1
|
Lee YJ, Aghayev A, Azene EM, Bhatti S, Ewell JC, Hedgire SS, Kendi AT, Kim ESH, Kirsch DS, Nagpal P, Pillai AK, Ripley B, Tannenbaum A, Thiessen MEW, Thomas R, Woolsey S, Steigner ML. ACR Appropriateness Criteria® Screening for Abdominal Aortic Aneurysm. J Am Coll Radiol 2024; 21:S286-S291. [PMID: 38823950 DOI: 10.1016/j.jacr.2024.02.027] [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: 02/20/2024] [Accepted: 02/28/2024] [Indexed: 06/03/2024]
Abstract
Abdominal aortic aneurysm (AAA) is a significant vascular disease found in 4% to 8% of the screening population. If ruptured, its mortality rate is between 75% and 90%, and it accounts for up to 5% of sudden deaths in the United States. Therefore, screening of AAA while asymptomatic has been a crucial portion of preventive health care worldwide. Ultrasound of the abdominal aorta is the primary imaging modality for screening of AAA recommended for asymptomatic adults regardless of their family history or smoking history. Alternatively, duplex ultrasound and CT abdomen and pelvis without contrast may be appropriate for screening. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.
Collapse
Affiliation(s)
- Yoo Jin Lee
- University of California, San Francisco, San Francisco, California.
| | - Ayaz Aghayev
- Panel Chair, Brigham & Women's Hospital, Boston, Massachusetts
| | | | - Salman Bhatti
- University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania; Society for Cardiovascular Magnetic Resonance
| | - Joshua C Ewell
- Rutgers, New Jersey Medical School, Newark, New Jersey; Committee on Emergency Radiology-GSER
| | - Sandeep S Hedgire
- Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - A Tuba Kendi
- Mayo Clinic, Rochester, Minnesota; Commission on Nuclear Medicine and Molecular Imaging
| | - Esther S H Kim
- Atrium Health, Sanger Heart and Vascular Institute, Charlotte, North Carolina; American Society of Echocardiography
| | | | - Prashant Nagpal
- University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin
| | - Anil K Pillai
- University of Texas Southwestern Medical Center, Dallas, Texas
| | - Beth Ripley
- VA Puget Sound Health Care System and University of Washington, Seattle, Washington
| | | | - Molly E W Thiessen
- Denver Health Medical Center, Denver, Colorado and University of Colorado School of Medicine, Aurora, Colorado; American College of Emergency Physicians
| | - Richard Thomas
- Lahey Hospital and Medical Center, Burlington, Massachusetts
| | - Sarah Woolsey
- Association for Utah Community Health, Salt Lake City, Utah; American Academy of Family Physicians
| | | |
Collapse
|
2
|
Wang DS, Shen J, Majdalany BS, Khaja MS, Bhatti S, Ferencik M, Ganguli S, Gunn AJ, Heitner JF, Johri AM, Obara P, Ohle R, Sadeghi MM, Schermerhorn M, Siracuse JJ, Steenburg SD, Sutphin PD, Vijay K, Waite K, Steigner ML. ACR Appropriateness Criteria® Pulsatile Abdominal Mass, Suspected Abdominal Aortic Aneurysm: 2023 Update. J Am Coll Radiol 2023; 20:S513-S520. [PMID: 38040468 DOI: 10.1016/j.jacr.2023.08.010] [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: 08/15/2023] [Accepted: 08/22/2023] [Indexed: 12/03/2023]
Abstract
Abdominal aortic aneurysm (AAA) is defined as abnormal dilation of the infrarenal abdominal aortic diameter to 3.0 cm or greater. The natural history of AAA consists of progressive expansion and potential rupture. Although most AAAs are clinically silent, a pulsatile abdominal mass identified on physical examination may indicate the presence of an AAA. When an AAA is suspected, an imaging study is essential to confirm the diagnosis. This document reviews the relative appropriateness of various imaging procedures for the initial evaluation of suspected AAA. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.
