1
|
Liu SX, Yu SQ, Yang KJ, Liu JY, Yang F, Li Y, Yao CL, Zhao GS, Sun FZ. Establishment and effectiveness evaluation of pre-test probability model of coronary heart disease combined with cardiopulmonary exercise test indexes. Sci Rep 2023; 13:16411. [PMID: 37775542 PMCID: PMC10541865 DOI: 10.1038/s41598-023-41884-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2023] [Accepted: 09/01/2023] [Indexed: 10/01/2023] Open
Abstract
To establish a pre-test probability model of coronary heart disease (CHD) combined with cardiopulmonary exercise test (CPET) indexes and to compare the clinical effectiveness with Duke clinical score (DCS) and updated Diamond-Forrester model (UDFM), thus further explore the predictive value. 342 cases were used to establish the prediction model equation and another 80 cases were used to verify the effectiveness. The patients were divided into CHD group (n = 157) and non-CHD group (n = 185) according to coronary artery stenosis degree >50% or not. Combining DCS and UDFM as reference models with CPET indexes, a multivariate logistic regression model was established. The area under the ROC curve of the three models were calculated to compare the predictive effectiveness. There were significant differences in gender, chest pain type, myocardial infarction history, hypertension history, smoking, pathological Q wave and ST-T change between two groups (P < 0.01), as well as age, LVEF, heart rate at anaerobic domain, peak oxygen uptake in kilograms of body weight, percentage of peak oxygen uptake to the predicted value, the oxygen uptake efficiency slope and carbon dioxide ventilation equivalent slope (P < 0.05). Multivariate analysis showed gender, age, chest pain type, myocardial infarction history, hypertension history, smoking, pathological Q wave, ST-T change, and peak oxygen pulse were independent risk factors of CHD. The pre-test probability model of CHD combined with CPET indexes has good distinguish and calibrate ability, its prediction accuracy is slightly better than DCS and UDFM, which still needs to be verified externally in more samples.
Collapse
Affiliation(s)
- Si Xu Liu
- Heart Center, Affiliated Zhongshan Hospital of Dalian University, No.6 Jie Fang Street, Zhongshan District, Dalian, 116001, Liaoning Province, China
| | - Sheng Qin Yu
- Heart Center, Affiliated Zhongshan Hospital of Dalian University, No.6 Jie Fang Street, Zhongshan District, Dalian, 116001, Liaoning Province, China
| | - Kai Jing Yang
- Heart Center, Affiliated Zhongshan Hospital of Dalian University, No.6 Jie Fang Street, Zhongshan District, Dalian, 116001, Liaoning Province, China
| | - Ji Yi Liu
- Heart Center, Affiliated Zhongshan Hospital of Dalian University, No.6 Jie Fang Street, Zhongshan District, Dalian, 116001, Liaoning Province, China
| | - Fan Yang
- Heart Center, Affiliated Zhongshan Hospital of Dalian University, No.6 Jie Fang Street, Zhongshan District, Dalian, 116001, Liaoning Province, China
| | - Ye Li
- Heart Center, Affiliated Zhongshan Hospital of Dalian University, No.6 Jie Fang Street, Zhongshan District, Dalian, 116001, Liaoning Province, China
| | - Chang Li Yao
- Heart Center, Affiliated Zhongshan Hospital of Dalian University, No.6 Jie Fang Street, Zhongshan District, Dalian, 116001, Liaoning Province, China
| | - Guang Sheng Zhao
- Minimally invasive interventional diagnosis and treatment center, Affiliated Zhongshan Hospital of Dalian University, No.6 Jie Fang Street, Zhongshan District, Dalian, 116001, Liaoning Province, China.
| | - Feng Zhi Sun
- Heart Center, Affiliated Zhongshan Hospital of Dalian University, No.6 Jie Fang Street, Zhongshan District, Dalian, 116001, Liaoning Province, China.
