1
|
de Jong CMM, Kroft LJM, van Mens TE, Huisman MV, Stöger JL, Klok FA. Modern imaging of acute pulmonary embolism. Thromb Res 2024; 238:105-116. [PMID: 38703584 DOI: 10.1016/j.thromres.2024.04.016] [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: 11/24/2023] [Revised: 03/16/2024] [Accepted: 04/15/2024] [Indexed: 05/06/2024]
Abstract
The first-choice imaging test for visualization of thromboemboli in the pulmonary vasculature in patients with suspected acute pulmonary embolism (PE) is multidetector computed tomography pulmonary angiography (CTPA) - a readily available and widely used imaging technique. Through technological advancements over the past years, alternative imaging techniques for the diagnosis of PE have become available, whilst others are still under investigation. In particular, the evolution of artificial intelligence (AI) is expected to enable further innovation in diagnostic management of PE. In this narrative review, current CTPA techniques and the emerging technology photon-counting CT (PCCT), as well as other modern imaging techniques of acute PE are discussed, including CTPA with iodine maps based on subtraction or dual-energy acquisition, single-photon emission CT (SPECT), magnetic resonance angiography (MRA), and magnetic resonance direct thrombus imaging (MRDTI). Furthermore, potential applications of AI are discussed.
Collapse
Affiliation(s)
- C M M de Jong
- Department of Medicine - Thrombosis and Hemostasis, Leiden University Medical Center, Leiden, the Netherlands
| | - L J M Kroft
- Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands
| | - T E van Mens
- Department of Medicine - Thrombosis and Hemostasis, Leiden University Medical Center, Leiden, the Netherlands
| | - M V Huisman
- Department of Medicine - Thrombosis and Hemostasis, Leiden University Medical Center, Leiden, the Netherlands
| | - J L Stöger
- Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands
| | - F A Klok
- Department of Medicine - Thrombosis and Hemostasis, Leiden University Medical Center, Leiden, the Netherlands.
| |
Collapse
|
2
|
Hamel C, Avard B, Isaac N, Jassal D, Kirkpatrick I, Leipsic J, Michaud A, Worrall J, Nguyen ET. Canadian Association of Radiologists Cardiovascular Imaging Referral Guideline. Can Assoc Radiol J 2024:8465371241246425. [PMID: 38733286 DOI: 10.1177/08465371241246425] [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: 05/13/2024] Open
Abstract
The Canadian Association of Radiologists (CAR) Cardiovascular Expert Panel is made up of physicians from the disciplines of radiology, cardiology, and emergency medicine, a patient advisor, and an epidemiologist/guideline methodologist. After developing a list of 30 clinical/diagnostic scenarios, a rapid scoping review was undertaken to identify systematically produced referral guidelines that provide recommendations for one or more of these clinical/diagnostic scenarios. Recommendations from 48 guidelines and contextualization criteria in the Grading of Recommendations, Assessment, Development, and Evaluations (GRADE) for guidelines framework were used to develop 125 recommendation statements across the 30 scenarios (27 unique scenarios as 2 scenarios point to the CAR Thoracic Diagnostic Imaging Referral Guideline and the acute pericarditis subscenario is included under 2 main scenarios). This guideline presents the methods of development and the referral recommendations for acute chest pain syndromes, chronic chest pain, cardiovascular screening and risk stratification, pericardial syndromes, intracardiac/pericardial mass, suspected valvular disease cardiomyopathy, aorta, venous thrombosis, and peripheral vascular disease.
