1
|
Simonato M, Vemulapalli S, Ben-Yehuda O, Wu C, Wood L, Popma J, Feldman T, Krohn C, Hardy KM, Guibone K, Christensen B, Alu MC, Chen S, Ng VG, Chau KH, Shahim B, Vincent F, MacMahon J, James S, Mack M, Leon MB, Thourani VH, Carroll J, Krucoff M. Minimum Core Data Elements for Evaluation of TAVR: A Scientific Statement by PASSION CV, HVC, and TVT Registry. JACC Cardiovasc Interv 2022; 15:685-697. [PMID: 35367168 DOI: 10.1016/j.jcin.2022.01.014] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/18/2021] [Revised: 12/03/2021] [Accepted: 01/10/2022] [Indexed: 01/07/2023]
Abstract
Transcatheter aortic valve replacement (TAVR) is the standard of care for severe, symptomatic aortic stenosis. Real-world TAVR data collection contributes to benefit/risk assessment and safety evidence for the U.S. Food and Drug Administration, quality evaluation for the Centers for Medicare and Medicaid Services and hospitals, as well as clinical research and real-world implementation through appropriate use criteria. The essential minimum core dataset for these purposes has not previously been defined but is necessary to promote efficient, reusable real-world data collection supporting quality, regulatory, and clinical applications. The authors performed a systematic review of the published research for high-impact TAVR studies and U.S. multicenter, multidevice registries. Two expert task forces, one from the Predictable and Sustainable Implementation of National Cardiovascular Registries/Heart Valve Collaboratory and another from The Society of Thoracic Surgeons/American College of Cardiology TVT (Transcatheter Valve Therapy) Registry convened separately and then met to reconcile a final list of essential data elements. From 276 unique data elements considered, unanimous consensus agreement was achieved on 132 "core" data elements, with the most common reasons for exclusion from the minimum core dataset being burden or difficulty in accurate assessment (36.9%), duplicative information (33.3%), and low likelihood of affecting outcomes (10.7%). After a systematic review and extensive discussions, a multilateral group of academicians, industry representatives, and regulators established 132 interoperable, reusable essential core data elements essential to supporting more efficient, consistent, and informative TAVR device evidence for regulatory submissions, safety surveillance, best practice, and hospital quality assessments.
Collapse
Affiliation(s)
| | | | - Ori Ben-Yehuda
- University of California-San Diego, San Diego, California, USA; Cardiovascular Research Foundation, New York, New York, USA
| | - Changfu Wu
- U.S. Food and Drug Administration, Silver Spring, Maryland, USA
| | - Larry Wood
- Edwards Lifesciences, Irvine, California, USA
| | | | - Ted Feldman
- Edwards Lifesciences, Irvine, California, USA
| | - Carole Krohn
- The Society of Thoracic Surgeons, Chicago, Illinois, USA
| | | | - Kimberly Guibone
- Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA
| | | | - Maria C Alu
- Cardiovascular Research Foundation, New York, New York, USA
| | - Shmuel Chen
- Columbia University Irving School of Medicine, New York, New York, USA
| | - Vivian G Ng
- Columbia University Irving School of Medicine, New York, New York, USA
| | - Katherine H Chau
- Columbia University Irving School of Medicine, New York, New York, USA
| | - Bahira Shahim
- Cardiovascular Research Foundation, New York, New York, USA
| | | | - John MacMahon
- Mitre Medical Corporation, Morgan Hill, California, USA
| | - Stefan James
- Department of Medical Sciences and Uppsala Clinical Research Center, Uppsala, Sweden
| | - Michael Mack
- Baylor Scott and White Health, Dallas, Texas, USA
| | - Martin B Leon
- Columbia University Irving School of Medicine, New York, New York, USA
| | | | - John Carroll
- University of Colorado School of Medicine, Denver, Colorado, USA
| | | |
Collapse
|
2
|
Simonato M, Vemulapalli S, Ben-Yehuda O, Wu C, Wood L, Popma J, Feldman T, Krohn C, Hardy KM, Guibone K, Christensen B, Alu MC, Chen S, Ng VG, Chau KH, Shahim B, Vincent F, MacMahon J, James S, Mack M, Leon MB, Thourani VH, Carroll J, Krucoff M. Minimum Core Data Elements for Evaluation of TAVR: A Scientific Statement by PASSION CV, HVC, and TVT Registry. Ann Thorac Surg 2022; 113:1730-1742. [PMID: 35367049 DOI: 10.1016/j.athoracsur.2022.01.018] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/18/2021] [Accepted: 01/10/2022] [Indexed: 11/20/2022]
Abstract
