A CCTA Image Assisted Triage Software for the Assessment of Patients With Suspected Coronary Artery Disease

A CCTA Image Assisted Triage Software for the Assessment of Patients With Suspected Coronary Artery Disease: a Retrospective, Multi-center, Blind-evaluation Study

The goal of this clinical trail is to evaluate the effectiveness and accuracy of the CCTA image assisted triage software(DeepVessel® Cardisight, Keya Medical.) for the triage of patients with suspected coronary artery disease.

Study Overview

• Status: Active, not recruiting
• Conditions: Coronary Heart Disease
• Intervention / Treatment: Other: No intervention

Detailed Description

The CCTA images collected by each center within a certain period of time would be screened, desensitized, and then evaluated by the software and independent expert group respectively, to evaluate the effectiveness and accuracy of the coronary CT angiography image stenosis assisted triage software developed by Koyal Medical Technology Co.

Experiment group: Evaluated by the software Independent expert group: Evaluated by experts (≥5 years of CCTA experience required)

• Study Type: Observational
• Enrollment (Actual): 1093

Contacts and Locations

Study Locations

• China
  • Beijing
    • Beijing, Beijing, China
      • Fuwai Hospital, Chinese Academy of Medical Sciences
  • Guangdong
    • Guangzhou, Guangdong, China
      • The Pearl River Hospital of Southern Medical University
  • Guizhou
    • Zunyi, Guizhou, China
      • Affiliated Hospital of Zunyi Medical University
  • Hebei
    • Shijiazhuang, Hebei, China
      • The First Affiliated Hospital of Hebei Medical University
  • Hubei
    • Huanggang, Hubei, China
      • Huanggang Central Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study Population

Suspected patients with coronary heart disease.

Description

Inclusion Criteria:

1. CCTA images acquired by CT detectors need to meet the following requirements:

   • Check Modal = CT
   • Number of detector rows ≥ 64 rows
   • Layer thickness ≤1mm
   • Layer spacing ≤1mm
   • Pixel pitch ≤ 0.5mm
   • Ball tube voltage ≥ 70kV
   • Number of layers ≥ 100 layers
2. CCTA image quality score ≥ 3 (5-point Likert scale).

Exclusion Criteria:

1. Severe coronary artery calcification, which in the judgment of readers affects the stenosis adjudicator;
2. Previous percutaneous coronary intervention (PCI) or coronary artery bypass grafting (CABG);
3. Congenital anomalies of coronary artery origin or other malformations;
4. Coronary artery occlusive lesions;
5. Implantation of the pacemaker, internal defibrillator electrode, or prosthetic heart valve.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

Suspected patients with coronary heart disease.; The coronary CT angiography (CCTA) images collected by each center within a certain period of time will be desensitized after the screening is successful. The final CCTA images were sent to an independent judgment expert group for diagnosis, the results of the test group and the independent judgment expert group were compared, and the clinical application of the coronary artery CT angiography image vascular stenosis auxiliary triage software developed by Keya Medical Technology Co., Ltd. was evaluated. Validity and Accuracy

Other: No intervention; Due to observational study

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity and specificity of experiment group in triage for patients with suspected coronary artery disease	Based on the results of the independent expert group, uses stenosis degree≥50% as the boundary for triage indication on a per-patient basis.	October 13,2022 to March 1,2023

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic time	Independent expert group: recording the sum of image post-processing time (T1) and the time to produce the results (T2); Experimental group: recording the time from image post-processing to outputting results; Calculate the difference between the two groups.	October 13,2022 to March 1,2023
Patient as research unit	Evaluation criteria were established based on the results of the independent expert group to evaluate the total conformity rate, KAPPA value, positive predictive value (PPV) and negative predictive value (NPV) of triage tips for patients with suspected coronary heart disease in the experimental group.	October 13,2022 to March 1,2023
Blood vessels were used as the research unit	Evaluation criteria were established based on the results of the independent expert group to evaluate the total conformity rate, KAPPA value, positive predictive value (PPV) and negative predictive value (NPV) of triage tips for patients with suspected coronary heart disease in the experimental group.	October 13,2022 to March 1,2023
The vascular segment was used as the research unit	Evaluation criteria were established based on the results of the independent expert group to evaluate the total conformity rate, KAPPA value, positive predictive value (PPV) and negative predictive value (NPV) of triage tips for patients with suspected coronary heart disease in the experimental group.	October 13,2022 to March 1,2023
Gender stratified statistics, respectively, with patients and blood vessels as research units	Evaluation criteria were established based on the results of the independent expert group to evaluate the sensitivity and specificity of the trial group to the triage hints of suspected patients with coronary heart disease	October 13,2022 to March 1,2023
Manufacturer stratified statistics, respectively, with patients and blood vessels as research units	Evaluation criteria were established based on the results of the independent expert group to evaluate the sensitivity and specificity of the trial group to the triage hints of suspected patients with coronary heart disease	October 13,2022 to March 1,2023
Row number stratified statistics, respectively, with patients and blood vessels as research units	Evaluation criteria were established based on the results of the independent expert group to evaluate the sensitivity and specificity of the trial group to the triage hints of suspected patients with coronary heart disease	October 13,2022 to March 1,2023
The stratified statistics of tube voltage were conducted with patients and blood vessels as research units	Evaluation criteria were established based on the results of the independent expert group to evaluate the sensitivity and specificity of the trial group to the triage hints of suspected patients with coronary heart disease	October 13,2022 to March 1,2023
Layer thickness stratified statistics, patients and blood vessels were used as research units	Evaluation criteria were established based on the results of the independent expert group to evaluate the sensitivity and specificity of the trial group to the triage hints of suspected patients with coronary heart disease	October 13,2022 to March 1,2023
The patients and blood vessels were selected as the research units	Evaluation criteria were established based on the results of the independent expert group to evaluate the sensitivity and specificity of the trial group to the triage hints of suspected patients with coronary heart disease	October 13,2022 to March 1,2023
Post-processing image quality evaluation	Calculate the percentage of post-processing images with the image quality score of 2 or above in the total post-processing images, and the difference between the independent expert group and experimental group.	October 13,2022 to March 1,2023
Software performance evaluation	From the function of use, ease of operation, stability to evaluate, divided into satisfactory, general, unsatisfactory three levels.	October 13,2022 to March 1,2023