| |
Collapse
|
2
|
Mincarone P, Bodini A, Tumolo MR, Vozzi F, Rocchiccioli S, Pelosi G, Caselli C, Sabina S, Leo CG. Discrimination capability of pretest probability of stable coronary artery disease: a systematic review and meta-analysis suggesting how to improve validation procedures. BMJ Open 2021; 11:e047677. [PMID: 34244268 PMCID: PMC8268916 DOI: 10.1136/bmjopen-2020-047677] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/27/2022] Open
Abstract
OBJECTIVE Externally validated pretest probability models for risk stratification of subjects with chest pain and suspected stable coronary artery disease (CAD), determined through invasive coronary angiography or coronary CT angiography, are analysed to characterise the best validation procedures in terms of discriminatory ability, predictive variables and method completeness. DESIGN Systematic review and meta-analysis. DATA SOURCES Global Health (Ovid), Healthstar (Ovid) and MEDLINE (Ovid) searched on 22 April 2020. ELIGIBILITY CRITERIA We included studies validating pretest models for the first-line assessment of patients with chest pain and suspected stable CAD. Reasons for exclusion: acute coronary syndrome, unstable chest pain, a history of myocardial infarction or previous revascularisation; models referring to diagnostic procedures different from the usual practices of the first-line assessment; univariable models; lack of quantitative discrimination capability. METHODS Eligibility screening and review were performed independently by all the authors. Disagreements were resolved by consensus among all the authors. The quality assessment of studies conforms to the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). A random effects meta-analysis of area under the receiver operating characteristic curve (AUC) values for each validated model was performed. RESULTS 27 studies were included for a total of 15 models. Besides age, sex and symptom typicality, other risk factors are smoking, hypertension, diabetes mellitus and dyslipidaemia. Only one model considers genetic profile. AUC values range from 0.51 to 0.81. Significant heterogeneity (p<0.003) was found in all but two cases (p>0.12). Values of I2 >90% for most analyses and not significant meta-regression results undermined relevant interpretations. A detailed discussion of individual results was then carried out. CONCLUSIONS We recommend a clearer statement of endpoints, their consistent measurement both in the derivation and validation phases, more comprehensive validation analyses and the enhancement of threshold validations to assess the effects of pretest models on clinical management. PROSPERO REGISTRATION NUMBER CRD42019139388.
Collapse
Affiliation(s)
- Pierpaolo Mincarone
- Institute for Research on Population and Social Policies, National Research Council, Brindisi, Italy
| | - Antonella Bodini
- Institute for Applied Mathematics and Information Technologies "Enrico Magenes", National Research Council, Milan, Italy
| | - Maria Rosaria Tumolo
- Institute for Research on Population and Social Policies, National Research Council, Brindisi, Italy
| | - Federico Vozzi
- Institute of Clinical Physiology, National Research Council, Pisa, Italy
| | | | - Gualtiero Pelosi
- Institute of Clinical Physiology, National Research Council, Pisa, Italy
| | - Chiara Caselli
- Institute of Clinical Physiology, National Research Council, Pisa, Italy
| | - Saverio Sabina
- Institute of Clinical Physiology, National Research Council, Lecce, Italy
| | - Carlo Giacomo Leo
- Institute of Clinical Physiology, National Research Council, Lecce, Italy
| |
Collapse
|
3
|