Transcatheter aortic valve replacement (TAVR) is the standard of care for severe, symptomatic aortic stenosis. Real-world TAVR data collection contributes to benefit/risk assessment and safety evidence for the U.S. Food and Drug Administration, quality evaluation for the Centers for Medicare and Medicaid Services and hospitals, as well as clinical research and real-world implementation through appropriate use criteria. The essential minimum core dataset for these purposes has not previously been defined but is necessary to promote efficient, reusable real-world data collection supporting quality, regulatory, and clinical applications. The authors performed a systematic review of the published research for high-impact TAVR studies and U.S. multicenter, multidevice registries. Two expert task forces, one from the Predictable and Sustainable Implementation of National Cardiovascular Registries/Heart Valve Collaboratory and another from The Society of Thoracic Surgeons/American College of Cardiology TVT (Transcatheter Valve Therapy) Registry convened separately and then met to reconcile a final list of essential data elements. From 276 unique data elements considered, unanimous consensus agreement was achieved on 132 "core" data elements, with the most common reasons for exclusion from the minimum core dataset being burden or difficulty in accurate assessment (36.9%), duplicative information (33.3%), and low likelihood of affecting outcomes (10.7%). After a systematic review and extensive discussions, a multilateral group of academicians, industry representatives, and regulators established 132 interoperable, reusable essential core data elements essential to supporting more efficient, consistent, and informative TAVR device evidence for regulatory submissions, safety surveillance, best practice, and hospital quality assessments.
Collapse
Affiliation(s)
| | | | - Ori Ben-Yehuda
- University of California-San Diego, San Diego, California; Cardiovascular Research Foundation, New York, New York
| | - Changfu Wu
- U.S. Food and Drug Administration, Silver Spring, Maryland
| | - Larry Wood
- Edwards Lifesciences, Irvine, California
| | | | | | - Carole Krohn
- The Society of Thoracic Surgeons, Chicago, Illinois
| | | | | | | | - Maria C Alu
- Cardiovascular Research Foundation, New York, New York
| | - Shmuel Chen
- Columbia University Irving School of Medicine, New York, New York
| | - Vivian G Ng
- Columbia University Irving School of Medicine, New York, New York
| | - Katherine H Chau
- Columbia University Irving School of Medicine, New York, New York
| | - Bahira Shahim
- Cardiovascular Research Foundation, New York, New York
| | | | | | - Stefan James
- Department of Medical Sciences and Uppsala Clinical Research Center, Uppsala, Sweden
| | | | - Martin B Leon
- Columbia University Irving School of Medicine, New York, New York
| | | | - John Carroll
- University of Colorado School of Medicine, Denver, Colorado
| | | |
Collapse
|
3
|
Liu S, Wang X, Xiang Y, Xu H, Wang H, Tang B. Multi-channel Fusion LSTM for Medical Event Prediction using HERs. J Biomed Inform 2022; 127:104011. [PMID: 35176451 DOI: 10.1016/j.jbi.2022.104011] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2021] [Revised: 01/04/2022] [Accepted: 02/01/2022] [Indexed: 01/16/2023]
Abstract
Automatic medical event prediction (MEP), e.g. diagnosis prediction, medication prediction, using electronic health records (EHRs) is a popular research direction in health informatics. In many cases, MEP relies on the determinations from different types of medical events, which demonstrates the heterogeneous nature of EHRs. However, most existing methods for MEP fail to distinguishingly model the type of event that is highly associated with the prediction task, i.e. task-wise event, which usually plays a more significant role than other events. In this paper, we proposed a Long Short-Term Memory network (LSTM)-based method for MEP, named Multi-Channel Fusion LSTM (MCF-LSTM), which models the correlations between different types of medical events using multiple network channels. To this end, we designed a task-wise fusion module, in which a gated network is applied to select how much information can be transferred between events. Furthermore, the irregular temporal interval between adjacent medical visits is also modeled in an individual channel, which is combined with other events in a unified manner. We compared MCF-LSTM with state-of-the-art methods on four MEP tasks on two public datasets: MIMIC-III and eICU. Experimental results show that MCF-LSTM achieves promising results on AUC(receiver operating characteristic curve), AUPR (area under the precision-recall curve), and top-k recall, and outperforms other methods with high stability.
