1
|
Yagi R, Goto S, Himeno Y, Katsumata Y, Hashimoto M, MacRae CA, Deo RC. Artificial intelligence-enabled prediction of chemotherapy-induced cardiotoxicity from baseline electrocardiograms. Nat Commun 2024; 15:2536. [PMID: 38514629 PMCID: PMC10957877 DOI: 10.1038/s41467-024-45733-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Accepted: 02/02/2024] [Indexed: 03/23/2024] Open
Abstract
Anthracyclines can cause cancer therapy-related cardiac dysfunction (CTRCD) that adversely affects prognosis. Despite guideline recommendations, only half of the patients undergo surveillance echocardiograms. An AI model detecting reduced left ventricular ejection fraction from 12-lead electrocardiograms (ECG) (AI-EF model) suggests ECG features reflect left ventricular pathophysiology. We hypothesized that AI could predict CTRCD from baseline ECG, leveraging the AI-EF model's insights, and developed the AI-CTRCD model using transfer learning on the AI-EF model. In 1011 anthracycline-treated patients, 8.7% experienced CTRCD. High AI-CTRCD scores indicated elevated CTRCD risk (hazard ratio (HR), 2.66; 95% CI 1.73-4.10; log-rank p < 0.001). This remained consistent after adjusting for risk factors (adjusted HR, 2.57; 95% CI 1.62-4.10; p < 0.001). AI-CTRCD score enhanced prediction beyond known factors (time-dependent AUC for 2 years: 0.78 with AI-CTRCD score vs. 0.74 without; p = 0.005). In conclusion, the AI model robustly stratified CTRCD risk from baseline ECG.
Collapse
Affiliation(s)
- Ryuichiro Yagi
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
- Department of Preventive Medicine and Public Health, Keio University School of Medicine, Tokyo, Japan
| | - Shinichi Goto
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
- Division of General Internal Medicine & Family Medicine, Department of General and Acute Medicine, Tokai University School of Medicine, Isehara, Kanagawa, Japan
| | - Yukihiro Himeno
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
| | - Yoshinori Katsumata
- Institute for Integrated Sports Medicine, Keio University School of Medicine, Tokyo, Japan
| | - Masahiro Hashimoto
- Department of Radiology, Keio University School of Medicine, Tokyo, Japan
| | - Calum A MacRae
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
| | - Rahul C Deo
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA.
- Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
2
|
Aras MA, Abreau S, Mills H, Radhakrishnan L, Klein L, Mantri N, Rubin B, Barrios J, Chehoud C, Kogan E, Gitton X, Nnewihe A, Quinn D, Bridges C, Butte AJ, Olgin JE, Tison GH. Electrocardiogram Detection of Pulmonary Hypertension Using Deep Learning. J Card Fail 2023; 29:1017-1028. [PMID: 36706977 PMCID: PMC10363571 DOI: 10.1016/j.cardfail.2022.12.016] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2022] [Revised: 11/23/2022] [Accepted: 12/25/2022] [Indexed: 01/26/2023]
Abstract
BACKGROUND Pulmonary hypertension (PH) is life-threatening, and often diagnosed late in its course. We aimed to evaluate if a deep learning approach using electrocardiogram (ECG) data alone can detect PH and clinically important subtypes. We asked: does an automated deep learning approach to ECG interpretation detect PH and its clinically important subtypes? METHODS AND RESULTS Adults with right heart catheterization or an echocardiogram within 90 days of an ECG at the University of California, San Francisco (2012-2019) were retrospectively identified as PH or non-PH. A deep convolutional neural network was trained on patients' 12-lead ECG voltage data. Patients were divided into training, development, and test sets in a ratio of 7:1:2. Overall, 5016 PH and 19,454 patients without PH were used in the study. The mean age at the time of ECG was 62.29 ± 17.58 years and 49.88% were female. The mean interval between ECG and right heart catheterization or echocardiogram was 3.66 and 2.23 days for patients with PH and patients without PH, respectively. In the test dataset, the model achieved an area under the receiver operating characteristic curve, sensitivity, and specificity, respectively of 0.89, 0.79, and 0.84 to detect PH; 0.91, 0.83, and 0.84 to detect precapillary PH; 0.88, 0.81, and 0.81 to detect pulmonary arterial hypertension, and 0.80, 0.73, and 0.76 to detect group 3 PH. We additionally applied the trained model on ECGs from participants in the test dataset that were obtained from up to 2 years before diagnosis of PH; the area under the receiver operating characteristic curve was 0.79 or greater. CONCLUSIONS A deep learning ECG algorithm can detect PH and PH subtypes around the time of diagnosis and can detect PH using ECGs that were done up to 2 years before right heart catheterization/echocardiogram diagnosis. This approach has the potential to decrease diagnostic delays in PH.
