: Validation in an in-silico-generated population. Front. Bioeng. Biotechnol. 11, 1199726 (2023).","journal-title":"Front. Bioeng. Biotechnol."},{"key":"10492_CR18","doi-asserted-by":"publisher","first-page":"e109230","DOI":"10.1371\/journal.pone.0109230","volume":"9","author":"E Kellner","year":"2014","unstructured":"Kellner, E. et al. Blood tracer kinetics in the arterial tree. PLoS ONE 9, e109230 (2014).","journal-title":"PLoS ONE"},{"key":"10492_CR19","doi-asserted-by":"publisher","unstructured":"Sharman, J. E., Segers, P. & Chirinos, J. A. Chapter 2: Measurements of arterial pressure and flow in vivo. in Textbook of Arterial Stiffness and Pulsatile Hemodynamics in Health and Disease (ed. Chirinos, J. A.) 27\u201347 (Academic Press, 2022). https:\/\/doi.org\/10.1016\/B978-0-323-91391-1.00002-9.","DOI":"10.1016\/B978-0-323-91391-1.00002-9"},{"key":"10492_CR20","doi-asserted-by":"publisher","first-page":"H208","DOI":"10.1152\/ajpheart.00037.2009","volume":"297","author":"P Reymond","year":"2009","unstructured":"Reymond, P., Merenda, F., Perren, F., R\u00fcfenacht, D. & Stergiopulos, N. Validation of a one-dimensional model of the systemic arterial tree. Am. J. Physiol.-Heart Circulatory Physiol. 297, H208\u2013H222 (2009).","journal-title":"Am. J. Physiol.-Heart Circulatory Physiol."},{"key":"10492_CR21","doi-asserted-by":"publisher","first-page":"10775","DOI":"10.1038\/s41598-023-37622-y","volume":"13","author":"V Bikia","year":"2023","unstructured":"Bikia, V., Rovas, G., Anagnostopoulos, S. & Stergiopulos, N. On the similarity between aortic and carotid pressure diastolic decay: A mathematical modelling study. Sci. Rep. 13, 10775 (2023).","journal-title":"Sci. Rep."},{"key":"10492_CR22","doi-asserted-by":"publisher","first-page":"5913","DOI":"10.1038\/s41598-024-56137-8","volume":"14","author":"V Bikia","year":"2024","unstructured":"Bikia, V., Segers, P., Rovas, G., Anagnostopoulos, S. & Stergiopulos, N. Novel theory and potential applications of central diastolic pressure decay time constant. Sci. Rep. 14, 5913 (2024).","journal-title":"Sci. Rep."},{"key":"10492_CR23","doi-asserted-by":"publisher","first-page":"H1173","DOI":"10.1152\/ajpheart.00821.2010","volume":"301","author":"P Reymond","year":"2011","unstructured":"Reymond, P., Bohraus, Y., Perren, F., Lazeyras, F. & Stergiopulos, N. Validation of a patient-specific one-dimensional model of the systemic arterial tree. Am. J. Physiol.-Heart Circulatory Physiol. 301, H1173\u2013H1182 (2011).","journal-title":"Am. J. Physiol.-Heart Circulatory Physiol."},{"key":"10492_CR24","doi-asserted-by":"publisher","first-page":"649866","DOI":"10.3389\/fbioe.2021.649866","volume":"9","author":"V Bikia","year":"2021","unstructured":"Bikia, V., Rovas, G., Pagoulatou, S. & Stergiopulos, N. Determination of aortic characteristic impedance and total arterial compliance from regional pulse wave velocities using machine learning: An in-silico study. Front. Bioeng. Biotechnol. 9, 649866 (2021).","journal-title":"Front. Bioeng. Biotechnol."},{"key":"10492_CR25","doi-asserted-by":"publisher","first-page":"1375","DOI":"10.1038\/s41598-018-37714-0","volume":"9","author":"D Marlevi","year":"2019","unstructured":"Marlevi, D. et al. Estimation of cardiovascular relative pressure using virtual work-energy. Sci. Rep. 9, 1375 (2019).","journal-title":"Sci. Rep."},{"key":"10492_CR26","doi-asserted-by":"publisher","first-page":"H1290","DOI":"10.1152\/ajpheart.00454.2023","volume":"325","author":"J Hong","year":"2023","unstructured":"Hong, J., Nandi, M., Charlton, P. H. & Alastruey, J. Noninvasive hemodynamic indices of vascular aging: an in silico assessment. Am. J. Physiol.-Heart Circulatory Physiol. 325, H1290\u2013H1303 (2023).","journal-title":"Am. J. Physiol.-Heart Circulatory Physiol."},{"key":"10492_CR27","doi-asserted-by":"publisher","first-page":"1719","DOI":"10.1093\/eurheartj\/eht565","volume":"35","author":"CM McEniery","year":"2014","unstructured":"McEniery, C. M., Cockcroft, J. R., Roman, M. J., Franklin, S. S. & Wilkinson, I. B. Central blood pressure: Current evidence and clinical importance. Eur. Heart J. 35, 1719\u20131725 (2014).","journal-title":"Eur. Heart J."},{"key":"10492_CR28","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1038\/hr.2015.78","volume":"38","author":"P Salvi","year":"2015","unstructured":"Salvi, P., Grillo, A. & Parati, G. Noninvasive estimation of central blood pressure and analysis of pulse waves by applanation tonometry. Hypertens. Res. 38, 646\u2013648 (2015).","journal-title":"Hypertens. Res."},{"key":"10492_CR29","doi-asserted-by":"publisher","first-page":"e003053","DOI":"10.1161\/JAHA.112.003053","volume":"1","author":"Z Liao","year":"2012","unstructured":"Liao, Z. et al. Relation of carotid artery diameter with cardiac geometry and mechanics in heart failure with preserved ejection fraction. J. Am. Heart Assoc. 1, e003053 (2012).","journal-title":"J. Am. Heart Assoc."