Collapse
Affiliation(s)
- David S Wang
- Stanford University Medical Center, Stanford, California.
| | - Jody Shen
- Research Author, Stanford University Medical Center, Stanford, California
| | - Bill S Majdalany
- Panel Chair, University of Vermont Medical Center, Burlington, Vermont
| | - Minhaj S Khaja
- Panel Vice-Chair, University of Michigan, Ann Arbor, Michigan
| | - Salman Bhatti
- University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania; Society for Cardiovascular Magnetic Resonance
| | - Maros Ferencik
- Knight Cardiovascular Institute, Oregon Health & Science University, Portland, Oregon; Society of Cardiovascular Computed Tomography
| | - Suvranu Ganguli
- Boston Medical Center/Boston University School of Medicine, Boston, Massachusetts
| | - Andrew J Gunn
- University of Alabama at Birmingham, Birmingham, Alabama
| | - John F Heitner
- New York University Langone Health, New York, New York; Society for Cardiovascular Magnetic Resonance
| | - Amer M Johri
- Queen's University, Kingston, Ontario, Canada; American Society of Echocardiography
| | - Piotr Obara
- NorthShore University HealthSystem, Evanston, Illinois
| | - Robert Ohle
- Northern Ontario School of Medicine, Sudbury, Ontario, Canada; American College of Emergency Physicians
| | - Mehran M Sadeghi
- Yale School of Medicine, New Haven, Connecticut; American Society of Nuclear Cardiology
| | - Marc Schermerhorn
- Harvard Medical School and Beth Israel Deaconess Medical Center, Boston, Massachusetts; Society for Vascular Surgery
| | - Jeffrey J Siracuse
- Boston Medical Centers, Boston University, and Chobanian and Avedisian School of Medicine, Boston, Massachusetts; Society for Vascular Surgery
| | - Scott D Steenburg
- Indiana University School of Medicine and Indiana University Health, Indianapolis, Indiana; Committee on Emergency Radiology-GSER
| | | | - Kanupriya Vijay
- University of Texas Southwestern Medical Center, Dallas, Texas
| | - Kathleen Waite
- Duke University Medical Center, Durham, North Carolina, Primary care physician
| | | |
Collapse
|
3
|
Zielinski AH, Bredahl KK, Ghulam QM, Rouet L, Dufour C, Sillesen HH, Eiberg JP. Full-Volume Assessment of Abdominal Aortic Aneurysm by Improved-Field-of-View 3-D Ultrasound Performs Comparably to Computed Tomographic Angiography. ULTRASOUND IN MEDICINE & BIOLOGY 2022; 48:283-292. [PMID: 34823944 DOI: 10.1016/j.ultrasmedbio.2021.10.018] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/12/2021] [Revised: 10/07/2021] [Accepted: 10/26/2021] [Indexed: 06/13/2023]
Abstract
Three-dimensional ultrasound (US) of abdominal aortic aneurysms (AAAs) is limited by the field-of-view of the 3D-US transducer. To obtain an extended field-of-view (XFoV), two transducer navigation system-assisted US protocols have been developed: XFoV-2D and XFoV-3D. In this study, the XFoV US protocols were compared with the currently available 3D-US protocol with standard field-of-view (FoV-st) and the established gold standard, computed tomography angiography (CTA). A total of 65 patients with AAA were included, and AAA imaging was processed offline with prototype software. The novel XFoV-2D and XFoV-3D protocols allowed for assessment of full AAA volume in significantly more patients (45/65 [69%] and 43/65 [66%], respectively), compared with the current 3D-US standard, FoV-st (30/65 [46%] patients). The mean difference in AAA volume estimation between each XFoV US protocol and 3-D CTA differed significantly (XFoV-2D: 16.9 mL, XFoV-3D: 7.6 mL, p = 0.002), indicating that XFoV-3D agreed best with 3D-CTA. No significant difference was found in the variance of full AAA volume quantification between each XFoV US protocol and CTA (p = 0.49). It is concluded that the XFoV US protocols improved the generation of full AAA volumes compared with the currently available 3D-US technology, with AAA volume estimates comparable to CTA estimates.