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Device Defects	In the course of clinical trials, there are unreasonable risks that may endanger human health and life safety under normal use of medical devices, such as label errors, quality problems, and frequent failures	October 13,2022 to March 1,2023

Collaborators and Investigators

• Sponsor: Keya Medical
• Investigators: Principal Investigator: Bin Lu, Chinese Academy of Medical Sciences, Fuwai Hospital

Publications and helpful links

General Publications

• Meijboom WB, Meijs MF, Schuijf JD, Cramer MJ, Mollet NR, van Mieghem CA, Nieman K, van Werkhoven JM, Pundziute G, Weustink AC, de Vos AM, Pugliese F, Rensing B, Jukema JW, Bax JJ, Prokop M, Doevendans PA, Hunink MG, Krestin GP, de Feyter PJ. Diagnostic accuracy of 64-slice computed tomography coronary angiography: a prospective, multicenter, multivendor study. J Am Coll Cardiol. 2008 Dec 16;52(25):2135-44. doi: 10.1016/j.jacc.2008.08.058.
• Lucke C, Foldyna B, Andres C, Boehmer-Lasthaus S, Grothoff M, Nitzsche S, Gutberlet M, Lehmkuhl L. Post-processing in cardiovascular computed tomography: performance of a client server solution versus a stand-alone solution. Rofo. 2014 Dec;186(12):1111-21. doi: 10.1055/s-0034-1366726. Epub 2014 Aug 14.
• Choi AD, Marques H, Kumar V, Griffin WF, Rahban H, Karlsberg RP, Zeman RK, Katz RJ, Earls JP. CT Evaluation by Artificial Intelligence for Atherosclerosis, Stenosis and Vascular Morphology (CLARIFY): A Multi-center, international study. J Cardiovasc Comput Tomogr. 2021 Nov-Dec;15(6):470-476. doi: 10.1016/j.jcct.2021.05.004. Epub 2021 Jun 12.
• Paul JF, Rohnean A, Giroussens H, Pressat-Laffouilhere T, Wong T. Evaluation of a deep learning model on coronary CT angiography for automatic stenosis detection. Diagn Interv Imaging. 2022 Jun;103(6):316-323. doi: 10.1016/j.diii.2022.01.004. Epub 2022 Jan 26.
• Meyer M, Schoepf UJ, Fink C, Goldenberg R, Apfaltrer P, Gruettner J, Vajcs D, Schoenberg SO, Henzler T. Diagnostic performance evaluation of a computer-aided simple triage system for coronary CT angiography in patients with intermediate risk for acute coronary syndrome. Acad Radiol. 2013 Aug;20(8):980-6. doi: 10.1016/j.acra.2013.02.014. Epub 2013 Jun 2.

Helpful Links

• Guerbet. Xenetix® 350: Comparative Assessment of Image Quality for Coronary CT Angiography (X-ACT)[EB/OL]

Study record dates

Study Major Dates

• Study Start (Actual): May 9, 2023
• Primary Completion (Actual): June 8, 2023
• Study Completion (Estimated): February 29, 2024

Study Registration Dates

• First Submitted: August 17, 2023
• First Submitted That Met QC Criteria: December 7, 2023
• First Posted (Estimated): December 15, 2023

Study Record Updates

• Last Update Posted (Estimated): December 15, 2023
• Last Update Submitted That Met QC Criteria: December 7, 2023
• Last Verified: August 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Cardiovascular Diseases; Vascular Diseases; Arteriosclerosis; Arterial Occlusive Diseases; Heart Diseases; Coronary Artery Disease; Myocardial Ischemia; Coronary Disease
• Other Study ID Numbers: CT-091-2022

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No