Collapse
Affiliation(s)
- Sicen Liu
- Department of Computer Science, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China
| | - Xiaolong Wang
- Department of Computer Science, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China
| | | | - Hui Xu
- Gennlife (Beijing) Technology Co Ltd, Beijing, China
| | - Hui Wang
- Gennlife (Beijing) Technology Co Ltd, Beijing, China
| | - Buzhou Tang
- Department of Computer Science, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China; Peng Cheng Laboratory, Shenzhen, China.
| |
Collapse
|
4
|
Gensheimer MF, Aggarwal S, Benson KRK, Carter JN, Henry AS, Wood DJ, Soltys SG, Hancock S, Pollom E, Shah NH, Chang DT. Automated model versus treating physician for predicting survival time of patients with metastatic cancer. J Am Med Inform Assoc 2021; 28:1108-1116. [PMID: 33313792 DOI: 10.1093/jamia/ocaa290] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2020] [Accepted: 11/09/2020] [Indexed: 02/06/2023] Open
Abstract
OBJECTIVE Being able to predict a patient's life expectancy can help doctors and patients prioritize treatments and supportive care. For predicting life expectancy, physicians have been shown to outperform traditional models that use only a few predictor variables. It is possible that a machine learning model that uses many predictor variables and diverse data sources from the electronic medical record can improve on physicians' performance. For patients with metastatic cancer, we compared accuracy of life expectancy predictions by the treating physician, a machine learning model, and a traditional model. MATERIALS AND METHODS A machine learning model was trained using 14 600 metastatic cancer patients' data to predict each patient's distribution of survival time. Data sources included note text, laboratory values, and vital signs. From 2015-2016, 899 patients receiving radiotherapy for metastatic cancer were enrolled in a study in which their radiation oncologist estimated life expectancy. Survival predictions were also made by the machine learning model and a traditional model using only performance status. Performance was assessed with area under the curve for 1-year survival and calibration plots. RESULTS The radiotherapy study included 1190 treatment courses in 899 patients. A total of 879 treatment courses in 685 patients were included in this analysis. Median overall survival was 11.7 months. Physicians, machine learning model, and traditional model had area under the curve for 1-year survival of 0.72 (95% CI 0.63-0.81), 0.77 (0.73-0.81), and 0.68 (0.65-0.71), respectively. CONCLUSIONS The machine learning model's predictions were more accurate than those of the treating physician or a traditional model.