Collapse
Affiliation(s)
| | - Kim Kargaard Bredahl
- Department of Vascular Surgery, Rigshospitalet, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | | | | | | | - Henrik Hegaard Sillesen
- Department of Vascular Surgery, Rigshospitalet, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Jones Peter Eiberg
- Department of Vascular Surgery, Rigshospitalet, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark; Copenhagen Academy for Medical Education and Simulation (CAMES), Capital Region of Denmark, Copenhagen, Denmark
| |
Collapse
|
4
|
Johnsen L, Hisdal J, Jonung T, Braaten A, Pedersen G. Three-dimensional Ultrasound Volume and Conventional Ultrasound Diameter Changes are Equally Good Markers of Endoleak in Follow-up after Endovascular Aneurysm Repair. J Vasc Surg 2021; 75:1030-1037.e1. [PMID: 34606959 DOI: 10.1016/j.jvs.2021.08.103] [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: 04/08/2021] [Accepted: 08/29/2021] [Indexed: 10/20/2022]
Abstract
INTRODUCTION The main disadvantages of computed tomography angiography in follow-up after endovascular aneurysm repair are the risks of contrast-induced renal impairment and radiation-induced cancer. Three-dimensional ultrasound is a new technique for volume estimation of the aneurysm sac. Some studies have reported promising results. The aim of this study was to evaluate the accuracy and precision of three-dimensional ultrasound aneurysm sac-volume estimates, and to explore whether volume and/or diameter changes on ultrasound can be used as markers of endoleak. METHODS A single-center diagnostic accuracy study was performed. 92 Patients planned for endovascular aneurysm repair were prospectively and consecutively enrolled (2013-2016). Aneurysm sac diameter and volume were measured using computed tomography angiography, conventional ultrasound, and three-dimensional ultrasound preoperatively and 1, 6, 12, and 24 months postoperatively. Three-dimensional ultrasound was performed with a commercially available electromechanical transducer. Patients with endoleak were observed 5 years after endovascular aneurysm repair. RESULTS 79 men and 13 women were included. Mean age was 74 years (57-92). Median follow-up was 24 months. Endoleak cases were observed for up to 55 months. Diameter measurements on conventional ultrasound correlated well with CT diameters (r = 0.9, P < 0.05, n = 347), and Bland-Altman analyses showed an upper limit of agreement of +0.5 cm and a lower limit of agreement of -0.8 cm. The mean difference was -0.13 cm ± 0.36 cm. Three-dimensional ultrasound volumes had a correlation with computed tomography angiography diameters of r = 0.8 (P < 0.05, n = 347) and with three-dimensional computed tomography volumes of r = 0.8 (P < 0.05, n = 155). Receiver operating characteristic analyses showed that the diameter and volume changes which led to reintervention were most accurate at 24-month follow-up, with area-under-the-curve percentage changes of 0.98 (two-dimensional ultrasound), 0.97 (three-dimensional ultrasound), and 0.97 (two-dimensional computed tomography). DISCUSSION Both diameter and volume changes can be used as markers for endoleak with excellent areas under the curve on receiver operating characteristic analyses. However, three-dimensional ultrasound volumes did not add any further diagnostic information. Conventional 2D diameter measurements were as accurate as volume changes as markers of endoleak. CONCLUSION Type II endoleaks can safely be followed up using a simple diameter measurement on conventional ultrasound.
Collapse
Affiliation(s)
- L Johnsen
- Haukeland University Hospital; University of Bergen; Norwegian University of Science and Technology.
| | - J Hisdal
- Norwegian University of Science and Technology; Oslo University Hospital; University of Oslo
| | | | | | - G Pedersen
- Haukeland University Hospital; University of Bergen
| |
Collapse
|
5
|
Svendsen MBS, Ghulam QM, Zielinski AH, Lachenmeier C, Eiberg JP. Validation of an assessment tool for estimation of abdominal aortic aneurysm compression in diagnostic ultrasound. ULTRASONICS 2021; 116:106484. [PMID: 34102524 DOI: 10.1016/j.ultras.2021.106484] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/11/2020] [Revised: 03/26/2021] [Accepted: 05/27/2021] [Indexed: 06/12/2023]
Abstract
The study investigated ultrasound (US) transducer push, tantamount to applied transducer pressure, during abdominal aortic aneurysm (AAA) US scanning in a simulated non-clinical setup. During an assessment of maximal AAA diameter on a three-dimensional print-based AAA phantom, US transducer push varied as much as 2000% (range: 0.52-12.45 kPa) amongst 16 experienced sonographers. The mean transducer push was 5.54 ± 3.91 kPa (CV = 0.71). Deformation of a standardized gel-pad allowed for transducer push calculation based on US images; Young's modulus of the gel-pad was estimated to 44,26 N/m2. The method is theoretically validated in a safe and non-clinical environment. Future investigations with the aim of clinical validation of the gel-pad principle on AAA patients are suggested, including the objectification of the magnitude of an eventual transducer push-related error during US AAA diameter measurement.
