1
|
Motazedian P, Marbach JA, Prosperi-Porta G, Parlow S, Di Santo P, Abdel-Razek O, Jung R, Bradford WB, Tsang M, Hyon M, Pacifici S, Mohanty S, Ramirez FD, Huggins GS, Simard T, Hon S, Hibbert B. Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction. NPJ Digit Med 2023; 6:201. [PMID: 37898711 PMCID: PMC10613290 DOI: 10.1038/s41746-023-00945-1] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2023] [Accepted: 10/13/2023] [Indexed: 10/30/2023] Open
Abstract
Focused cardiac ultrasound (FoCUS) is becoming standard practice in a wide spectrum of clinical settings. There is limited data evaluating the real-world use of FoCUS with artificial intelligence (AI). Our objective was to determine the accuracy of FoCUS AI-assisted left ventricular ejection fraction (LVEF) assessment and compare its accuracy between novice and experienced users. In this prospective, multicentre study, participants requiring a transthoracic echocardiogram (TTE) were recruited to have a FoCUS done by a novice or experienced user. The AI-assisted device calculated LVEF at the bedside, which was subsequently compared to TTE. 449 participants were enrolled with 424 studies included in the final analysis. The overall intraclass coefficient was 0.904, and 0.921 in the novice (n = 208) and 0.845 in the experienced (n = 216) cohorts. There was a significant bias of 0.73% towards TTE (p = 0.005) with a level of agreement of 11.2%. Categorical grading of LVEF severity had excellent agreement to TTE (weighted kappa = 0.83). The area under the curve (AUC) was 0.98 for identifying an abnormal LVEF (<50%) with a sensitivity of 92.8%, specificity of 92.3%, negative predictive value (NPV) of 0.97 and a positive predictive value (PPV) of 0.83. In identifying severe dysfunction (<30%) the AUC was 0.99 with a sensitivity of 78.1%, specificity of 98.0%, NPV of 0.98 and PPV of 0.76. Here we report that FoCUS AI-assisted LVEF assessments provide highly reproducible LVEF estimations in comparison to formal TTE. This finding was consistent among senior and novice echocardiographers suggesting applicability in a variety of clinical settings.
Collapse
Affiliation(s)
- Pouya Motazedian
- CAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
- Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
- School of Epidemiology and Public Health, University of Ottawa, Ottawa, Ontario, Canada
| | - Jeffrey A Marbach
- Division of Cardiology, Knight Cardiovascular Institute, Oregon Health and Sciences University, Portland, OR, USA
| | - Graeme Prosperi-Porta
- CAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
- Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
| | - Simon Parlow
- CAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
- Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
| | - Pietro Di Santo
- CAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
- School of Epidemiology and Public Health, University of Ottawa, Ottawa, Ontario, Canada
- Department of Medicine, University of Ottawa, Ottawa, Ontario, Canada
| | - Omar Abdel-Razek
- CAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
- Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
| | - Richard Jung
- CAPITAL Research Group, Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
- Department of Medicine, University of Ottawa, Ottawa, Ontario, Canada
| | - William B Bradford
- Division of Cardiology, Tufts Medical Center and Tufts University School of Medicine, Boston, MA, USA
| | - Miranda Tsang
- Division of Cardiology, Tufts Medical Center and Tufts University School of Medicine, Boston, MA, USA
| | - Michael Hyon
- Division of Cardiology, Tufts Medical Center and Tufts University School of Medicine, Boston, MA, USA
| | - Stefano Pacifici
- Division of Cardiology, Tufts Medical Center and Tufts University School of Medicine, Boston, MA, USA
| | - Sharanya Mohanty
- Division of Cardiology, Tufts Medical Center and Tufts University School of Medicine, Boston, MA, USA
| | - F Daniel Ramirez
- Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada
| | - Gordon S Huggins
- Division of Cardiology, Tufts Medical Center and Tufts University School of Medicine, Boston, MA, USA
| | - Trevor Simard
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA
| | - Stephanie Hon
- Division of Pulmonary and Critical Care Medicine, Tufts Medical Center and Tufts University School of Medicine, Boston, MA, USA
| | - Benjamin Hibbert
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.
