1
|
Liu PY, Lin C, Lin CS, Fang WH, Lee CC, Wang CH, Tsai DJ. Artificial Intelligence-Enabled Electrocardiography Detects B-Type Natriuretic Peptide and N-Terminal Pro-Brain Natriuretic Peptide. Diagnostics (Basel) 2023; 13:2723. [PMID: 37685262 PMCID: PMC10487184 DOI: 10.3390/diagnostics13172723] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2023] [Revised: 08/18/2023] [Accepted: 08/20/2023] [Indexed: 09/10/2023] Open
Abstract
BACKGROUND: The B-type natriuretic peptide (BNP) and N-terminal pro-brain natriuretic peptide (pBNP) are predictors of cardiovascular morbidity and mortality. Since the artificial intelligence (AI)-enabled electrocardiogram (ECG) system is widely used in the management of many cardiovascular diseases (CVDs), patients requiring intensive monitoring may benefit from an AI-ECG with BNP/pBNP predictions. This study aimed to develop an AI-ECG to predict BNP/pBNP and compare their values for future mortality. METHODS: The development, tuning, internal validation, and external validation sets included 47,709, 16,249, 4001, and 6042 ECGs, respectively. Deep learning models (DLMs) were trained using a development set for estimating ECG-based BNP/pBNP (ECG-BNP/ECG-pBNP), and the tuning set was used to guide the training process. The ECGs in internal and external validation sets belonging to nonrepeating patients were used to validate the DLMs. We also followed-up all-cause mortality to explore the prognostic value. RESULTS: The DLMs accurately distinguished mild (≥500 pg/mL) and severe (≥1000 pg/mL) an abnormal BNP/pBNP with AUCs of ≥0.85 in the internal and external validation sets, which provided sensitivities of 68.0-85.0% and specificities of 77.9-86.2%. In continuous predictions, the Pearson correlation coefficient between ECG-BNP and ECG-pBNP was 0.93, and they were both associated with similar ECG features, such as the T wave axis and correct QT interval. ECG-pBNP provided a higher all-cause mortality predictive value than ECG-BNP. CONCLUSIONS: The AI-ECG can accurately estimate BNP/pBNP and may be useful for monitoring the risk of CVDs. Moreover, ECG-pBNP may be a better indicator to manage the risk of future mortality.
Collapse
Affiliation(s)
- Pang-Yen Liu
- Division of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan; (P.-Y.L.); (C.-S.L.)
| | - Chin Lin
- Medical Technology Education Center, School of Medicine, National Defense Medical Center, Taipei 114, Taiwan;
- School of Public Health, National Defense Medical Center, Taipei 114, Taiwan
- Artificial Intelligence of Things Center, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan;
| | - Chin-Sheng Lin
- Division of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan; (P.-Y.L.); (C.-S.L.)
- Medical Technology Education Center, School of Medicine, National Defense Medical Center, Taipei 114, Taiwan;
| | - Wen-Hui Fang
- Artificial Intelligence of Things Center, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan;
- Department of Family and Community Medicine, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan
| | - Chia-Cheng Lee
- Medical Informatics Office, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan;
- Division of Colorectal Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan
| | - Chih-Hung Wang
- Department of Otolaryngology–Head and Neck Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan;
- Graduate Institute of Medical Sciences, National Defense Medical Center, Taipei 114, Taiwan
| | - Dung-Jang Tsai
- Medical Technology Education Center, School of Medicine, National Defense Medical Center, Taipei 114, Taiwan;
- School of Public Health, National Defense Medical Center, Taipei 114, Taiwan
- Artificial Intelligence of Things Center, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan;
- Department of Statistics and Information Science, Fu Jen Catholic University, New Taipei City 242, Taiwan
| |
Collapse
|
4
|
Goode KM, Clark AL, Bristow JA, Sykes KB, Cleland JG. Screening for left ventricular systolic dysfunction in high-risk patients in primary-care: A cost-benefit analysis. Eur J Heart Fail 2008; 9:1186-95. [DOI: 10.1016/j.ejheart.2007.10.003] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/09/2007] [Revised: 09/24/2007] [Accepted: 10/11/2007] [Indexed: 11/29/2022] Open
Affiliation(s)
- Kevin M. Goode
- Department of Cardiology; Castle Hill Hospital; Kingston-upon-Hull United Kingdom
| | - Andrew L. Clark
- Department of Cardiology; Castle Hill Hospital; Kingston-upon-Hull United Kingdom
| | - Janet A. Bristow
- Department of Cardiology; Castle Hill Hospital; Kingston-upon-Hull United Kingdom
| | - Kim B. Sykes
- Department of Cardiology; Castle Hill Hospital; Kingston-upon-Hull United Kingdom
| | - John G.F. Cleland
- Department of Cardiology; Castle Hill Hospital; Kingston-upon-Hull United Kingdom
| |
Collapse
|
7
|
Zuber M, Attenhofer Jost CH, Kipfer P, Collins SP, Michota F, Peacock WF. Acoustic cardiography augments prolonged QRS duration for detecting left ventricular dysfunction. Ann Noninvasive Electrocardiol 2008; 12:316-28. [PMID: 17970957 DOI: 10.1111/j.1542-474x.2007.00181.x] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/29/2022] Open
Abstract
BACKGROUND Prolonged QRS duration has been used as a marker for left ventricular (LV) systolic dysfunction (SD) and is used in the evaluation of patients presenting with known or suspected heart failure. The goal of this study was to compare the abilities of QRS duration and simultaneous digital ECG and heart sounds, that is acoustic cardiographic, parameters to identify patients with LV dysfunction. METHODS Our learning population consisted of 171 patients with possible chronic compensated or mildly decompensated heart failure who presented to an ambulatory cardiology clinic for echocardiographic examination. We defined LVSD as a LV ejection fraction < 50%, and estimated LV filling pressures from diastolic measurements. These patients also had acoustic cardiographic recordings from which we obtained a variety of individual ECG and acoustic cardiographic parameters. We used the product of four of these parameters to obtain a diagnostic score for LV dysfunction. We then compared the diagnostic performances of QRS duration and the score on a test population of patients who presented to an emergency department with possible heart failure. RESULTS In the learning population, the sensitivities/specificities of QRS duration > or =120 ms and the score for prediction of LVSD were 51%/92% and 77%/90%, respectively. In the test population, the score remained superior to QRS duration for detecting LVSD as well as acute decompensated heart failure. CONCLUSIONS Improved identification of LVSD and clinical heart failure can be achieved with a cost-effective bedside screening tool with the simple combination of simultaneously acquired digital ECG and heart sound data.