Collapse
Affiliation(s)
| | - Qasam Mohammed Ghulam
- Department of Vascular Surgery, Rigshospitalet, Blegdamsvej 9, 2100 Copenhagen, Denmark.
| | - Alexander Hakon Zielinski
- Department of Vascular Surgery, Rigshospitalet, Blegdamsvej 9, 2100 Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Blegdamsvej 3B, 2200 Copenhagen, Denmark
| | - Christian Lachenmeier
- Copenhagen Academy for Medical Education and Simulation (CAMES), Teilum, Blegdamsvej 9, 2100 Copenhagen, Denmark
| | - Jonas Peter Eiberg
- Copenhagen Academy for Medical Education and Simulation (CAMES), Teilum, Blegdamsvej 9, 2100 Copenhagen, Denmark; Department of Vascular Surgery, Rigshospitalet, Blegdamsvej 9, 2100 Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Blegdamsvej 3B, 2200 Copenhagen, Denmark
| |
Collapse
|
6
|
Fadel BM, Mohty D, Kazzi BE, Alamro B, Arshi F, Mustafa M, Echahidi N, Aboyans V. Ultrasound Imaging of the Abdominal Aorta: A Comprehensive Review. J Am Soc Echocardiogr 2021; 34:1119-1136. [PMID: 34224827 DOI: 10.1016/j.echo.2021.06.012] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/23/2021] [Revised: 06/10/2021] [Accepted: 06/10/2021] [Indexed: 11/28/2022]
Abstract
Ultrasound is the imaging modality of choice for the initial evaluation of disorders that involve the abdominal aorta (AA). The diagnostic value of ultrasound resides in its ability to allow assessment of the anatomy and structure of the AA using two- dimensional, three-dimensional, and contrast-enhanced imaging. Moreover, ultrasound permits evaluation of the physiologic and hemodynamic consequences of abnormalities through Doppler interrogation of blood flow, thus enabling the identification and quantification of disorders within the AA and beyond its boundaries. The approach to ultrasound imaging of the AA varies, depending on the purpose of the study and whether it is performed in a radiology or vascular laboratory or in an echocardiography laboratory. The aim of this review is to demonstrate the usefulness of ultrasound imaging for the detection and evaluation of disorders that involve the AA, detail the abnormalities that are detected or further assessed, and outline its value for echocardiographers, sonographers, and radiologists.
Collapse
Affiliation(s)
- Bahaa M Fadel
- King Faisal Specialist Hospital & Research Center, Riyadh, Saudi Arabia; Alfaisal University, Riyadh, Saudi Arabia.
| | - Dania Mohty
- King Faisal Specialist Hospital & Research Center, Riyadh, Saudi Arabia; Alfaisal University, Riyadh, Saudi Arabia; Department of Cardiology, Dupuytren-2 University Hospital, and Inserm 1094 & IRD, Limoges University, Limoges, France
| | | | - Bandar Alamro
- King Faisal Specialist Hospital & Research Center, Riyadh, Saudi Arabia; Alfaisal University, Riyadh, Saudi Arabia
| | - Fatima Arshi
- King Faisal Specialist Hospital & Research Center, Riyadh, Saudi Arabia
| | - Manal Mustafa
- King Faisal Specialist Hospital & Research Center, Riyadh, Saudi Arabia
| | - Najmeddine Echahidi
- King Faisal Specialist Hospital & Research Center, Riyadh, Saudi Arabia; Department of Cardiology, Dupuytren-2 University Hospital, and Inserm 1094 & IRD, Limoges University, Limoges, France
| | - Victor Aboyans
- Department of Cardiology, Dupuytren-2 University Hospital, and Inserm 1094 & IRD, Limoges University, Limoges, France
| |
Collapse
|
7
|
Bredahl KK, Taudorf M, Ghulam QM, Rouet L, Sillesen HH, Eiberg JP. Three- and Two-Dimensional Ultrasound is as Accurate as Computed Tomography in Aortic Sac Assessment after Endovascular Aortic Repair. Ann Vasc Surg 2020; 72:321-329. [PMID: 33160060 DOI: 10.1016/j.avsg.2020.09.061] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2020] [Revised: 09/23/2020] [Accepted: 09/25/2020] [Indexed: 10/23/2022]
Abstract
BACKGROUND To compare aortic sac changes after endovascular aneurysm repair (EVAR) assessed by three-dimensional ultrasound (3D-US), two-dimensional ultrasound (2D-US), and traditional computed tomographic angiography (CTA). METHODS Using volume assessment with three-dimensional CTA (3D-CTA-volume) as the gold standard, this study investigated aortic sac changes at three and 12 months after EVAR with three different ultrasound methods (2D-US anterior-posterior (AP) diameter, 3D-US AP centerline diameter, and 3D-US partial volume), and traditional CT multiplanar outer-to-outer diameter (CT-MPR OTO diameter). From august 1st, 2011 to January 2014, consecutive EVAR patients (n = 113) were available for analysis in two time intervals; 1) between preoperative and three-month follow-up and 2) between three and 12 month follow-up. RESULTS The risk of missing true aortic sac growth (false negative finding) at three-month postoperative visit using 3D-US partial volume, 3D-US AP centerline diameter, 2D-US AP diameter, and CT-MPR OTO diameter was 19%, 21%, 22%, and 18%, respectively. Corresponding low sensitivities (0% to 21%) and kappa-values (<0.50) in detecting aortic sac changes were found. The risk of missing true growth between three and 12 months were lower (6%, 5%, 6%, and 6%, respectively), and matching sensitivities 33%, 33%, 17%, and 17%, respectively. CONCLUSIONS All tested methods for aortic sac changes were as good as traditional CT-MPR OTO diameter and corresponded poorly with 3D-CTA-volume at three months postoperative visit but substantially better after 12 months where the residual sac change was more profound.
