Brugada Syndrome and Artificial Intelligence Applications to Diagnosis (BrAID)
Primary Purpose
Brugada Syndrome 1
Status
Unknown status
Phase
Not Applicable
Locations
Italy
Study Type
Interventional
Intervention
Patients affected by Brugada Syndrome 1
Sponsored by
About this trial
This is an interventional diagnostic trial for Brugada Syndrome 1
Eligibility Criteria
Inclusion Criteria:
- Brugada patients: patients with Brugada Syndrome 1 spontaneous or induced by the ajmaline test; patients with non-diagnostic electrocardiographic pattern for Brugada Syndrome 1 or negative in the presence of high clinical suspicion (family history for Brugada Syndrome, patients who survived cardiac arrest without organic heart disease)
- Control patients: patients with frequent premature ventricular complex and normal left and right ventricular function; patients with suspected Brugada Syndrome 1 not confirmed by ajmaline test
Exclusion Criteria:
- organic heart disease or diseases interfering with protocol completion
- lack of signed informed consent
- pregnancy
- acute coronary artery disease, heart failure in the previous 3 months
- severe renal or liver failure
Sites / Locations
- Azienda USL Toscana Sud Est - U.O.C Cardiologia
- Azienda Ospedaliera Universitaria Careggi - SOD Aritmologia
- Azienda Ospedaliero Universitaria Pisana - Cardiologia 2
- Fondazione Toscana Gabriele Monasterio
- Istituto di Fisiologia Clinica IFC-CNR
- Azienda Usl Toscana Nord Ovest - U.O.C. Cardiologia
Arms of the Study
Arm 1
Arm 2
Arm Type
Experimental
Active Comparator
Arm Label
Patients affected by Brugada Syndrome 1
Controls
Arm Description
Patients with spontaneous or drug-induced Brugada Syndrome 1
Patients with no condition associated with spontaneous or drug-induced Brugada Syndrome 1
Outcomes
Primary Outcome Measures
Machine Learning recognition of Brugada Syndrome 1
Identification of Brugada type 1 Syndrome coved ST component in a cohort of 44 patients (prospective study) and validated in a cohort of 100 patients (validation study) according to the diagnostic patterns related to Brugada Syndrome 1 on 12-leads ECG as already published on current international guidelines
Machine Learning recognition of Brugada Syndrome 1
Identification of Brugada type 1 Syndrome QRS fragmentation component in a cohort of 44 patients (prospective study) and validated in a cohort of 100 patients (validation study) according to the diagnostic patterns related to Brugada Syndrome 1 on 12-leads ECG as already published on current international guidelines
Machine Learning recognition of Brugada Syndrome 1
Identification and characterization of Brugada type 1 Syndrome T segment depression component in a cohort of 44 patients (prospective study) and validated in a cohort of 100 patients (validation study) according to the diagnostic patterns related to Brugada Syndrome 1 on 12-leads ECG as already published on current international guidelines
Machine Learning recognition of Brugada Syndrome 1
Identification of Brugada type 1 Syndrome broad P wave with PQ prolongation component in a cohort of 44 patients (prospective study) and validated in a cohort of 100 patients (validation study) according to the diagnostic patterns related to Brugada Syndrome 1 on 12-leads ECG as already published on current international guidelines
Secondary Outcome Measures
Biomarkers associated with Brugada Syndrome 1
Identification of biomarkers associated with Brugada Syndrome 1 by the means of blood transcriptomic profile and exosomes analysis of patients. Transcriptomic and exosome could provide new insight into the pathophysiology of signalling in this pathology, as well as for application in Brugada Syndrome 1 diagnosis and therapeutics.
Transcriptomic will provide a global picture of phenotypical changes associated with the disease, highlighting the potential genes involved in the development of Brugada Syndrome 1 The analysis of exosome coding and noncoding RNAs, participating in a variety of basic cellular functions, could also evidence potentially important pathophysiologic effects both in cardiac cells as well as on the release of electrical stimuli.
The study will be performed in a cohort of 44 patients (prospective study) and results will be validated in a cohort of 100 patients (validation study)
Stratification risk
Development of stratification risk system for Brugada type 1 Syndrome by the integration of ECG Machine Learning algorithms and biomarkers. In particular, the module will combine the peculiar ECG patterns associated with BrS (coved ST, QRS fragmentation, T segment depression, broad P wave with PQ prolongation)(outcome 1-4) and omic (genes) and exosome markers (coding and noncoding RNAs)(outcome 5) with the aim to improve patient risk stratification.
Specifically, gene expression modulation (expressed as % respect to control population) of Na+ (e.g., Nav1.5, Nav1.3, Nav2.1), Ca2+ (e.g. Cav3.1, HCN3) and K+ channels (e.g.,TWIK1, Kv4.3) will be evaluated.
The study will be performed in a cohort of 44 patients (prospective study) and results will be validated in a cohort of 100 patients (validation study).