Collapse
Affiliation(s)
| | - Sonya Aggarwal
- Department of Radiation Oncology, Stanford University, Stanford, CA, USA
| | - Kathryn R K Benson
- Department of Radiation Oncology, Stanford University, Stanford, CA, USA
| | - Justin N Carter
- Department of Radiation Oncology, Stanford University, Stanford, CA, USA
| | - A Solomon Henry
- Department of Biomedical Data Science, Stanford University, Stanford, CA, USA
| | - Douglas J Wood
- Department of Biomedical Data Science, Stanford University, Stanford, CA, USA
| | - Scott G Soltys
- Department of Radiation Oncology, Stanford University, Stanford, CA, USA
| | - Steven Hancock
- Department of Radiation Oncology, Stanford University, Stanford, CA, USA
| | - Erqi Pollom
- Department of Radiation Oncology, Stanford University, Stanford, CA, USA
| | - Nigam H Shah
- Department of Biomedical Data Science, Stanford University, Stanford, CA, USA
| | - Daniel T Chang
- Department of Radiation Oncology, Stanford University, Stanford, CA, USA
| |
Collapse
|
5
|
Predictors of Mortality in Patients Treated with Veno-Arterial ECMO for Cardiogenic Shock Complicating Acute Myocardial Infarction: a Systematic Review and Meta-Analysis. J Cardiovasc Transl Res 2021; 15:227-238. [PMID: 34081255 DOI: 10.1007/s12265-021-10140-w] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/02/2021] [Accepted: 05/27/2021] [Indexed: 10/21/2022]
Abstract
BACKGROUND Mortality for patients on veno-arterial extracorporeal membrane oxygenation (VA-ECMO) for cardiogenic shock (CS) complicating acute myocardial infarction (AMI) remains high. This meta-analysis aims to identify factors that predict higher risk of mortality after VA-ECMO for AMI. METHODS We meta-analyzed mortality after VA-ECMO for CS complicating AMI and the effect of factors from systematically selected studies published after 2009. RESULTS 72 studies (10,276 patients) were included with a pooled mortality estimate of 58 %. With high confidence in estimates, failure to achieve TIMI III flow and left main culprit were identified as factors associated with higher mortality. With low-moderate confidence, older age, high BMI, renal dysfunction, increasing lactate, prothrombin activity < 50%, VA-ECMO implantation after revascularization, and non-shockable ventricular arrythmias were identified as factors associated with mortality. CONCLUSION These results provide clinicians with a framework for selecting patients for VA-ECMO for CS complicating AMI.
Collapse
|
6
|
Abstract
Identifying patients with heart failure at high risk for poor outcomes is important for patient care, resource allocation, and process improvement. Although numerous risk models exist to predict mortality, hospitalization, and patient-reported health status, they are infrequently used for several reasons, including modest performance, lack of evidence to support routine clinical use, and barriers to implementation. Artificial intelligence has the potential to enhance the performance of risk prediction models, but has its own limitations and remains unproved.
Collapse
Affiliation(s)
- Ramsey M Wehbe
- Division of Cardiology, Department of Medicine, Northwestern University Feinberg School of Medicine, 676 North St. Clair Street, Suite 600, Chicago, IL 60611, USA. https://twitter.com/ramseywehbemd
| | - Sadiya S Khan
- Division of Cardiology, Department of Medicine, Northwestern University Feinberg School of Medicine, 676 North St. Clair Street, Suite 600, Chicago, IL 60611, USA; Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, 680 N Lake Shore Drive, Suite 1400, Chicago, IL 60611, USA. https://twitter.com/HeartDocSadiya
| | - Sanjiv J Shah
- Division of Cardiology, Department of Medicine, Northwestern University Feinberg School of Medicine, 676 North St. Clair Street, Suite 600, Chicago, IL 60611, USA. https://twitter.com/HFpEF
| | - Faraz S Ahmad
- Division of Cardiology, Department of Medicine, Northwestern University Feinberg School of Medicine, 676 North St. Clair Street, Suite 600, Chicago, IL 60611, USA; Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, 680 N Lake Shore Drive, Suite 1400, Chicago, IL 60611, USA; Center for Health Information Partnerships, Institute for Public Health and Medicine, Northwestern University Feinberg School of Medicine, 625 N Michigan Avenue, 15th Floor, Chicago, IL 60611, USA.
| |
Collapse
|
7
|
Slawnych M. Management of the Dying Cardiac Patient in the Last Days and Hours of Life. Can J Cardiol 2020; 36:1061-1067. [DOI: 10.1016/j.cjca.2020.02.085] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2019] [Revised: 02/06/2020] [Accepted: 02/14/2020] [Indexed: 11/26/2022] Open
|
8
|
Heckman GA, Hirdes JP, McKelvie RS. The Role of Physicians in the Era of Big Data. Can J Cardiol 2020; 36:19-21. [DOI: 10.1016/j.cjca.2019.09.018] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2019] [Revised: 09/25/2019] [Accepted: 09/26/2019] [Indexed: 12/13/2022] Open
|