1
|
Bhagawati M, Paul S, Mantella L, Johri AM, Gupta S, Laird JR, Singh IM, Khanna NN, Al-Maini M, Isenovic ER, Tiwari E, Singh R, Nicolaides A, Saba L, Anand V, Suri JS. Cardiovascular Disease Risk Stratification Using Hybrid Deep Learning Paradigm: First of Its Kind on Canadian Trial Data. Diagnostics (Basel) 2024; 14:1894. [PMID: 39272680 PMCID: PMC11393849 DOI: 10.3390/diagnostics14171894] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2024] [Revised: 08/12/2024] [Accepted: 08/26/2024] [Indexed: 09/15/2024] Open
Abstract
BACKGROUND The risk of cardiovascular disease (CVD) has traditionally been predicted via the assessment of carotid plaques. In the proposed study, AtheroEdge™ 3.0HDL (AtheroPoint™, Roseville, CA, USA) was designed to demonstrate how well the features obtained from carotid plaques determine the risk of CVD. We hypothesize that hybrid deep learning (HDL) will outperform unidirectional deep learning, bidirectional deep learning, and machine learning (ML) paradigms. METHODOLOGY 500 people who had undergone targeted carotid B-mode ultrasonography and coronary angiography were included in the proposed study. ML feature selection was carried out using three different methods, namely principal component analysis (PCA) pooling, the chi-square test (CST), and the random forest regression (RFR) test. The unidirectional and bidirectional deep learning models were trained, and then six types of novel HDL-based models were designed for CVD risk stratification. The AtheroEdge™ 3.0HDL was scientifically validated using seen and unseen datasets while the reliability and statistical tests were conducted using CST along with p-value significance. The performance of AtheroEdge™ 3.0HDL was evaluated by measuring the p-value and area-under-the-curve for both seen and unseen data. RESULTS The HDL system showed an improvement of 30.20% (0.954 vs. 0.702) over the ML system using the seen datasets. The ML feature extraction analysis showed 70% of common features among all three methods. The generalization of AtheroEdge™ 3.0HDL showed less than 1% (p-value < 0.001) difference between seen and unseen data, complying with regulatory standards. CONCLUSIONS The hypothesis for AtheroEdge™ 3.0HDL was scientifically validated, and the model was tested for reliability and stability and is further adaptable clinically.
Collapse
Affiliation(s)
- Mrinalini Bhagawati
- Department of Biomedical Engineering, North-Eastern Hill University, Shillong 793022, India
| | - Sudip Paul
- Department of Biomedical Engineering, North-Eastern Hill University, Shillong 793022, India
| | - Laura Mantella
- Division of Cardiology, Department of Medicine, University of Toronto, Toronto, ON M5S 1A1, Canada
| | - Amer M Johri
- Division of Cardiology, Department of Medicine, Queen's University, Kingston, ON K7L 3N6, Canada
| | - Siddharth Gupta
- Department of Computer Science and Engineering, Bharati Vidyapeeth's College of Engineering, New Delhi 110063, India
| | - John R Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St. Helena, CA 94574, USA
| | - Inder M Singh
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA
| | | | - Mustafa Al-Maini
- Allergy, Clinical Immunology and Rheumatology Institute, Toronto, ON M5G 1N8, Canada
| | - Esma R Isenovic
- Department of Radiobiology and Molecular Genetics, National Institute of The Republic of Serbia, University of Belgrade, 11001 Belgrade, Serbia
| | - Ekta Tiwari
- Department of Computer Science, Visvesvaraya National Institute of Technology (VNIT), Nagpur 440010, India
| | - Rajesh Singh
- Division of Research and Innovation, UTI, Uttaranchal University, Dehradun 248007, India
| | - Andrew Nicolaides
- Vascular Screening and Diagnostic Centre, University of Nicosia, Nicosia 2417, Cyprus
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria, 40138 Cagliari, Italy
| | - Vinod Anand
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA
| | - Jasjit S Suri
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA
- Department of CE, Graphic Era Deemed to be University, Dehradun 248002, India
- Department of ECE, Idaho State University, Pocatello, ID 83209, USA
- University Center for Research & Development, Chandigarh University, Mohali 140413, India
- Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune 412115, India
| |
Collapse
|
2
|
Bhagawati M, Paul S, Mantella L, Johri AM, Laird JR, Singh IM, Singh R, Garg D, Fouda MM, Khanna NN, Cau R, Abraham A, Al-Maini M, Isenovic ER, Sharma AM, Fernandes JFE, Chaturvedi S, Karla MK, Nicolaides A, Saba L, Suri JS. Deep learning approach for cardiovascular disease risk stratification and survival analysis on a Canadian cohort. THE INTERNATIONAL JOURNAL OF CARDIOVASCULAR IMAGING 2024; 40:1283-1303. [PMID: 38678144 DOI: 10.1007/s10554-024-03100-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Accepted: 04/02/2024] [Indexed: 04/29/2024]
Abstract
The quantification of carotid plaque has been routinely used to predict cardiovascular risk in cardiovascular disease (CVD) and coronary artery disease (CAD). To determine how well carotid plaque features predict the likelihood of CAD and cardiovascular (CV) events using deep learning (DL) and compare against the machine learning (ML) paradigm. The participants in this study consisted of 459 individuals who had undergone coronary angiography, contrast-enhanced ultrasonography, and focused carotid B-mode ultrasound. Each patient was tracked for thirty days. The measurements on these patients consisted of maximum plaque height (MPH), total plaque area (TPA), carotid intima-media thickness (cIMT), and intraplaque neovascularization (IPN). CAD risk and CV event stratification were performed by applying eight types of DL-based models. Univariate and multivariate analysis was also conducted to predict the most significant risk predictors. The DL's model effectiveness was evaluated by the area-under-the-curve measurement while the CV event prediction was evaluated using the Cox proportional hazard model (CPHM) and compared against the DL-based concordance index (c-index). IPN showed a substantial ability to predict CV events (p < 0.0001). The best DL system improved by 21% (0.929 vs. 0.762) over the best ML system. DL-based CV event prediction showed a ~ 17% increase in DL-based c-index compared to the CPHM (0.86 vs. 0.73). CAD and CV incidents were linked to IPN and carotid imaging characteristics. For survival analysis and CAD prediction, the DL-based system performs superior to ML-based models.