Collapse
Affiliation(s)
- Candyce Hamel
- Canadian Association of Radiologists, Ottawa, ON, Canada
| | - Barb Avard
- North York General Hospital, Toronto, ON, Canada
| | - Neil Isaac
- Department of Medical Imaging, North York General Hospital, Toronto, ON, Canada
| | - Davinder Jassal
- Section of Cardiology, Department of Internal Medicine, Max Rady College of Medicine, Rady Faculty of Health Sciences University of Manitoba, Bergen Cardiac Care Centre St. Boniface Hospital, Winnipeg, MB, Canada
| | - Iain Kirkpatrick
- Max Rady College of Medicine, University of Manitoba, St. Boniface Hospital, Winnipeg, MB, Canada
| | - Jonathon Leipsic
- Department of Medicine, University of British Columbia, Vancouver, BC, Canada
| | | | - James Worrall
- Department of Emergency Medicine, The Ottawa Hospital, Ottawa, ON, Canada
| | - Elsie T Nguyen
- University Medical Imaging Toronto, University of Toronto, Toronto General Hospital, Peter Munk Cardiac Centre, Toronto, ON, Canada
| |
Collapse
|
3
|
Barash Y, Klang E, Konen E, Sorin V. ChatGPT-4 Assistance in Optimizing Emergency Department Radiology Referrals and Imaging Selection. J Am Coll Radiol 2023; 20:998-1003. [PMID: 37423350 DOI: 10.1016/j.jacr.2023.06.009] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Revised: 06/19/2023] [Accepted: 06/29/2023] [Indexed: 07/11/2023]
Abstract
PURPOSE The quality of radiology referrals influences patient management and imaging interpretation by radiologists. The aim of this study was to evaluate ChatGPT-4 as a decision support tool for selecting imaging examinations and generating radiology referrals in the emergency department (ED). METHODS Five consecutive clinical notes from the ED were retrospectively extracted, for each of the following pathologies: pulmonary embolism, obstructing kidney stones, acute appendicitis, diverticulitis, small bowel obstruction, acute cholecystitis, acute hip fracture, and testicular torsion. A total of 40 cases were included. These notes were entered into ChatGPT-4, requesting recommendations on the most appropriate imaging examinations and protocols. The chatbot was also asked to generate radiology referrals. Two independent radiologists graded the referral on a scale ranging from 1 to 5 for clarity, clinical relevance, and differential diagnosis. The chatbot's imaging recommendations were compared with the ACR Appropriateness Criteria (AC) and with the examinations performed in the ED. Agreement between readers was assessed using linear weighted Cohen's κ coefficient. RESULTS ChatGPT-4's imaging recommendations aligned with the ACR AC and ED examinations in all cases. Protocol discrepancies between ChatGPT and the ACR AC were observed in two cases (5%). ChatGPT-4-generated referrals received mean scores of 4.6 and 4.8 for clarity, 4.5 and 4.4 for clinical relevance, and 4.9 from both reviewers for differential diagnosis. Agreement between readers was moderate for clinical relevance and clarity and substantial for differential diagnosis grading. CONCLUSIONS ChatGPT-4 has shown potential in aiding imaging study selection for select clinical cases. As a complementary tool, large language models may improve radiology referral quality. Radiologists should stay informed about this technology and be mindful of potential challenges and risks.
Collapse
Affiliation(s)
- Yiftach Barash
- Department of Diagnostic Imaging, Chaim Sheba Medical Center, Tel Hashomer, Israel; Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel; DeepVision Lab, Chaim Sheba Medical Center, Tel Hashomer, Israel.
| | - Eyal Klang
- Department of Diagnostic Imaging, Chaim Sheba Medical Center, Tel Hashomer, Israel; Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel; Head, Sami Sagol AI Hub, ARC, Chaim Sheba Medical Center, Tel Hashomer, Israel; DeepVision Lab, Chaim Sheba Medical Center, Tel Hashomer, Israel
| | - Eli Konen
- Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel; Head, Department of Diagnostic Imaging, Chaim Sheba Medical Center, Tel Hashomer, Israel
| | - Vera Sorin
- Department of Diagnostic Imaging, Chaim Sheba Medical Center, Tel Hashomer, Israel; Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel; DeepVision Lab, Chaim Sheba Medical Center, Tel Hashomer, Israel
| |
Collapse
|
4
|
Sametzadeh M, Dadgostar S, Hanafi MG, Mohammadi M. Application of CT pulmonary angiography and echocardiography in acute pulmonary embolism: A cross-sectional study. Health Sci Rep 2023; 6:e1546. [PMID: 37670847 PMCID: PMC10476463 DOI: 10.1002/hsr2.1546] [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: 05/19/2023] [Revised: 07/31/2023] [Accepted: 08/22/2023] [Indexed: 09/07/2023] Open
Abstract
Background Pulmonary Embolism (PE) is an acute and potentially fatal condition defined as the blockage of pulmonary arteries by an embolism that can be from various origins. Objective The present study aimed to investigate the findings of computed tomography pulmonary angiography (CTPA) and echocardiography in patients with acute PE. Methods The present cross-sectional study included some patients with clinical manifestations of PE who underwent CTPA and echocardiography. The radiologic findings, PE severity, and outcome of the patients were recorded. Moreover, echocardiography was performed by an expert cardiologist using a high-resolution device, while CTPA was performed by an expert radiologist using a 16-slice device and a two-step selective test bolus method. Results According to our findings, a total number of 147 patients were diagnosed with PE, including 44 (29.93%), 44 (29.93%), and 59 (40.14%) cases of mild, moderate, and severe PE, respectively. Moreover, 25 patients (17%) finally expired due to PE. Regarding the CTPA findings, 31 patients (21.1%) had septum flattening, while 35 (23.8%) had a septum deviation toward the left ventricle. Also, there were significant correlations between mortality and some CTPA findings, including severe PE (p < 0.001), the presence of septal deviation (p = 0.007), and higher diameters of the main pulmonary artery (p < 0.001) and right ventricle (p = 0.008). Conclusion CTPA is a valid and accessible modality for diagnosing and evaluating PE in suspected patients. Moreover, several findings in CTPA could predict adverse outcomes, such as death, in patients with PE.
