{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:45:47Z","timestamp":1766159147231,"version":"3.41.2"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T00:00:00Z","timestamp":1686009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:p>One of the crucial steps in assessing hemodynamic parameters using impedance cardiography (ICG) is the detection of the characteristic points in the dZ\/dt ICG complex, especially the X point. The most often estimated parameters from the ICG complex are stroke volume and cardiac output, for which is required the left ventricular pre-ejection time. Unfortunately, for beat-to-beat calculations, the accuracy of detection is affected by the variability of the ICG complex subtypes. Thus, in this work, we aim to create a predictive model that can predict the missing points and decrease the previous work percentages of missing points to support the detection of ICG characteristic points and the extraction of hemodynamic parameters according to several existing subtypes. Thus, a time-series non-linear autoregressive model with exogenous inputs (NARX) feedback neural network approach was implemented to forecast the missing ICG points according to the different existing subtypes. The NARX was trained on two different datasets with an open-loop mode to ensure that the network is fed with correct feedback inputs. Once the training is satisfactory, the loop can be closed for multi-step prediction tests and simulation. The results show that we can predict the missing characteristic points in all the complexes with a success rate ranging between 75% and 88% in the evaluated datasets. Previously, without the NARX predictive model, the successful detection rate was 21%\u201330% for the same datasets. Thus, this work indicates a promising method and an accuracy increase in the detection of X, Y, O, and Z points for both datasets.<\/jats:p>","DOI":"10.3389\/fphys.2023.1181745","type":"journal-article","created":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T20:17:17Z","timestamp":1686082637000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Time-series NARX feedback neural network for forecasting impedance cardiography ICG missing points: a predictive model"],"prefix":"10.3389","volume":"14","author":[{"given":"Sara","family":"Benouar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Malika","family":"Kedir-Talha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando","family":"Seoane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,6,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"72","DOI":"10.2478\/joeb-2018-0012","article-title":"Systematic variability in ICG recordings results in ICG complex subtypes\u2013steps towards the enhancement of ICG characterization","volume":"9","author":"Benouar","year":"2018","journal-title":"J. Electr. Bioimpedance"},{"key":"B2","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/BF02344724","article-title":"Stroke volume equation for impedance cardiography","volume":"43","author":"Bernstein","year":"2005","journal-title":"Med. Biol. Eng. Comput."},{"key":"B3","unstructured":"Biopac AcqKnowledge impedance2018"},{"key":"B4","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/978-3-642-11987-3_3","article-title":"Ambulatory impedance cardiography","volume-title":"Ambulatory impedance cardiography","author":"Cybulski","year":"2011"},{"key":"B5","article-title":"A new algorithm for improved detection of aortic valve opening by impedance cardiography","volume-title":"Computers in cardiology","author":"DeMarzo","year":"1996"},{"key":"B6","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1111\/j.1751-7141.2008.00012.x","article-title":"Using impedance cardiography to detect subclinical cardiovascular disease in women with multiple risk factors: A pilot study","volume":"12","author":"DeMarzo","year":"2009","journal-title":"Prev. Cardiol."},{"key":"B7","first-page":"69","article-title":"Stroke volume optimization after cardiac surgery: A comparison between cardiac output derived from arterial pressure waveform analysis and thermodilution","volume":"49","author":"Guinot","year":"2019","journal-title":"J. Crit. Care"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1883","DOI":"10.1109\/JBHI.2017.2783949","article-title":"Full impedance cardiography measurement device using Raspberry PI3 and system-on-chip biomedical instrumentation solutions","volume":"22","author":"Hafid","year":"2017","journal-title":"IEEE J. Biomed. health Inf."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2018\/3269534","article-title":"Simultaneous recording of ICG and ECG using Z-RPI device with minimum number of electrodes","volume":"2018","author":"Hafid","year":"2018","journal-title":"J. Sensors"},{"key":"B10","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/0301-0511(93)90080-r","article-title":"Comparative measures of systolic ejection during treadmill exercise by impedance cardiography and Doppler echocardiography","volume":"36","author":"Kizakevich","year":"1993","journal-title":"Biol. Psychol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1046\/j.1475-097x.2003.00465.x","article-title":"invasive assessment of arterial stiffness and haemodynamics\u2013a validation study","volume":"23","author":"K\u00f6\u00f6bi","year":"2003","journal-title":"Clin. Physiol. Funct. imaging"},{"key":"B12","first-page":"1208","article-title":"Development and evaluation of an impedance cardiac output system","volume":"37","author":"Kubicek","year":"1966","journal-title":"Aerosp. Med."