Collapse
Affiliation(s)
- Kim K Bredahl
- Department of Vascular Surgery, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark.
| | - Mikkel Taudorf
- Department of Radiology, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Qasam M Ghulam
- Department of Vascular Surgery, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | | | - Henrik H Sillesen
- Department of Vascular Surgery, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Jonas P Eiberg
- Department of Vascular Surgery, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark; Copenhagen Academy for Medical Education and Simulation (CAMES), Capital Region of Denmark, Copenhagen, Denmark
| |
Collapse
|
8
|
Clinical validation of three-dimensional ultrasound for abdominal aortic aneurysm. J Vasc Surg 2020; 71:180-188. [DOI: 10.1016/j.jvs.2019.03.066] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2019] [Accepted: 03/30/2019] [Indexed: 11/19/2022]
|
9
|
Lee R, Jarchi D, Perera R, Jones A, Cassimjee I, Handa A, Clifton DA. Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in Humans. EJVES Short Rep 2018; 39:24-28. [PMID: 29988820 PMCID: PMC6033055 DOI: 10.1016/j.ejvssr.2018.03.004] [Citation(s) in RCA: 41] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2018] [Revised: 03/15/2018] [Accepted: 03/25/2018] [Indexed: 01/16/2023] Open
Abstract
Objective Accurate prediction of abdominal aortic aneurysm (AAA) growth in an individual can allow personalised stratification of surveillance intervals and better inform the timing for surgery. The authors recently described the novel significant association between flow mediated dilatation (FMD) and future AAA growth. The feasibility of predicting future AAA growth was explored in individual patients using a set of benchmark machine learning techniques. Methods The Oxford Abdominal Aortic Aneurysm Study (OxAAA) prospectively recruited AAA patients undergoing the routine NHS management pathway. In addition to the AAA diameter, FMD was systemically measured in these patients. A benchmark machine learning technique (non-linear Kernel support vector regression) was applied to predict future AAA growth in individual patients, using their baseline FMD and AAA diameter as input variables. Results Prospective growth data were recorded at 12 months (360 ± 49 days) in 94 patients. Of these, growth data were further recorded at 24 months (718 ± 81 days) in 79 patients. The average growth in AAA diameter was 3.4% at 12 months, and 2.8% per year at 24 months. The algorithm predicted the individual's AAA diameter to within 2 mm error in 85% and 71% of patients at 12 and 24 months. Conclusions The data highlight the utility of FMD as a biomarker for AAA and the value of machine learning techniques for AAA research in the new era of precision medicine. Flow mediated dilatation of brachial artery is a biomarker of AAA progression. It is feasible to predict future AAA growth in individuals using machine learning techniques. Endothelial dysfunction is a key feature in human AAA disease.
Collapse
Affiliation(s)
- R Lee
- Nuffield Department of Surgical Sciences, University of Oxford, Oxford, UK
| | - D Jarchi
- Department of Engineering Science, University of Oxford, Oxford, UK
| | - R Perera
- Nuffield Department of Primary Care Health, University of Oxford, Oxford, UK
| | - A Jones
- Nuffield Department of Surgical Sciences, University of Oxford, Oxford, UK
| | - I Cassimjee
- Nuffield Department of Surgical Sciences, University of Oxford, Oxford, UK
| | - A Handa
- Nuffield Department of Surgical Sciences, University of Oxford, Oxford, UK
| | - D A Clifton
- Nuffield Department of Primary Care Health, University of Oxford, Oxford, UK
| | | | | |
Collapse
|