Collapse
Affiliation(s)
- Mozhgan Sametzadeh
- Department of Radiology, School of Medicine, Golestan HospitalAhvaz Jundishapur University of Medical SciencesAhvazIran
| | - Sahar Dadgostar
- Department of Radiology, School of MedicineAhvaz Jundishapur University of Medical SciencesAhvazIran
| | - Mohammad Ghasem Hanafi
- Department of Radiology, School of Medicine, Imam Khomeini HospitalAhvaz Jundishapur University of Medical SciencesAhvazIran
| | - Mohammad Mohammadi
- Department of Cardiology, School of Medicine, Golestan HospitalAhvaz Jundishapur University of Medical SciencesAhvazIran
| |
Collapse
|
5
|
Diagnostic test accuracy of imaging modalities for adults with acute pulmonary embolism: A systematic review and meta-analysis. J Med Imaging Radiat Sci 2023; 54:178-194. [PMID: 36456459 DOI: 10.1016/j.jmir.2022.11.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2022] [Revised: 10/26/2022] [Accepted: 11/07/2022] [Indexed: 11/29/2022]
Abstract
OBJECTIVES This systematic review and meta-analysis aimed to evaluate the current literature on diagnostic test accuracy (DTA) of imaging modalities for adults with acute pulmonary embolism (APE). BACKGROUND Medical imaging plays an integral role in evaluating and managing those with APE. Guidance for imaging modality use for APE diagnosis varies due to a lack of clinical standardisation. Despite this, CTPA remains the first-line imaging modality used by clinicians. METHODS A literature search of PubMed, EMBASE, Trove and Mednar databases (2012-2020; English language) was performed. Studies assessing the DTA of imaging modalities for APE diagnosis were included. DTA studies methodological quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2 tool). Results of eligible studies were pooled using random or fixed effects modelling the calculate the pooled DTA of explored imaging modalities for APE. The Higgins I2 test were performed to assess between study heterogeneity. RESULTS 10 Studies, involving 998 participants, were enrolled and pooled using the random effects model. Of the explored modalities, magnetic resonance imaging (MRI), specifically pulmonary MRI and magnetic resonance pulmonary angiography (MRPA) exhibited the highest pooled DTA. Sensitivity, specificity, negative likelihood ratio, positive likelihood ratio and diagnostic odds ratio for MRPA were 0.952 (95% CI, 0.881 to 0.987), 0.857 (95% CI, 0.637 to 0.97), 5.631 (95% CI, 2.163 to 14.659), 0.06 (95% CI, 0.007 to 0.537) and 80.310 (95% CI, 15.607 to 413.25) respectively. Based on the QUADAS-2 criteria, most studies presented low to moderate risk of bias and concern regarding applicability. CONCLUSION The explored ultrasound and MRI protocols which exhibit a lower radiation burden when compared to the current gold standard computed tomography pulmonary angiography (CTPA), have acceptable diagnostic accuracy for APE and can be useful in certain situations.
Collapse
|