Yamagishi M, Tamaki N, Akasaka T, Ikeda T, Ueshima K, Uemura S, Otsuji Y, Kihara Y, Kimura K, Kimura T, Kusama Y, Kumita S, Sakuma H, Jinzaki M, Daida H, Takeishi Y, Tada H, Chikamori T, Tsujita K, Teraoka K, Nakajima K, Nakata T, Nakatani S, Nogami A, Node K, Nohara A, Hirayama A, Funabashi N, Miura M, Mochizuki T, Yokoi H, Yoshioka K, Watanabe M, Asanuma T, Ishikawa Y, Ohara T, Kaikita K, Kasai T, Kato E, Kamiyama H, Kawashiri M, Kiso K, Kitagawa K, Kido T, Kinoshita T, Kiriyama T, Kume T, Kurata A, Kurisu S, Kosuge M, Kodani E, Sato A, Shiono Y, Shiomi H, Taki J, Takeuchi M, Tanaka A, Tanaka N, Tanaka R, Nakahashi T, Nakahara T, Nomura A, Hashimoto A, Hayashi K, Higashi M, Hiro T, Fukamachi D, Matsuo H, Matsumoto N, Miyauchi K, Miyagawa M, Yamada Y, Yoshinaga K, Wada H, Watanabe T, Ozaki Y, Kohsaka S, Shimizu W, Yasuda S, Yoshino H. JCS 2018 Guideline on Diagnosis of Chronic Coronary Heart Diseases. Circ J 2021; 85:402-572. [PMID: 33597320 DOI: 10.1253/circj.cj-19-1131] [Citation(s) in RCA: 40] [Impact Index Per Article: 13.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/10/2023]
Affiliation(s)
| | - Nagara Tamaki
- Department of Radiology, Kyoto Prefectural University of Medicine Graduate School
| | - Takashi Akasaka
- Department of Cardiovascular Medicine, Wakayama Medical University
| | - Takanori Ikeda
- Department of Cardiovascular Medicine, Toho University Graduate School
| | - Kenji Ueshima
- Center for Accessing Early Promising Treatment, Kyoto University Hospital
| | - Shiro Uemura
- Department of Cardiology, Kawasaki Medical School
| | - Yutaka Otsuji
- Second Department of Internal Medicine, University of Occupational and Environmental Health, Japan
| | - Yasuki Kihara
- Department of Cardiovascular Medicine, Hiroshima University Graduate School of Biomedical and Health Sciences
| | - Kazuo Kimura
- Division of Cardiology, Yokohama City University Medical Center
| | - Takeshi Kimura
- Department of Cardiovascular Medicine, Kyoto University Graduate School
| | | | | | - Hajime Sakuma
- Department of Radiology, Mie University Graduate School
| | | | - Hiroyuki Daida
- Department of Cardiovascular Medicine, Juntendo University Graduate School
| | | | - Hiroshi Tada
- Department of Cardiovascular Medicine, University of Fukui
| | | | - Kenichi Tsujita
- Department of Cardiovascular Medicine, Graduate School of Medical Sciences, Kumamoto University
| | | | - Kenichi Nakajima
- Department of Functional Imaging and Artificial Intelligence, Kanazawa Universtiy
| | | | - Satoshi Nakatani
- Division of Functional Diagnostics, Department of Health Sciences, Osaka University Graduate School of Medicine
| | | | - Koichi Node
- Department of Cardiovascular Medicine, Saga University
| | - Atsushi Nohara
- Division of Clinical Genetics, Ishikawa Prefectural Central Hospital
| | | | | | - Masaru Miura
- Department of Cardiology, Tokyo Metropolitan Children's Medical Center
| | | | | | | | - Masafumi Watanabe
- Department of Cardiology, Pulmonology, and Nephrology, Yamagata University
| | - Toshihiko Asanuma
- Division of Functional Diagnostics, Department of Health Sciences, Osaka University Graduate School
| | - Yuichi Ishikawa
- Department of Pediatric Cardiology, Fukuoka Children's Hospital
| | - Takahiro Ohara
- Division of Community Medicine, Tohoku Medical and Pharmaceutical University
| | - Koichi Kaikita
- Department of Cardiovascular Medicine, Graduate School of Medical Sciences, Kumamoto University
| | - Tokuo Kasai
- Department of Cardiology, Uonuma Kinen Hospital
| | - Eri Kato
- Department of Cardiovascular Medicine, Department of Clinical Laboratory, Kyoto University Hospital
| | | | - Masaaki Kawashiri
- Department of Cardiovascular and Internal Medicine, Kanazawa University
| | - Keisuke Kiso
- Department of Diagnostic Radiology, Tohoku University Hospital
| | - Kakuya Kitagawa
- Department of Advanced Diagnostic Imaging, Mie University Graduate School
| | - Teruhito Kido
- Department of Radiology, Ehime University Graduate School
| | | | | | | | - Akira Kurata
- Department of Radiology, Ehime University Graduate School
| | - Satoshi Kurisu
- Department of Cardiovascular Medicine, Hiroshima University Graduate School of Biomedical and Health Sciences
| | - Masami Kosuge
- Division of Cardiology, Yokohama City University Medical Center
| | - Eitaro Kodani
- Department of Internal Medicine and Cardiology, Nippon Medical School Tama Nagayama Hospital
| | - Akira Sato
- Department of Cardiology, University of Tsukuba
| | - Yasutsugu Shiono