Collapse
Affiliation(s)
- Michel Zuber
- Cardiology Outpatient Clinic, Othmarsingen and Frauenfeld, Switzerland.
| | | | | | | | | | | |
Collapse
|
8
|
Ewald B, Ewald D, Thakkinstian A, Attia J. Meta-analysis of B type natriuretic peptide and N-terminal pro B natriuretic peptide in the diagnosis of clinical heart failure and population screening for left ventricular systolic dysfunction. Intern Med J 2007; 38:101-13. [DOI: 10.1111/j.1445-5994.2007.01454.x] [Citation(s) in RCA: 83] [Impact Index Per Article: 4.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
9
|
Khan NK, Goode KM, Cleland JGF, Rigby AS, Freemantle N, Eastaugh J, Clark AL, de Silva R, Calvert MJ, Swedberg K, Komajda M, Mareev V, Follath F. Prevalence of ECG abnormalities in an international survey of patients with suspected or confirmed heart failure at death or discharge. Eur J Heart Fail 2007; 9:491-501. [PMID: 17218150 DOI: 10.1016/j.ejheart.2006.11.003] [Citation(s) in RCA: 66] [Impact Index Per Article: 3.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/05/2006] [Revised: 10/05/2006] [Accepted: 11/13/2006] [Indexed: 11/24/2022] Open
Abstract
BACKGROUND Most patients suspected of having heart failure (HF) will get a 12-lead electrocardiogram (ECG) but its utility for excluding HF or assisting in its management has rarely been investigated. METHODS The EuroHeart Failure survey identified 11,327 patients hospitalised with a suspected diagnosis of HF from 115 hospitals in 24 countries. ECGs were obtained from 9315 patients, of whom 5934 had cardiac imaging tests. The utility of the ECG was assessed for excluding or diagnosing major structural heart disease (MSHD) or major left ventricular systolic dysfunction (MLVSD) and for therapeutic decision making. FINDINGS MSHD was present in 70% and MLVSD in 54% of patients overall but in only 21% and 5%, respectively, if the ECG was entirely normal. However, <2% of patients had a normal ECG. No single ECG characteristic identified a probability <25% of MSHD or <20% of MLVSD. Patients with QRS width >or=120 ms or anterior pathological Q-waves had a probability >80% of MSHD and >70% of MLVSD. Diagnostic models suggested that electrocardiographic criteria alone were not accurate for the diagnosis or exclusion of important heart disease in this population. However, 2468 patients (42%) had an electrocardiographic finding that should be used to guide the choice of therapy. CONCLUSIONS A normal ECG is rare in patients with suspected HF but has limited diagnostic value in this setting. The ECG has an important role in guiding therapy.
Collapse
Affiliation(s)
- Nasrin K Khan
- University of Hull, Kingston upon Hull, United Kingdom
| | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
10
|
Abstract
Structural heart disease, electrical instability, and increased sympathetic activity can generate a number of specific and nonspecific ECG changes and arrhythmias in patients with congestive heart failure (CHF). This review describes direct alterations of the P-QRS-T complex and ECG-derived parameters in CHF, together with the significance of cardiac arrhythmias, markers of atrial and ventricular electrical instability, and the parameters of sympathetic nervous system activity.
Collapse
Affiliation(s)
- Vinzenz Hombach
- Department of Internal Medicine II, University Hospital of Ulm, Robet-Koch Strasse 8, Ulm D-89081, Germany.
| |
Collapse
|
11
|
Sakhuja R, Chen AA, Anwaruddin S, Baggish AL, Januzzi JL. Combined use of amino terminal-pro-brain natriuretic peptide levels and QRS duration to predict left ventricular systolic dysfunction in patients with dyspnea. Am J Cardiol 2005; 96:263-6. [PMID: 16018854 DOI: 10.1016/j.amjcard.2005.03.056] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/10/2004] [Revised: 03/03/2005] [Accepted: 03/03/2005] [Indexed: 11/15/2022]
Abstract
The combination of elevated amino-terminal pro-brain natriuretic peptide levels and wide QRS duration was highly sensitive and specific for the prediction of impaired left ventricular systolic function among a group of patients presenting with dyspnea to the emergency department. This strategy can be used to predict depressed function and target more formal evaluation with echocardiography in patients with dyspnea.
Collapse
Affiliation(s)
- Rahul Sakhuja
- Cardiology Division, and Department of Medicine, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | | | | | | | | |
Collapse
|