Collapse
Affiliation(s)
- Mandar A Aras
- UCSF Department of Medicine, Division of Cardiology, San Francisco, California
| | - Sean Abreau
- UCSF Department of Medicine, Division of Cardiology, San Francisco, California
| | - Hunter Mills
- Bakar Computation Health Sciences Institute, University of California, San Francisco, San Francisco, California
| | - Lakshmi Radhakrishnan
- Bakar Computation Health Sciences Institute, University of California, San Francisco, San Francisco, California
| | - Liviu Klein
- UCSF Department of Medicine, Division of Cardiology, San Francisco, California
| | - Neha Mantri
- UCSF Department of Medicine, Division of Cardiology, San Francisco, California
| | - Benjamin Rubin
- Bakar Computation Health Sciences Institute, University of California, San Francisco, San Francisco, California
| | - Joshua Barrios
- UCSF Department of Medicine, Division of Cardiology, San Francisco, California
| | | | - Emily Kogan
- Janssen Pharmaceuticals, Inc, Raritan, New Jersey
| | - Xavier Gitton
- Actelion Pharmaceuticals Ltd., Allschwil, Switzerland
| | | | | | | | - Atul J Butte
- Bakar Computation Health Sciences Institute, University of California, San Francisco, San Francisco, California
| | - Jeffrey E Olgin
- UCSF Department of Medicine, Division of Cardiology, San Francisco, California
| | - Geoffrey H Tison
- UCSF Department of Medicine, Division of Cardiology, San Francisco, California; Bakar Computation Health Sciences Institute, University of California, San Francisco, San Francisco, California; Division of Cardiology, Department of Medicine and Cardiovascular Research Institute, University of California, San Francisco, San Francisco, California.
| |
Collapse
|
3
|
Phillips P, Krahn AD, Andrade JG, Chakrabarti S, Thompson CR, Harris DJ, Forman JM, Karim SS, Sterns LD, Fedoruk LM, Partlow E, Bashir J. Treatment and Prevention of Cardiovascular Implantable Electronic Device (CIED) Infections. CJC Open 2022; 4:946-958. [DOI: 10.1016/j.cjco.2022.07.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2022] [Accepted: 07/03/2022] [Indexed: 10/15/2022] Open
|
4
|
Vervoort D, Kimmaliardjuk DM, Ross HJ, Fremes SE, Ouzounian M, Mashford-Pringle A. Access to Cardiovascular Care for Indigenous Peoples in Canada: A Rapid Review. CJC Open 2022; 4:782-791. [PMID: 36148252 PMCID: PMC9486860 DOI: 10.1016/j.cjco.2022.05.010] [Citation(s) in RCA: 19] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Accepted: 05/31/2022] [Indexed: 11/15/2022] Open
Abstract
Indigenous peoples in Canada are at an increased risk of cardiovascular disease compared to non-Indigenous people. Contributing factors include historical oppression, racism, healthcare biases, and disparities in terms of the social determinants of health. Access to and inequity in cardiovascular care for Indigenous peoples in Canada remain poorly studied and understood. A rapid review of the literature was performed using the PubMed/MEDLINE, Web of Science, and Indigenous Studies Portal (iPortal) databases to identify articles describing access to cardiovascular care for Indigenous peoples in Canada between 2002 and 2021. Included articles were presented narratively in the context of delays in seeking, reaching, or receiving care, or as disparities in cardiovascular outcomes, and were assessed for their successful engagement in indigenous health research using a preexisting framework. Current research suggests that gaps most prominently present as delays in receiving care and as poorer long-term outcomes. The literature is concentrated in Alberta, Manitoba, and Ontario, as well as among First Nations people, and is largely rooted in a biomedical worldview. Additional community-driven research is required to better elucidate the gaps in access to holistic cardiovascular care for Indigenous peoples in Canada. Healthcare professionals, researchers, and policymakers should reflect further upon their actions and privilege, educate themselves about historical facts and the Truth and Reconciliation Commission, tackle prevailing disparities and systemic barriers in the healthcare systems, and develop culturally safe and ethically appropriate healthcare interventions to improve the health of all Indigenous peoples in Canada.