- Department of Cardiovascular Medicine, Wakayama Medical University
| | - Hiroki Shiomi
- Department of Cardiovascular Medicine, Kyoto University Graduate School
| | - Junichi Taki
- Department of Nuclear Medicine, Kanazawa University
| | - Masaaki Takeuchi
- Department of Laboratory and Transfusion Medicine, Hospital of the University of Occupational and Environmental Health, Japan
| | | | - Nobuhiro Tanaka
- Department of Cardiology, Tokyo Medical University Hachioji Medical Center
| | - Ryoichi Tanaka
- Department of Reconstructive Oral and Maxillofacial Surgery, Iwate Medical University
| | | | | | - Akihiro Nomura
- Innovative Clinical Research Center, Kanazawa University Hospital
| | - Akiyoshi Hashimoto
- Department of Cardiovascular, Renal and Metabolic Medicine, Sapporo Medical University
| | - Kenshi Hayashi
- Department of Cardiovascular Medicine, Kanazawa University Hospital
| | - Masahiro Higashi
- Department of Radiology, National Hospital Organization Osaka National Hospital
| | - Takafumi Hiro
- Division of Cardiology, Department of Medicine, Nihon University
| | | | - Hitoshi Matsuo
- Department of Cardiovascular Medicine, Gifu Heart Center
| | - Naoya Matsumoto
- Division of Cardiology, Department of Medicine, Nihon University
| | | | | | | | - Keiichiro Yoshinaga
- Department of Diagnostic and Therapeutic Nuclear Medicine, Molecular Imaging at the National Institute of Radiological Sciences
| | - Hideki Wada
- Department of Cardiology, Juntendo University Shizuoka Hospital
| | - Tetsu Watanabe
- Department of Cardiology, Pulmonology, and Nephrology, Yamagata University
| | - Yukio Ozaki
- Department of Cardiology, Fujita Medical University
| | - Shun Kohsaka
- Department of Cardiology, Keio University School of Medicine
| | - Wataru Shimizu
- Department of Cardiovascular Medicine, Nippon Medical School
| | - Satoshi Yasuda
- Department of Cardiovascular Medicine, Tohoku University Graduate School of Medicine
| | | | | |
Collapse
|
4
|
Prospective validation of an acoustic-based system for the detection of obstructive coronary artery disease in a high-prevalence population. Heart Vessels 2021; 36:1132-1140. [PMID: 33582860 DOI: 10.1007/s00380-021-01800-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/13/2020] [Accepted: 01/29/2021] [Indexed: 11/27/2022]
Abstract
Recent guidelines recommend a risk-adjusted, non-invasive work-up in patients presenting with chest discomfort to exclude coronary artery disease (CAD). However, a risk-adjusted diagnostic approach remains challenging in clinical practice. An acoustic detection device for analyzing micro-bruits induced by stenosis-generated turbulence in the coronary circulation has shown potential for ruling out CAD in patients with low-to-intermediate likelihood. We examined the diagnostic value of this acoustic detection system in a high-prevalence cohort. In total, 226 patients scheduled for clinically indicated invasive coronary angiography (ICA) were prospectively enrolled at two centers and examined using a portable, acoustic detection system. The acoustic analysis was performed in double-blinded fashion prior to quantitative ICA and following percutaneous coronary intervention (PCI). An acoustic detection result (CAD score) was obtained in 94% of all patients. The mean baseline CAD score was 41.2 ± 11.9 in patients with obstructive CAD and 33.8 ± 13.4 in patients without obstructive CAD (p < 0.001). ROC analysis revealed an AUC of 0.661 (95% CI 0.584-0.737). Sensitivity was 97.6% (95% confidence interval (CI) 91.5-99.7%), specificity was 14.5% (CI 9.0-21.7%), negative predictive value was 90.5% (CI 69.6-98.8%), and positive predictive value was 41.7% (CI 34.6-49.0%). Following PCI, the mean CAD score decreased from 40.5 ± 11.2 to 38.3 ± 13.7 (p = 0.039). Using an acoustic detection device identified individuals with CAD in a high-prevalence cohort with high sensitivity but relatively low specificity. The negative predictive value was within the predicted range and may be of value for a fast rule-out of obstructive CAD even in a high-prevalence population.