},{"key":"B13","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1111\/j.1749-6632.1970.tb17735.x","article-title":"Impedance cardiography as a noninvasive method of monitoring cardiac function and other parameters of the cardiovascular system","volume":"170","author":"Kubicek","year":"1970","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"B14","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1161\/01.cir.41.4.651","article-title":"The first derivative thoracic impedance cardiogram","volume":"41","author":"Lababidi","year":"1970","journal-title":"Circulation"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.envsoft.2016.02.004","article-title":"Assessing spatial predictive models in the environmental sciences: Accuracy measures, data variation and variance explained","volume":"80","author":"Li","year":"2016","journal-title":"Environ. Model. Softw."},{"key":"B16","doi-asserted-by":"publisher","first-page":"e0183250","DOI":"10.1371\/journal.pone.0183250","article-title":"Assessing the accuracy of predictive models for numerical data: Not r nor r2, why not? Then what?","volume":"12","author":"Li","year":"2017","journal-title":"PloS one"},{"key":"B17","doi-asserted-by":"publisher","first-page":"45","DOI":"10.5617\/jeb.542","article-title":"Textrode-enabled transthoracic electrical bioimpedance measurements\u2013towards wearable applications of impedance cardiography","volume":"4","author":"Marquez","year":"2013","journal-title":"J. Electr. Bioimpedance"},{"key":"B18","doi-asserted-by":"publisher","first-page":"S383","DOI":"10.1088\/0967-3334\/29\/6\/S32","article-title":"Method to measure autonomic control of cardiac function using time interval parameters from impedance cardiography","volume":"29","author":"Meijer","year":"2008","journal-title":"Physiol. Meas."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1063\/1.1719283","article-title":"Alternate approach to the resolution of tunneling current structure by differentiation","volume":"35","author":"Patterson","year":"1964","journal-title":"Rev. Sci. Instrum."},{"volume-title":"Python machine learning: Machine learning and deep learning with Python, scikit-learn, and TensorFlow 2","year":"2019","author":"Raschka","key":"B20"},{"article-title":"On the feasibility of textrodes for impedance cardiography","year":"2011","author":"Rempfler","key":"B21"},{"key":"B22","doi-asserted-by":"publisher","first-page":"467","DOI":"10.3758\/bf03195525","article-title":"Large-scale ensemble averaging of ambulatory impedance cardiograms","volume":"35","author":"Riese","year":"2003","journal-title":"Behav. Res. Methods, Instrum. Comput."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/j.1469-8986.1990.tb02171.x","article-title":"Methodological guidelines for impedance cardiography","volume":"27","author":"Sherwood","year":"1990","journal-title":"Psychophysiology"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2365","DOI":"10.1152\/jappl.1998.85.6.2365","article-title":"Ambulatory impedance cardiography: A feasibility study","volume":"85","author":"Sherwood","year":"1998","journal-title":"J. Appl. Physiology"},{"key":"B25","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1111\/j.1553-2712.2003.tb00054.x","article-title":"Bench to bedside: Electrophysiologic and clinical principles of noninvasive hemodynamic monitoring using impedance cardiography","volume":"10","author":"Summers","year":"2003","journal-title":"Acad. Emerg. Med."},{"key":"B26","doi-asserted-by":"publisher","first-page":"139","DOI":"10.2478\/joeb-2019-0020","article-title":"Age-related differences in the morphology of the impedance cardiography signal","volume":"10","author":"Tronstad","year":"2019","journal-title":"J. Electr. Bioimpedance"},{"key":"B27","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/s11886-006-0031-0","article-title":"Impedance cardiography: More questions than answers","volume":"3","author":"Wang","year":"2006","journal-title":"Curr. heart Fail. Rep."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2023.1181745\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T20:17:22Z","timestamp":1686082642000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2023.1181745\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,6]]},"references-count":27,"alternative-id":["10.3389\/fphys.2023.1181745"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2023.1181745","relation":{},"ISSN":["1664-042X"],"issn-type":[{"type":"electronic","value":"1664-042X"}],"subject":[],"published":{"date-parts":[[2023,6,6]]},"article-number":"1181745"}}