Collapse
Affiliation(s)
- Dominique Vervoort
- Division of Cardiac Surgery, University of Toronto, Toronto, Ontario, Canada
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada
- Corresponding author: Dr Dominique Vervoort, Institute of Health Policy, Management and Evaluation, University of Toronto, 155 College St, 4th Floor, Toronto, Ontario M5T 3M6, Canada. Tel.: +1-416-989-7874.
| | - Donna May Kimmaliardjuk
- Division of Cardiovascular Surgery, Eastern Health, Memorial University of Newfoundland, St. John’s, Newfoundland and Labrador, Canada
| | - Heather J. Ross
- Division of Cardiology, Peter Munk Cardiac Centre, Toronto General Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Stephen E. Fremes
- Division of Cardiac Surgery, University of Toronto, Toronto, Ontario, Canada
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada
- Schulich Heart Centre, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, Ontario, Canada
| | - Maral Ouzounian
- Division of Cardiac Surgery, University of Toronto, Toronto, Ontario, Canada
- Division of Cardiovascular Surgery, Peter Munk Cardiac Centre, Toronto General Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Angela Mashford-Pringle
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada
- Waakebiness-Bryce Institute for Indigenous Health, Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada
| |
Collapse
|
5
|
Vervoort D, Chung JCY, Ouzounian M. Access to Thoracic Aortic Care: Challenges and Opportunities in Universal Health Coverage Systems. Can J Cardiol 2022; 38:726-728. [PMID: 35272002 DOI: 10.1016/j.cjca.2022.03.004] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2022] [Revised: 03/02/2022] [Accepted: 03/03/2022] [Indexed: 11/02/2022] Open
Affiliation(s)
- Dominique Vervoort
- Division of Cardiac Surgery, University of Toronto, Toronto, Ontario; Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario.