| |
Collapse
|
2
|
Diagnosis of Blood Vessel Stenosis Caused by Arterial Thrombosis of Lower Extremities by Ultrasound Based on the Mobile Information System. JOURNAL OF HEALTHCARE ENGINEERING 2022; 2022:7282192. [PMID: 35256900 PMCID: PMC8898109 DOI: 10.1155/2022/7282192] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/25/2021] [Revised: 01/10/2022] [Accepted: 02/10/2022] [Indexed: 11/18/2022]
Abstract
The thrombosis process is a multifactorial evolution process that includes many genetic and environmental factors that interact with each other. It refers to the existence of blood deposits in the heart or blood vessel walls or abnormal blood clots in the circulatory blood flow during the survival period of humans or animals for some reason. This article aims to analyze the research of blood vessel stenosis caused by arterial thrombosis of the lower extremities under the diagnosis of cardiac ultrasound based on the mobile information system. This article first introduces the mobile information nursing system and its development process. The mobile nursing information system has experienced three stages of development and is an important application of the further development of science and technology in medical information technology. It also proposes a medical diagnosis method based on SRM on a mobile platform and gives a technical roadmap for heart sound analysis and processing. Then, based on the mobile information system, the formation of arterial thrombosis in the lower extremities was analyzed and discussed in the ultrasound diagnosis of the heart, and the vascular stenosis caused by the arterial thrombosis of the lower extremities was analyzed by imaging. Experimental results show that when there is >50% stenosis or complete occlusion, the CTA false positive is more prominent, especially when the calf artery type is complete stenosis. The main cause is that the circulation of the lower limbs is very poor, the blood entering the blood vessels of the lower limbs is scarce, the capillaries are weakly enhanced, and the quality cannot be improved.
Collapse
|
3
|
Pattock AM, Kim MM, Kersey CB, Liu L, Kirkpatrick JN, Adedipe A, Kessler R, Morris A, Nikravan S, Mazimba S, Kwon Y. Cardiac point-of-care ultrasound publication trends. Echocardiography 2022; 39:240-247. [PMID: 35034372 DOI: 10.1111/echo.15297] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2021] [Revised: 12/21/2021] [Accepted: 01/05/2022] [Indexed: 02/02/2023] Open
Abstract
INTRODUCTION Cardiac point-of-care ultrasound (c-POCUS) is an increasingly implemented diagnostic tool with the potential to guide clinical management. We sought to characterize and analyze the existing c-POCUS literature with a focus on the temporal trends and differences across specialties. METHODS A literature search for c-POCUS and related terms was conducted using Ovid (MEDLINE and Embase) and Web of Science databases through 2020. Eligible publications were classified by publication type and topic, author specialty, geographical region of senior author, and journal specialty. RESULTS The initial search produced 1761 potential publications. A strict definition of c-POCUS yielded a final total of 574 cardiac POCUS manuscripts. A yearly increase in c-POCUS publications was observed. Nearly half of publications were original research (48.8%) followed by case report or series (22.8%). Most publications had an emergency medicine senior author (38.5%), followed by cardiology (20.8%), anesthesiology (12.5%), and critical care (12.5%). The proportion authored by emergency medicine and cardiologists has decreased over time while those by anesthesiology and critical care has generally increased, particularly over the last decade. First authorship demonstrated a similar trend. Articles were published in emergency medicine (24.4%) and cardiology journals (20.5%) with comparable frequency. CONCLUSION The annual number of c-POCUS publications has steadily increased over time, reflecting the increased recognition and utilization of c-POCUS. This study can help inform clinicians of the current state of c-POCUS and augment the discussion surrounding barriers to continued adoption across all specialties.
Collapse
Affiliation(s)
| | | | - Cooper B Kersey
- University of Washington, Department of Medicine, Seattle, Washington, USA
| | - Linda Liu
- University of Washington, Department of Medicine, Seattle, Washington, USA
| | | | - Adeyinka Adedipe
- University of Washington, Department of Emergency Medicine, Seattle, Washington, USA
| | - Ross Kessler
- University of Washington, Department of Emergency Medicine, Seattle, Washington, USA
| | - Amy Morris
- University of Washington, Division of Pulmonary, Critical Care and Sleep Medicine, Seattle, Washington, USA
| | - Sara Nikravan
- University of Washington, Department of Anesthesiology and Pain Medicine, Seattle, Washington, USA
| | - Sula Mazimba
- University of Virginia, Division of Cardiovascular Medicine, Charlottesville, Virginia, USA
| | - Younghoon Kwon
- University of Washington, Division of Cardiology, Seattle, Washington, USA
| |
Collapse
|
4
|
