دورية أكاديمية
أعرض في EDS

Multicenter validation of a machine learning phase space electro-mechanical pulse wave analysis to predict elevated left ventricular end diastolic pressure at the point-of-care.

التفاصيل البيبلوغرافية
العنوان: Multicenter validation of a machine learning phase space electro-mechanical pulse wave analysis to predict elevated left ventricular end diastolic pressure at the point-of-care.
المؤلفون: Bhavnani SP; Division of Cardiovascular Medicine, Healthcare Innovation & Practice Transformation Laboratory, Scripps Clinic, San Diego, California, United States of America., Khedraki R; Division of Cardiology, Section Advanced Heart Failure, Scripps Clinic, San Diego, California, United States of America., Cohoon TJ; Division of Cardiovascular Medicine, Healthcare Innovation & Practice Transformation Laboratory, Scripps Clinic, San Diego, California, United States of America., Meine FJ 3rd; Novant Health New Hanover Regional Medical Center, Wilmington, North Carolina, United States of America., Stuckey TD; Cone Health Heart and Vascular Center, Greensboro, North Carolina, United States of America., McMinn T; Austin Heart, Austin, Texas, United States of America., Depta JP; Rochester General Hospital, Rochester, New York, United States of America., Bennett B; Jackson Heart Clinic, Jackson, Mississippi, United States of America., McGarry T; Oklahoma Heart Hospital, Oklahoma City, Oklahoma, United States of America., Carroll W; Cardiology Associates of North Mississippi, Tupelo, Mississippi, United States of America., Suh D; Atlanta Heart Specialists, Atlanta, Georgia, United States of America., Steuter JA; Bryan Heart, Lincoln, Nebraska, United States of America., Roberts M; Lexington Medical Center, West Columbia, South Carolina, United States of America., Gillins HR; CorVista Health, Inc., Washington, DC, United States of America., Shadforth I; CorVista Health, Inc., Washington, DC, United States of America., Lange E; CorVista Health, Toronto, Ontario, Canada.; Analytics For Life Inc., d.b.a CorVista Health, Toronto, Canada., Doomra A; CorVista Health, Toronto, Ontario, Canada.; Analytics For Life Inc., d.b.a CorVista Health, Toronto, Canada., Firouzi M; CorVista Health, Toronto, Ontario, Canada.; Analytics For Life Inc., d.b.a CorVista Health, Toronto, Canada., Fathieh F; CorVista Health, Toronto, Ontario, Canada.; Analytics For Life Inc., d.b.a CorVista Health, Toronto, Canada., Burton T; CorVista Health, Toronto, Ontario, Canada.; Analytics For Life Inc., d.b.a CorVista Health, Toronto, Canada., Khosousi A; CorVista Health, Toronto, Ontario, Canada.; Analytics For Life Inc., d.b.a CorVista Health, Toronto, Canada., Ramchandani S; CorVista Health, Toronto, Ontario, Canada.; Analytics For Life Inc., d.b.a CorVista Health, Toronto, Canada., Sanders WE Jr; CorVista Health, Inc., Washington, DC, United States of America., Smart F; LSU Health Science Center, New Orleans, Louisiana, United States of America.
المصدر: PloS one [PLoS One] 2022 Nov 15; Vol. 17 (11), pp. e0277300. Date of Electronic Publication: 2022 Nov 15 (Print Publication: 2022).
نوع المنشور: Multicenter Study; Journal Article; Research Support, Non-U.S. Gov't
اللغة: English
بيانات الدورية: Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
أسماء مطبوعة: Original Publication: San Francisco, CA : Public Library of Science
مواضيع طبية MeSH: Ventricular Dysfunction, Left*/diagnosis, Humans ; Blood Pressure ; Point-of-Care Systems ; Pulse Wave Analysis ; Machine Learning ; Ventricular Function, Left ; Ventricular Pressure ; Stroke Volume
مستخلص: Background: Phase space is a mechanical systems approach and large-scale data representation of an object in 3-dimensional space. Whether such techniques can be applied to predict left ventricular pressures non-invasively and at the point-of-care is unknown.
Objective: This study prospectively validated a phase space machine-learned approach based on a novel electro-mechanical pulse wave method of data collection through orthogonal voltage gradient (OVG) and photoplethysmography (PPG) for the prediction of elevated left ventricular end diastolic pressure (LVEDP).
Methods: Consecutive outpatients across 15 US-based healthcare centers with symptoms suggestive of coronary artery disease were enrolled at the time of elective cardiac catheterization and underwent OVG and PPG data acquisition immediately prior to angiography with signals paired with LVEDP (IDENTIFY; NCT #03864081). The primary objective was to validate a ML algorithm for prediction of elevated LVEDP using a definition of ≥25 mmHg (study cohort) and normal LVEDP ≤ 12 mmHg (control cohort), using AUC as the measure of diagnostic accuracy. Secondary objectives included performance of the ML predictor in a propensity matched cohort (age and gender) and performance for an elevated LVEDP across a spectrum of comparative LVEDP (<12 through 24 at 1 mmHg increments). Features were extracted from the OVG and PPG datasets and were analyzed using machine-learning approaches.