Collapse
Affiliation(s)
- Mrinalini Bhagawati
- Department of Biomedical Engineering, North-Eastern Hill University, Shillong, India
| | - Sudip Paul
- Department of Biomedical Engineering, North-Eastern Hill University, Shillong, India
| | - Laura Mantella
- Division of Cardiology, Department of Medicine, University of Toronto, Toronto, Canada
| | - Amer M Johri
- Division of Cardiology, Department of Medicine, Queen's University, Kingston, Canada
| | - John R Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St Helena, CA, 94574, USA
| | - Inder M Singh
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA, 95661, USA
| | - Rajesh Singh
- Division of Research and Innovation, UTI, Uttaranchal University, Dehradun, India
| | - Deepak Garg
- School of Cowereter Science and Artificial Intelligence, SR University, Warangal, Telangana, 506371, India
| | - Mostafa M Fouda
- Department of ECE, Idaho State University, Pocatello, ID, 83209, USA
| | | | - Riccardo Cau
- Department of Radiology, Azienda Ospedaliero Universitaria, 40138, Cagliari, Italy
| | | | - Mostafa Al-Maini
- Allergy, Clinical Immunology and Rheumatology Institute, Toronto, ON, Canada
| | - Esma R Isenovic
- Department of Radiobiology and Molecular Genetics, National Institute of The Republic of Serbia, University of Belgrade, 11001, Belgrade, Serbia
| | - Aditya M Sharma
- Division of Cardiovascular Medicine, University of Virginia, Charlottesville, VA, 22904, USA
| | | | - Seemant Chaturvedi
- Department of Neurology & Stroke Program, University of Maryland, Baltimore, MD, USA
| | - Mannudeep K Karla
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Andrew Nicolaides
- Vascular Screening and Diagnostic Centre, University of Nicosia Medical School, Nicosia, Cyprus
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria, 40138, Cagliari, Italy
| | - Jasjit S Suri
- Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA, 95661, USA.
- Department of ECE, Idaho State University, Pocatello, ID, 83209, USA.
- Department of CE, Graphic Era Deemed to be University, 248002, Dehradun, India.
| |
Collapse
|
3
|
Wang Y, Bu F, Lv X, Hou Z, Bu L, Meng F, Wang Z. Attention-based message passing and dynamic graph convolution for spatiotemporal data imputation. Sci Rep 2023; 13:6887. [PMID: 37106057 PMCID: PMC10140034 DOI: 10.1038/s41598-023-34077-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Accepted: 04/24/2023] [Indexed: 04/29/2023] Open
Abstract
Although numerous spatiotemporal approaches have been presented to address the problem of missing spatiotemporal data, there are still limitations in concurrently capturing the underlying spatiotemporal dependence of spatiotemporal graph data. Furthermore, most imputation methods miss the hidden dynamic connection associations that exist between graph nodes over time. To address the aforementioned spatiotemporal data imputation challenge, we present an attention-based message passing and dynamic graph convolution network (ADGCN). Specifically, this paper uses attention mechanisms to unify temporal and spatial continuity and aggregate node neighbor information in multiple directions. Furthermore, a dynamic graph convolution module is designed to capture constantly changing spatial correlations in sensors utilizing a new dynamic graph generation method with gating to transmit node information. Extensive imputation tests in the air quality and traffic flow domains were carried out on four real missing data sets. Experiments show that the ADGCN outperforms the state-of-the-art baseline.
Collapse
Affiliation(s)
- Yifan Wang
- School of Information Network Security, People's Public Security University of China, Beijing, 100038, China
| | - Fanliang Bu
- School of Information Network Security, People's Public Security University of China, Beijing, 100038, China.
| | - Xiaojun Lv
- Institute of Computing Technology, China Academy of Railway Sciences Corporation Limited, Beijing, 100081, China
| | - Zhiwen Hou
- School of Information Network Security, People's Public Security University of China, Beijing, 100038, China
| | - Lingbin Bu
- School of Information Network Security, People's Public Security University of China, Beijing, 100038, China
| | - Fanxu Meng
- School of Information Network Security, People's Public Security University of China, Beijing, 100038, China
| | - Zhongqing Wang
- School of Information Network Security, People's Public Security University of China, Beijing, 100038, China
| |
Collapse
|
4
|
Adusei KK, Ng KTW, Karimi N, Mahmud TS, Doolittle E. Modeling of municipal waste disposal behaviors related to meteorological seasons using recurrent neural network LSTM models. ECOL INFORM 2022. [DOI: 10.1016/j.ecoinf.2022.101925] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|