Collapse
|
5
|
Alizadehsani R, Khosravi A, Roshanzamir M, Abdar M, Sarrafzadegan N, Shafie D, Khozeimeh F, Shoeibi A, Nahavandi S, Panahiazar M, Bishara A, Beygui RE, Puri R, Kapadia S, Tan RS, Acharya UR. Coronary artery disease detection using artificial intelligence techniques: A survey of trends, geographical differences and diagnostic features 1991-2020. Comput Biol Med 2020; 128:104095. [PMID: 33217660 DOI: 10.1016/j.compbiomed.2020.104095] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2020] [Revised: 10/24/2020] [Accepted: 10/24/2020] [Indexed: 02/06/2023]
Abstract
While coronary angiography is the gold standard diagnostic tool for coronary artery disease (CAD), but it is associated with procedural risk, it is an invasive technique requiring arterial puncture, and it subjects the patient to radiation and iodinated contrast exposure. Artificial intelligence (AI) can provide a pretest probability of disease that can be used to triage patients for angiography. This review comprehensively investigates published papers in the domain of CAD detection using different AI techniques from 1991 to 2020, in order to discern broad trends and geographical differences. Moreover, key decision factors affecting CAD diagnosis are identified for different parts of the world by aggregating the results from different studies. In this study, all datasets that have been used for the studies for CAD detection, their properties, and achieved performances using various AI techniques, are presented, compared, and analyzed. In particular, the effectiveness of machine learning (ML) and deep learning (DL) techniques to diagnose and predict CAD are reviewed. From PubMed, Scopus, Ovid MEDLINE, and Google Scholar search, 500 papers were selected to be investigated. Among these selected papers, 256 papers met our criteria and hence were included in this study. Our findings demonstrate that AI-based techniques have been increasingly applied for the detection of CAD since 2008. AI-based techniques that utilized electrocardiography (ECG), demographic characteristics, symptoms, physical examination findings, and heart rate signals, reported high accuracy for the detection of CAD. In these papers, the authors ranked the features based on their assessed clinical importance with ML techniques. The results demonstrate that the attribution of the relative importance of ML features for CAD diagnosis is different among countries. More recently, DL methods have yielded high CAD detection performance using ECG signals, which drives its burgeoning adoption.
Collapse
Affiliation(s)
- Roohallah Alizadehsani
- Institute for Intelligent Systems Research and Innovations (IISRI), Deakin University, Geelong, Australia
| | - Abbas Khosravi
- Institute for Intelligent Systems Research and Innovations (IISRI), Deakin University, Geelong, Australia
| | - Mohamad Roshanzamir
- Department of Engineering, Fasa Branch, Islamic Azad University, Post Box No 364, Fasa, Fars, 7461789818, Iran
| | - Moloud Abdar
- Institute for Intelligent Systems Research and Innovations (IISRI), Deakin University, Geelong, Australia
| | - Nizal Sarrafzadegan
- Isfahan Cardiovascular Research Center, Cardiovascular Research Institute, Isfahan University of Medical Sciences, Khorram Ave, Isfahan, Iran; Faculty of Medicine, SPPH, University of British Columbia, Vancouver, BC, Canada.
| | - Davood Shafie
- Heart Failure Research Center, Cardiovascular Research Institute, Isfahan University of Medical Sciences, Isfahan, Iran
| | - Fahime Khozeimeh
- Institute for Intelligent Systems Research and Innovations (IISRI), Deakin University, Geelong, Australia
| | - Afshin Shoeibi
- Computer Engineering Department, Ferdowsi University of Mashhad, Mashhad, Iran; Faculty of Electrical and Computer Engineering, Biomedical Data Acquisition Lab, K. N. Toosi University of Technology, Tehran, Iran
| | - Saeid Nahavandi
- Institute for Intelligent Systems Research and Innovations (IISRI), Deakin University, Geelong, Australia
| | - Maryam Panahiazar
- Institute for Computational Health Sciences, University of California, San Francisco, USA
| | - Andrew Bishara
- Department of Anesthesia and Perioperative Care, University of California, San Francisco, USA
| | - Ramin E Beygui
- Cardiovascular Surgery Division, Department of Surgery, University of California, San Francisco, CA, USA
| | - Rishi Puri
- Department of Cardiovascular Medicine, Cleveland Clinic, OH, USA
| | - Samir Kapadia
- Department of Cardiovascular Medicine, Cleveland Clinic, OH, USA
| | - Ru-San Tan
- Department of Cardiology, National Heart Centre Singapore, Singapore
| | - U Rajendra Acharya
- Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore; Department of Biomedical Engineering, School of Science and Technology, Singapore University of Social Sciences, Singapore; Department of Bioinformatics and Medical Engineering, Asia University, Taiwan
| |
Collapse
|
6
|