Results: The study cohort consisted of 684 subjects stratified into three LVEDP categories, ≤12 mmHg (N = 258), LVEDP 13-24 mmHg (N = 347), and LVEDP ≥25 mmHg (N = 79). Testing of the ML predictor demonstrated an AUC of 0.81 (95% CI 0.76-0.86) for the prediction of an elevated LVEDP with a sensitivity of 82% and specificity of 68%, respectively. Among a propensity matched cohort (N = 79) the ML predictor demonstrated a similar result AUC 0.79 (95% CI: 0.72-0.8). Using a constant definition of elevated LVEDP and varying the lower threshold across LVEDP the ML predictor demonstrated and AUC ranging from 0.79-0.82.
Conclusion: The phase space ML analysis provides a robust prediction for an elevated LVEDP at the point-of-care. These data suggest a potential role for an OVG and PPG derived electro-mechanical pulse wave strategy to determine if LVEDP is elevated in patients with symptoms suggestive of cardiac disease.
Competing Interests: I have read the journal’s policy and authors of this manuscript have the following competing interests. Sanjeev Bhavnani MD is a scientific advisor to Corvista Health and Blumio; consultant to Bristol Meyers Squibb, Pfizer, and Infineon Semiconductor; data safety monitoring board chair at Proteus Digital; has received research support from Scripps Clinic and the Qualcomm Foundation and is member of the healthcare innovation advisory boards at the American College of Cardiology, American Society of Echocardiography, and BIOCOM (all non-profit institutions with all positions voluntary). Jeremiah P. Depta MD reports consulting fees from Edwards Lifesciences LLC, Boston Scientific, V wave Medical Ltd and Abbot. Brett Bennett MD reports payment or honoraria for lecture from Philips. Horace R. Gillins BS, Ian Shadforth EngD, Emmanuel Lange, Abhinav Doomra MScAC, Mohammad Firouzi MSc, Farhad Fathieh PhD, Timothy Burton BComp, Ali Khosousi PhD, Shyam Ramchandani PhD and William E. Sanders Jr. MD report employment by CorVista Health, and stock options in the same. Frank Smart MD reports grants or contracts from Abbot (GUIDE HF clinical trial), NIH / Ohio State (DCM genetic study), Duke Clinical Research (Transform HF), CorVista Health (Pulmonary Hypertension clinical trial), and participation on a Data Safety Monitoring Board or Advisory Board (Abbott Medical; GUIDE-HF Steering committee). All other authors report no disclosures. This does not alter our adherence to PLOS ONE policies on sharing data and materials.
(Copyright: © 2022 Bhavnani et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
References: Circulation. 1982 Dec;66(6):1159-67. (PMID: 6216024)
Circulation. 1976 May;53(5):839-47. (PMID: 1260987)
JACC Cardiovasc Imaging. 2021 Oct;14(10):1904-1915. (PMID: 34147443)
J Am Heart Assoc. 2016 Jan 25;5(1):. (PMID: 26811160)
IEEE Trans Biomed Eng. 2011 Feb;58(2):339-47. (PMID: 20693104)
JACC Cardiovasc Imaging. 2020 Jan;13(1 Pt 2):258-271. (PMID: 31202770)
Nat Med. 2019 Jan;25(1):70-74. (PMID: 30617318)
JACC Cardiovasc Imaging. 2020 Sep;13(9):2017-2035. (PMID: 32912474)
J Am Coll Cardiol. 2019 Mar 26;73(11):1317-1335. (PMID: 30898208)
J Am Coll Cardiol. 2019 Apr 23;73(15):1961-1977. (PMID: 31000000)
JACC Cardiovasc Imaging. 2021 Nov;14(11):2091-2104. (PMID: 34147456)
JACC Heart Fail. 2021 Mar;9(3):192-200. (PMID: 33422435)
Acad Emerg Med. 2016 Mar;23(3):223-42. (PMID: 26910112)
Int J Cardiol. 2020 Aug 1;312:81-86. (PMID: 32247573)
JACC Cardiovasc Imaging. 2021 Oct;14(10):1887-1900. (PMID: 34023263)
Comput Methods Programs Biomed. 2021 Apr;202:105970. (PMID: 33610035)
Int J Cardiol. 2017 Apr 15;233:61-66. (PMID: 28185703)
J Am Coll Cardiol. 2018 Apr 17;71(15):1650-1660. (PMID: 29650121)
ESC Heart Fail. 2021 Feb;8(1):566-576. (PMID: 33230957)
J Am Coll Cardiol. 2017 Nov 28;70(21):2696-2718. (PMID: 29169478)
Circ Heart Fail. 2010 Sep;3(5):617-26. (PMID: 20682947)
Eur J Heart Fail. 2017 Dec;19(12):1651-1660. (PMID: 28984057)
PLoS One. 2018 Aug 8;13(8):e0198603. (PMID: 30089110)
Stat Med. 2011 Jan 15;30(1):11-21. (PMID: 21204120)
N Engl J Med. 2002 Jul 18;347(3):161-7. (PMID: 12124404)
Clin Chem. 2015 Dec;61(12):1446-52. (PMID: 26510957)
Circulation. 2007 Mar 13;115(10):1306-24. (PMID: 17322457)
تواريخ الأحداث: Date Created: 20221115 Date Completed: 20221118 Latest Revision: 20230104
رمز التحديث: 20240628
مُعرف محوري في PubMed: PMC9665374
DOI: 10.1371/journal.pone.0277300
PMID: 36378672
قاعدة البيانات: MEDLINE
الوصف
تدمد:1932-6203
DOI:10.1371/journal.pone.0277300