},{"key":"10492_CR30","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1097\/ALN.0000000000003553","volume":"134","author":"K Kouz","year":"2020","unstructured":"Kouz, K., Scheeren, T. W. L., de Backer, D. & Saugel, B. Pulse wave analysis to estimate cardiac output. Anesthesiology 134, 119\u2013126 (2020).","journal-title":"Anesthesiology"},{"key":"10492_CR31","doi-asserted-by":"publisher","unstructured":"Sun, J. X., Reisner, A. T., Saeed, M. & Mark, R. G. Estimating cardiac output from arterial blood pressurewaveforms: A critical evaluation using the MIMIC II database. in Computers in Cardiology, 2005 295\u2013298 (IEEE, Lyon, France, 2005). https:\/\/doi.org\/10.1109\/CIC.2005.1588095.","DOI":"10.1109\/CIC.2005.1588095"},{"key":"10492_CR32","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.bja.2020.03.013","volume":"125","author":"B Saugel","year":"2020","unstructured":"Saugel, B. et al. Continuous noninvasive pulse wave analysis using finger cuff technologies for arterial blood pressure and cardiac output monitoring in perioperative and intensive care medicine: A systematic review and meta-analysis. Br. J. Anaesth. 125, 25\u201337 (2020).","journal-title":"Br. J. Anaesth."},{"key":"10492_CR33","doi-asserted-by":"publisher","first-page":"231","DOI":"10.3389\/fmed.2017.00231","volume":"4","author":"AS Meidert","year":"2018","unstructured":"Meidert, A. S. & Saugel, B. Techniques for non-invasive monitoring of arterial blood pressure. Front. Med. 4, 231 (2018).","journal-title":"Front. Med."},{"key":"10492_CR34","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1007\/s10877-013-9540-8","volume":"28","author":"B Saugel","year":"2014","unstructured":"Saugel, B. et al. An autocalibrating algorithm for non-invasive cardiac output determination based on the analysis of an arterial pressure waveform recorded with radial artery applanation tonometry: A proof of concept pilot analysis. J. Clin. Monit. Comput. 28, 357\u2013362 (2014).","journal-title":"J. Clin. Monit. Comput."},{"key":"10492_CR35","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1109\/10.324522","volume":"41","author":"JF Martin","year":"1994","unstructured":"Martin, J. F., Volfson, L. B., Kirzon-Zolin, V. V. & Schukin, V. G. Application of pattern recognition and image classification techniques to determine continuous cardiac output from the arterial pressure waveform. IEEE Trans. Biomed. Eng. 41, 913\u2013920 (1994).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10492_CR36","unstructured":"Dabanloo, N. J., Adaei, F. & Nasrabadi, A. M. The performance of neural network in the estimation of cardiac output using arterial blood pressure waveforms. in 2011 Computing in Cardiology 145\u2013148 (2011)."},{"key":"10492_CR37","doi-asserted-by":"publisher","first-page":"S85","DOI":"10.1097\/TA.0000000000000671","volume":"79","author":"NT Liu","year":"2015","unstructured":"Liu, N. T., Kramer, G. C., Khan, M. N., Kinsky, M. P. & Salinas, J. Blood pressure and heart rate from the arterial blood pressure waveform can reliably estimate cardiac output in a conscious sheep model of multiple hemorrhages and resuscitation using computer machine learning approaches. J. Trauma Acute Care Surg. 79, S85-92 (2015).","journal-title":"J. Trauma Acute Care Surg."},{"key":"10492_CR38","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.3390\/jcm8091419","volume":"8","author":"Y-J Moon","year":"2019","unstructured":"Moon, Y.-J. et al. Deep learning-based stroke volume estimation outperforms conventional arterial contour method in patients with hemodynamic instability. J. Clin. Med. 8, 1419 (2019).","journal-title":"J. Clin. Med."},{"key":"10492_CR39","doi-asserted-by":"publisher","first-page":"5130","DOI":"10.3390\/s21155130","volume":"21","author":"H-M Kwon","year":"2021","unstructured":"Kwon, H.-M. et al. Estimation of stroke volume variance from arterial blood pressure: Using a 1-D convolutional neural network. Sensors (Basel) 21, 5130 (2021).","journal-title":"Sensors (Basel)"},{"key":"10492_CR40","doi-asserted-by":"publisher","first-page":"e24762","DOI":"10.2196\/24762","volume":"9","author":"H-L Yang","year":"2021","unstructured":"Yang, H.-L. et al. Development and validation of an arterial pressure-based cardiac output algorithm using a convolutional neural network: Retrospective study based on prospective registry data. JMIR Med. Inform. 9, e24762 (2021).","journal-title":"JMIR Med. Inform."},{"key":"10492_CR41","doi-asserted-by":"publisher","first-page":"9057","DOI":"10.3390\/s23229057","volume":"23","author":"X Xu","year":"2023","unstructured":"Xu, X., Tang, Q. & Chen, Z. Improved U-net model to estimate cardiac Output based on photoplethysmography and arterial pressure waveform. Sensors 23, 9057 (2023).","journal-title":"Sensors"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-10492-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-10492-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-10492-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T10:57:50Z","timestamp":1757242670000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-10492-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,15]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["10492"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-10492-2","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,15]]},"assertion":[{"value":"21 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25562"}}