Impact of sex-specific differences in calculating the pretest probability of obstructive coronary artery disease in symptomatic patients: a coronary computed tomographic angiography study. Coron Artery Dis 2020; 30:124-130. [PMID: 30629000 PMCID: PMC6369895 DOI: 10.1097/mca.0000000000000696] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
Objectives Little is known about the impact of sex-specific differences in calculating the pretest probability (PTP) of obstructive coronary artery disease. We sought to determine whether the calculation of PTP differ by sex in symptomatic patients referred to coronary computed tomographic angiography (CCTA). Patients and methods The characteristics of 5777 men and women who underwent CCTA were compared. For each patient, PTP was calculated according to the updated Diamond–Forrester method (UDFM) and the Duke clinical score (DCS), respectively. Follow-up clinical data were also recorded. Area under the receiver operating characteristic curve, integrated discrimination improvement, net reclassification improvement, and the Hosmer–Lemeshow goodness-of-fit statistic were used to assess the models’ performance. Results The area under the receiver operating characteristic curve of UDFM and DCS showed little difference in men (0.782 vs. 0.785, P=0.4708) and women (0.668 vs. 0.654, P=0.1255), and calibration of neither model was satisfactory. Compared with UDFM, DCS showed positive integrated discrimination improvement (10% in men, P<0.0001, and 8% in women, P<0.0001, respectively), net reclassification improvement (12.17% in men, P<0.0001, and 27.19% in women, P<0.0001, respectively), and obviously reduced unnecessary noninvasive testing for women with negative CCTA. Conclusion Although the performance of neither model was favorable, DCS offered a more accurate calculation of PTP than UDFM and application of DCS instead of UDFM would result in a significant decrease in inappropriate testing, especially in women.
Collapse
|
7
|
Alizadehsani R, Abdar M, Roshanzamir M, Khosravi A, Kebria PM, Khozeimeh F, Nahavandi S, Sarrafzadegan N, Acharya UR. Machine learning-based coronary artery disease diagnosis: A comprehensive review. Comput Biol Med 2019; 111:103346. [PMID: 31288140 DOI: 10.1016/j.compbiomed.2019.103346] [Citation(s) in RCA: 68] [Impact Index Per Article: 13.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2019] [Revised: 06/26/2019] [Accepted: 06/26/2019] [Indexed: 02/02/2023]
Abstract
Coronary artery disease (CAD) is the most common cardiovascular disease (CVD) and often leads to a heart attack. It annually causes millions of deaths and billions of dollars in financial losses worldwide. Angiography, which is invasive and risky, is the standard procedure for diagnosing CAD. Alternatively, machine learning (ML) techniques have been widely used in the literature as fast, affordable, and noninvasive approaches for CAD detection. The results that have been published on ML-based CAD diagnosis differ substantially in terms of the analyzed datasets, sample sizes, features, location of data collection, performance metrics, and applied ML techniques. Due to these fundamental differences, achievements in the literature cannot be generalized. This paper conducts a comprehensive and multifaceted review of all relevant studies that were published between 1992 and 2019 for ML-based CAD diagnosis. The impacts of various factors, such as dataset characteristics (geographical location, sample size, features, and the stenosis of each coronary artery) and applied ML techniques (feature selection, performance metrics, and method) are investigated in detail. Finally, the important challenges and shortcomings of ML-based CAD diagnosis are discussed.
Collapse
Affiliation(s)
- Roohallah Alizadehsani
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia.
| | - Moloud Abdar
- Département d'informatique, Université du Québec à Montréal, Montréal, Québec, Canada
| | - Mohamad Roshanzamir
- Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran
| | - Abbas Khosravi
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia
| | - Parham M Kebria
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia
| | - Fahime Khozeimeh
- Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
| | - Saeid Nahavandi
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia
| | - Nizal Sarrafzadegan
- Faculty of Medicine, SPPH, University of British Columbia, Vancouver, BC, Canada; Isfahan Cardiovascular Research Center, Cardiovascular Research Institute, Isfahan University of Medical Sciences, Khorram Ave, Isfahan, Iran
| | - U Rajendra Acharya
- Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore; Department of Biomedical Engineering, School of Science and Technology, Singapore University of Social Sciences, Singapore; Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Malaysia
| |
Collapse
|
8
|