Gregorietti V, Fernandez TL, Costa D, Chahla EO, Daniele AJ. Use of Sacubitril/valsartan in patients with cardio toxicity and heart failure due to chemotherapy. CARDIO-ONCOLOGY (LONDON, ENGLAND) 2020; 6:24. [PMID: 33292750 PMCID: PMC7643279 DOI: 10.1186/s40959-020-00078-4] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/04/2020] [Accepted: 09/23/2020] [Indexed: 12/11/2022]
Abstract
BACKGROUND Cancer therapy-related cardiac dysfunction (CTRCD) is a critical problem with an impact on both oncological and cardiovascular prognosis, especially when it prevents patients from receiving cancer treatment. Standard therapy for heart failure (HF) is recommended for CTRCD, but there is no well-established evidence on how sacubitril/valsartan may help cancer patients with cardiotoxicity. OBJECTIVES The aim of this trial was to study the effectiveness of sacubitril-valsartan in patients with CTRCD treated in cardio-oncology units. METHODS We enrolled 635 patients with breast cancer and followed them with echocardiography and NT- proBNP. Patients who developed left ventricular dysfunction and heart failure were treated with angiotensin-converting enzyme inhibitors (ACEI) (enalapril) or angiotensin receptor blockers (ARB) (valsartan), aldosterone antagonists (eplerenone), digitalis and diuretics (furosemide), as needed. When patients remained symptomatic and met the PARADIGM-HF inclusion criteria, sacubitril/valsartan was started instead of enalapril or valsartan. We analyzed clinical, laboratory and echocardiographic variables to determine the beneficial effects of sacubitril/valsartan on left ventricular remodeling (improvement of left ventricular ejection fraction (LVEF), left ventricle internal diameter in diastole), diastolic dysfunction (E/e' ratio), reduction in NT-proBNP levels, New York Heart Association (NHYA) class and improvement in the 6-min walk test. Also, we analyzed serum creatinine and potassium levels to determine treatmentsafety in this population. Median follow-up was 20 months. RESULTS Twenty-eight patients developed cardiotoxicity and were treated with sacubitril/valsartan. The sacubitril/valsartan dose was 100 mg (sacubitril 49 mg/valsartan 51 mg) in 12 patients (42.85%) and 200 mg (sacubitril 97 mg/valsartan 103 mg) in 16 patients (57.15%). No deaths were reported, and one patient underwent heart transplantation. Baseline median NT-proBNP was 997.5 pg/ml (IQR 663.8 - 2380.8), which decreased to a median of 416.5 pg/ml (IQR 192.0-798.2) on follow-up with p < 0.001. Baseline NYHA functional class was III (78.6%) or IV (21.4%), and it improved to I (57.1%) or II (42.9%) on follow-up. LVEF increased with treatment from 26.7 ± 5.4% to 32.3 ± 5.5% (p < 0.001). There were also significant improvements in left ventricle internal diameter in diastole (LVIDD), diastolic function, 6-min walk test, and mitral valve regurgitation. There were no differences between basal and follow-up levels of serum creatinine or potassium. CONCLUSION Sacubitril/valsartan might be a promising treatment option in patients with refractory CTRCD.
Collapse
Affiliation(s)
- Vanesa Gregorietti
- Cardio-Oncology Department, Roffo Institute, 5481 Av San Martin. CABA,, Buenos Aires, Argentina
| | | | - Diego Costa
- Cardio-Oncology Department, Roffo Institute, 5481 Av San Martin. CABA,, Buenos Aires, Argentina
| | - Elías Ortega Chahla
- Cardio-Oncology Department, Roffo Institute, 5481 Av San Martin. CABA,, Buenos Aires, Argentina
| | - Andrés J Daniele
- Cardio-Oncology Department, Roffo Institute, 5481 Av San Martin. CABA,, Buenos Aires, Argentina.
| |
Collapse
|
5
|
Abstract
Cardiac ultrasound is increasingly used to guide hemodynamic decision making in the neonatal intensive care unit (NICU). This article focuses on likely future progress in training, accreditation, digital connectivity, miniaturization, and modality development. Many documents have been published internationally to guide cardiac ultrasound training, accreditation, and implementation in the NICU, but challenges remain in providing assessments of hemodynamic status without risking missed structural diagnoses. Advances in simulation training and digital connectivity provide an opportunity to standardize approaches across institutions and continents. Development of machine learning and ultrasound modalities in turn provide huge scope for improving robustness and completeness of assessment.
Collapse
Affiliation(s)
- Alan Groves
- Division of Newborn Medicine, Icahn School of Medicine at Mount Sinai, 1184 5th Avenue, New York, NY 10029, USA.
| |
Collapse
|
7
|
Cullen MW, Sinha SS, Sharma G. Fellows-in-Training and Early Career Section: Emerging Specialties for a New Year. J Am Coll Cardiol 2020; 75:1231-1232. [PMID: 32164895 DOI: 10.1016/j.jacc.2020.02.016] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/24/2022]
Affiliation(s)
- Michael W Cullen
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota.
| | - Shashank S Sinha
- Inova Heart and Vascular Institute, Inova Fairfax Medical Center, Falls Church, Virginia. https://twitter.com/ShashankSinhaMD
| | - Garima Sharma
- Johns Hopkins Ciccarone Center for Prevention of Cardiovascular Disease, Division of Cardiology, The Johns Hopkins University School of Medicine, Baltimore, Maryland. https://twitter.com/GarimaVSharmaMD
| |
Collapse
|