| | - Jennifer C Y Chung
- Division of Cardiac Surgery, University of Toronto, Toronto, Ontario; Division of Cardiovascular Surgery, Peter Munk Cardiac Centre, Toronto General Hospital, Toronto, Ontario
| | - Maral Ouzounian
- Division of Cardiac Surgery, University of Toronto, Toronto, Ontario; Division of Cardiovascular Surgery, Peter Munk Cardiac Centre, Toronto General Hospital, Toronto, Ontario
| |
Collapse
|
6
|
Pulmonary arterial hypertension screening practices in scleroderma patients among Canadian rheumatologists. JOURNAL OF SCLERODERMA AND RELATED DISORDERS 2020; 5:237-241. [DOI: 10.1177/2397198320942038] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2020] [Accepted: 05/30/2020] [Indexed: 11/17/2022]
Abstract
Background: Current international guidelines recommend annual screening for pulmonary arterial hypertension with transthoracic echocardiogram and pulmonary function testing in all patients with scleroderma (systemic sclerosis). Our objectives were to determine Canadian rheumatologists’ screening practices for pulmonary arterial hypertension in patients with systemic sclerosis and identify reasons why current guideline recommendations may not be followed. Methods: A survey was emailed to all Canadian Rheumatology Association members. They self-identified as systemic sclerosis experts or non-experts and provided basic demographic data. Participants were asked how frequently they screened with transthoracic echocardiogram and pulmonary function testing and, if applicable, why they did not adhere to recommendations. Results: A total of 71 rheumatologists participated, of whom 43 identified as non-experts. Overall, 81.4% ordered annual transthoracic echocardiogram and 77.6% annual pulmonary function testing. Rates of annual transthoracic echocardiogram testing were similar between experts and non-experts, whereas experts ordered annual pulmonary function testing more often. Clinicians with a higher proportion of systemic sclerosis patients in their practice were more likely to follow guidelines. There was an inverse relationship between years in practice and adherence to screening guidelines. The most common reason for not following screening guidelines was disagreement with recommendations, followed by unfamiliarity with guidelines. Conclusions: Pulmonary arterial hypertension screening rates remain sub-optimal in Canada but have improved since 2012. Failure to adopt guidelines is due to rheumatologists disagreeing with or not knowing current recommendations. Future studies should examine why rheumatologists disagree with guidelines and how to improve awareness.
Collapse
|
7
|
Wu YM, Liu CC, Yeh CC, Sung LC, Lin CS, Cherng YG, Chen TL, Liao CC. Hospitalization outcome of heart diseases between patients who received medical care by cardiologists and non-cardiologist physicians: A propensity-score matched study. PLoS One 2020; 15:e0235207. [PMID: 32629459 PMCID: PMC7338078 DOI: 10.1371/journal.pone.0235207] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2019] [Accepted: 05/28/2020] [Indexed: 11/28/2022] Open
Abstract
Background and aims The effects of physician specialty on the outcome of heart disease remains incompletely understood because of inconsistent findings from some previous studies. Our purpose is to compare the admission outcomes of heart disease in patients receiving care by cardiologists and noncardiologist (NC) physicians. Methods Using reimbursement claims data of Taiwan’s National Health Insurance from 2008–2013, we conducted a matched study of 6264 patients aged ≥20 years who received a cardiologist’s care during admission for heart disease. Using a propensity score matching procedure adjusted for sociodemographic characteristics, medical condition, and type of heart disease, 6264 controls who received an NC physician’s care were selected. Logistic regressions were used to calculate odds ratios (ORs) with 95% confidence intervals (CIs) for complications and mortality during admission for heart disease associated with a cardiologist’s care. Results Patients who received a cardiologist’s care had a lower risk of pneumonia (OR = 0.61; 95% CI, 0.53–0.70), septicemia (OR = 0.49; 95% CI, 0.39–0.61), urinary tract infection (OR = 0.76; 95% CI, 0.66–0.88), and in-hospital mortality (OR = 0.37; 95% CI, 0.29–0.47) than did patients who received an NC physician’s care. The association between a cardiologist’s care and reduced adverse events following admission was significant in both sexes and in patients aged ≥40 years. Conclusion We raised the possibility that cardiologist care was associated with reduced infectious complications and mortality among patients who were admitted due to heart disease.