Zhou J, Liu Y, Huang L, Tan Y, Li X, Zhang H, Ma Y, Zhang Y. Validation and comparison of four models to calculate pretest probability of obstructive coronary artery disease in a Chinese population: A coronary computed tomographic angiography study. J Cardiovasc Comput Tomogr 2017; 11:317-323. [DOI: 10.1016/j.jcct.2017.05.004] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/14/2017] [Revised: 04/28/2017] [Accepted: 05/08/2017] [Indexed: 01/21/2023]
|
9
|
He T, Liu X, Xu N, Li Y, Wu Q, Liu M, Yuan H. Diagnostic models of the pre-test probability of stable coronary artery disease: A systematic review. Clinics (Sao Paulo) 2017; 72:188-196. [PMID: 28355366 PMCID: PMC5350262 DOI: 10.6061/clinics/2017(03)10] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/29/2016] [Accepted: 12/16/2016] [Indexed: 02/02/2023] Open
Abstract
A comprehensive search of PubMed and Embase was performed in January 2015 to examine the available literature on validated diagnostic models of the pre-test probability of stable coronary artery disease and to describe the characteristics of the models. Studies that were designed to develop and validate diagnostic models of pre-test probability for stable coronary artery disease were included. Data regarding baseline patient characteristics, procedural characteristics, modeling methods, metrics of model performance, risk of bias, and clinical usefulness were extracted. Ten studies involving the development of 12 models and two studies focusing on external validation were identified. Seven models were validated internally, and seven models were validated externally. Discrimination varied between studies that were validated internally (C statistic 0.66-0.81) and externally (0.49-0.87). Only one study presented reclassification indices. The majority of better performing models included sex, age, symptoms, diabetes, smoking, and hyperlipidemia as variables. Only two diagnostic models evaluated the effects on clinical decision making processes or patient outcomes. Most diagnostic models of the pre-test probability of stable coronary artery disease have had modest success, and very few present data regarding the effects of these models on clinical decision making processes or patient outcomes.
Collapse
Affiliation(s)
- Ting He
- Central South University, The Third Xiangya Hospital, Department of Cardiology, Changsha 410013
| | - Xing Liu
- Central South University, The Third Xiangya Hospital, Department of Cardiology, Changsha 410013
| | - Nana Xu
- Central South University, The Third Xiangya Hospital, Center of Clinical Pharmacology, Changsha 410013
| | - Ying Li
- Central South University, The Third Xiangya Hospital, Center of Clinical Pharmacology, Changsha 410013
| | - Qiaoyu Wu
- Central South University, The Third Xiangya Hospital, Department of Cardiology, Changsha 410013
| | - Meilin Liu
- The First Hospital of Beijing University, Department of Gerontology, Beijing, The People’s Republic of China
| | - Hong Yuan
- Central South University, The Third Xiangya Hospital, Department of Cardiology, Changsha 410013
- Central South University, The Third Xiangya Hospital, Center of Clinical Pharmacology, Changsha 410013
- *Corresponding author. E-mail:
| |
Collapse
|
10
|
Mori T, Sakakura K, Wada H, Taniguchi Y, Yamamoto K, Adachi Y, Funayama H, Momomura SI, Fujita H. Comparison of mid-term clinical outcomes between on-label and off-label use of rotational atherectomy. Heart Vessels 2016; 32:514-519. [PMID: 27709324 DOI: 10.1007/s00380-016-0899-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/31/2016] [Accepted: 09/30/2016] [Indexed: 11/25/2022]
Abstract
While rotational atherectomy (RA) is used for complex lesions in percutaneous coronary intervention, there are several contraindications such as unprotected left main stenosis or left ventricular dysfunction. We previously reported that the incidence of in-hospital complications was significantly greater in off-label as compared to on-label use RA. However, the mid-term clinical outcomes between off-label and on-label RA have not been investigated. The purpose of this study was to compare the mid-term clinical outcomes between off-label (n = 156) and on-label RA (n = 94). The primary endpoint was the incidence of major adverse cardiovascular events (MACE) defined as the composite of ischemia-driven target vessel revascularization (TVR), non-fatal MI, and all-cause death. We also identified 154 patients who underwent RA and follow-up angiography within 1 year, and compared quantitative coronary analysis between the off-label group (n = 96) and on-label group (n = 58). There was no significant difference in late luminal loss between the groups (0.03 ± 0.53 mm in the off-label and -0.05 ± 0.44 mm in the on-label groups, P = 0.57). However, the incidence of MACE was less in the on-label group (3.2 %) as compared to the off-label group (9.0 %) without reaching statistical significance (P = 0.08). In conclusion, mid-term clinical outcomes tended to be worse in the off-label group than in the on-label group. We may have to follow-up the patient who underwent off-label RA more carefully than the patient who underwent on-label RA.
Collapse
Affiliation(s)
- Takayuki Mori
- Division of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma, Omiya, Saitama, 330-8503, Japan
| | - Kenichi Sakakura
- Division of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma, Omiya, Saitama, 330-8503, Japan.
| | - Hiroshi Wada
- Division of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma, Omiya, Saitama, 330-8503, Japan
| | - Yousuke Taniguchi
- Division of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma, Omiya, Saitama, 330-8503, Japan
| | - Kei Yamamoto
- Division of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma, Omiya, Saitama, 330-8503, Japan
| | - Yusuke Adachi
- Division of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma, Omiya, Saitama, 330-8503, Japan
| | - Hiroshi Funayama
- Division of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma, Omiya, Saitama, 330-8503, Japan
| | - Shin-Ichi Momomura
- Division of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma, Omiya, Saitama, 330-8503, Japan
| | - Hideo Fujita
- Division of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma, Omiya, Saitama, 330-8503, Japan
| |
Collapse
|
11
|
Schuhbäck A, Kolwelter J, Achenbach S. [Diamond-Forrester and cardiac CT : Is there a need to redefine the pretest probability of coronary artery disease?]. Herz 2016; 41:371-5. [PMID: 27272195 DOI: 10.1007/s00059-016-4437-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Abstract
Apart from the Diamond-Forrester classification, which is widely used particularly in the USA for the pretest probability of coronary artery disease, other scores also exist, such as an updated version of the classification table by Genders et al., the Morise score and the Duke clinical risk score. These scores estimate the probability of coronary artery disease, defined as the presence of at least one high-grade stenosis, based on symptom characteristics, age, gender and other parameters. All of the scores were derived from patient cohorts in which invasive coronary angiography had been performed for clinical reasons. It has subsequently been shown that these scores, especially those developed several decades ago, substantially overestimate the pretest probability of coronary artery disease. When these risk scores are applied to patients for whom a non-invasive work-up of suspected coronary artery disease is planned, for example by coronary computed tomography (CT) angiography, the expected prevalence of significant coronary stenosis will be overestimated. This, in turn, influences the test characteristics and the significance of the non-invasive examination (positive and negative predictive values) and needs to be taken into account when interpreting test results.
Collapse
Affiliation(s)
- A Schuhbäck
- Medizinische Klinik 2 - Kardiologie, Angiologie, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Ulmenweg 18, 91054, Erlangen, Deutschland
| | - J Kolwelter
- Medizinische Klinik 2 - Kardiologie, Angiologie, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Ulmenweg 18, 91054, Erlangen, Deutschland
| | - S Achenbach
- Medizinische Klinik 2 - Kardiologie, Angiologie, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Ulmenweg 18, 91054, Erlangen, Deutschland.
| |
Collapse
|
12
|
Association between smoking habits and severity of coronary stenosis as assessed by coronary computed tomography angiography. Heart Vessels 2015; 31:1061-8. [PMID: 26187325 DOI: 10.1007/s00380-015-0716-7] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/09/2015] [Accepted: 07/10/2015] [Indexed: 10/23/2022]
Abstract
Smoking promotes arteriosclerosis and is one of the most important coronary risk factors. However, few studies have investigated the association between smoking habits and the severity of coronary stenosis as assessed by coronary computed tomography angiography (CTA). We enrolled 416 patients [165/251 = smoker (past and current)/non-smoker)]. They had all undergone CTA and either were clinically suspected of having coronary artery disease (CAD) or had at least one cardiovascular risk factor. We divided the patients into smoking and non-smoking groups, and evaluated the presence of CAD, the number of significantly stenosed coronary vessels (VD), and the Gensini score as assessed by CTA in the two groups. The incidence of CAD, VD, the Gensini score, and coronary calcification score in the smoking group were all significantly greater than those in the non-smoking group (CAD, p = 0.009; VD, p = 0.003; Gensini score, p = 0.007; coronary calcification score, p = 0.01). Pack-year was significantly associated with VD and the Gensini score, and was strongly associated with multi-vessel disease (2- and 3-VD) (p < 0.05), whereas the duration of cessation in past smokers was not associated with VD or the Gensini score. Pack-year, but not the duration of cessation, may be the most important factor that was associated with the severity of coronary stenosis in terms of VD and the Gensini score.
Collapse
|
13
|
Affiliation(s)
- Ferid Murad
- Medical School, The University of Texas-Houston Health Science Center, 6431 Fannin MSB 4.098, Houston, Texas 77030, USA.
| |
Collapse
|