Collapse
Affiliation(s)
- Yu-Ming Wu
- Department of Anesthesiology, Shuang Ho Hospital, Taipei Medical University, New Taipei City, Taiwan
- Department of Anesthesiology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan
| | - Chih-Chung Liu
- Department of Anesthesiology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan
- Department of Anesthesiology, Taipei Medical University Hospital, Taipei, Taiwan
- Anesthesiology and Health Policy Research Center, Taipei Medical University Hospital, Taipei, Taiwan
| | - Chun-Chieh Yeh
- Department of Surgery, China Medical University Hospital, Taichung, Taiwan
- Department of Surgery, University of Illinois, Chicago, IL, United States of America
| | - Li-Chin Sung
- Division of Cardiology, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City, Taiwan
- Division of Cardiology, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan
- Taipei Heart Institute, Taipei Medical University, Taipei, Taiwan
| | - Chao-Shun Lin
- Department of Anesthesiology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan
- Department of Anesthesiology, Taipei Medical University Hospital, Taipei, Taiwan
- Anesthesiology and Health Policy Research Center, Taipei Medical University Hospital, Taipei, Taiwan
| | - Yih-Giun Cherng
- Department of Anesthesiology, Shuang Ho Hospital, Taipei Medical University, New Taipei City, Taiwan
- Department of Anesthesiology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan
| | - Ta-Liang Chen
- Department of Anesthesiology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan
- Anesthesiology and Health Policy Research Center, Taipei Medical University Hospital, Taipei, Taiwan
- Department of Anesthesiology, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan
| | - Chien-Chang Liao
- Department of Anesthesiology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan
- Department of Anesthesiology, Taipei Medical University Hospital, Taipei, Taiwan
- Anesthesiology and Health Policy Research Center, Taipei Medical University Hospital, Taipei, Taiwan
- Research Center of Big Data and Meta-Analysis, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan
- School of Chinese Medicine, College of Chinese Medicine, China Medical University, Taichung, Taiwan
- * E-mail: ,
| |
Collapse
|
8
|
Boom NK, Lee DS, Tu JV. Comparison of processes of care and clinical outcomes for patients newly hospitalized for heart failure attended by different physician specialists. Am Heart J 2012; 163:252-9. [PMID: 22305844 DOI: 10.1016/j.ahj.2011.11.012] [Citation(s) in RCA: 43] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/31/2011] [Accepted: 11/17/2011] [Indexed: 11/18/2022]
Abstract
BACKGROUND Previous studies suggest that patients with heart failure (HF) treated by cardiologists have improved outcomes compared with patients treated by other physicians. It remains unclear whether these findings reflect differences in patient characteristics, processes of care, practice setting, or a combination of these factors. METHODS We examined physician specialty-related differences in processes of care and clinical outcomes for 7,634 patients newly hospitalized for HF in Ontario, Canada, who were included in the EFFECT study between April 2004 and March 2005. Patients were categorized according to whether they received cardiologist, generalist (e.g., internist or family doctor), or generalist care with cardiology consultation. RESULTS Multivariable hierarchical modeling demonstrated that patients treated by generalists alone had higher risk of 30-day (odds ratio [OR] 1.50, 95% CI 1.18-1.91) and 1-year mortality (OR 1.29, 95% CI 1.10-1.50), as well as the 1-year composite outcome of death and readmission, compared with patients treated by cardiologists. These differences were significantly attenuated if patients who had "do not resuscitate" orders were excluded. Patients who had a cardiologist involved in their care were more likely to undergo diagnostic procedures, such as echocardiography, and had higher rates of certain evidence-based pharmacologic therapy such as β-blockers. CONCLUSION Physician specialty-related differences in HF outcomes appear to reflect a combination of both case-mix differences and differences in the use of certain heart failure processes of care. These findings suggest that it may be possible to improve HF outcomes in patients receiving care from generalist physicians.
Collapse
Affiliation(s)
- Nicole K Boom
- Institute for Clinical Evaluative Sciences, Toronto, Ontario, Canada
| | | | | |
Collapse
|
9
|
Eastwood C, Doucet J, Estrella-Holder E, MacDonald J, Nichols N, Sherrard H, Smigorowsky M, Yates G, Woodend K. A commentary on access to cardiovascular services: Nursing roles and initiatives. Can J Cardiol 2008; 24:107-12. [DOI: 10.1016/s0828-282x(08)70563-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022] Open
|