Full Information
NCT ID
NCT04641585
First Posted
October 22, 2020
Last Updated
November 17, 2020
Sponsor
Istituto di Fisiologia Clinica CNR
Collaborators
Fondazione Toscana Gabriele Monasterio, Azienda USL Toscana Sud Est, Azienda USL Toscana Nord Ovest, Azienda Ospedaliero-Universitaria Careggi, Azienda Ospedaliero, Universitaria Pisana
1. Study Identification
Unique Protocol Identification Number
NCT04641585
Brief Title
Brugada Syndrome and Artificial Intelligence Applications to Diagnosis
Acronym
BrAID
Official Title
Brugada Syndrome and Artificial Intelligence Applications to Diagnosis
Study Type
Interventional
2. Study Status
Record Verification Date
November 2020
Overall Recruitment Status
Unknown status
Study Start Date
January 15, 2021 (Anticipated)
Primary Completion Date
March 15, 2023 (Anticipated)
Study Completion Date
September 15, 2023 (Anticipated)
3. Sponsor/Collaborators
Responsible Party, by Official Title
Sponsor
Name of the Sponsor
Istituto di Fisiologia Clinica CNR
Collaborators
Fondazione Toscana Gabriele Monasterio, Azienda USL Toscana Sud Est, Azienda USL Toscana Nord Ovest, Azienda Ospedaliero-Universitaria Careggi, Azienda Ospedaliero, Universitaria Pisana
4. Oversight
Studies a U.S. FDA-regulated Drug Product
No
Studies a U.S. FDA-regulated Device Product
No
5. Study Description
Brief Summary
Aim of the project is the development of an integrated platform, based on machine learning and omic techniques, able to support physicians in as much as possible accurate diagnosis of Type 1 Brugada Syndrome (BrS).
Detailed Description
The aim of BrAID project is to integrate classic clinical guidelines for Brugada Syndrome 1 diagnosis evaluation with innovative Information and Communication Technologies and omic approaches, generating new diagnostic strategies in cardiovascular precision medicine of this disease.
6. Conditions and Keywords
Primary Disease or Condition Being Studied in the Trial, or the Focus of the Study
Brugada Syndrome 1
7. Study Design
Primary Purpose
Diagnostic
Study Phase
Not Applicable
Interventional Study Model
Parallel Assignment
Masking
None (Open Label)
Allocation
Non-Randomized
Enrollment
144 (Anticipated)
8. Arms, Groups, and Interventions
Arm Title
Patients affected by Brugada Syndrome 1
Arm Type
Experimental
Arm Description
Patients with spontaneous or drug-induced Brugada Syndrome 1
Arm Title
Controls
Arm Type
Active Comparator
Arm Description
Patients with no condition associated with spontaneous or drug-induced Brugada Syndrome 1
Intervention Type
Diagnostic Test
Intervention Name(s)
Patients affected by Brugada Syndrome 1
Intervention Description
ECG analysis by Machine Learning algorithms and blood collection for the transcriptomic study of markers possibly associated with the disease
Primary Outcome Measure Information:
Title
Machine Learning recognition of Brugada Syndrome 1
Description
Identification of Brugada type 1 Syndrome coved ST component in a cohort of 44 patients (prospective study) and validated in a cohort of 100 patients (validation study) according to the diagnostic patterns related to Brugada Syndrome 1 on 12-leads ECG as already published on current international guidelines
Time Frame
Week 20
Title
Machine Learning recognition of Brugada Syndrome 1
Description
Identification of Brugada type 1 Syndrome QRS fragmentation component in a cohort of 44 patients (prospective study) and validated in a cohort of 100 patients (validation study) according to the diagnostic patterns related to Brugada Syndrome 1 on 12-leads ECG as already published on current international guidelines
Time Frame
Week 20
Title
Machine Learning recognition of Brugada Syndrome 1
Description
Identification and characterization of Brugada type 1 Syndrome T segment depression component in a cohort of 44 patients (prospective study) and validated in a cohort of 100 patients (validation study) according to the diagnostic patterns related to Brugada Syndrome 1 on 12-leads ECG as already published on current international guidelines
Time Frame
Week 20
Title
Machine Learning recognition of Brugada Syndrome 1
Description
Identification of Brugada type 1 Syndrome broad P wave with PQ prolongation component in a cohort of 44 patients (prospective study) and validated in a cohort of 100 patients (validation study) according to the diagnostic patterns related to Brugada Syndrome 1 on 12-leads ECG as already published on current international guidelines
Time Frame
Week 20
Secondary Outcome Measure Information:
Title
Biomarkers associated with Brugada Syndrome 1
Description
Identification of biomarkers associated with Brugada Syndrome 1 by the means of blood transcriptomic profile and exosomes analysis of patients. Transcriptomic and exosome could provide new insight into the pathophysiology of signalling in this pathology, as well as for application in Brugada Syndrome 1 diagnosis and therapeutics.
Transcriptomic will provide a global picture of phenotypical changes associated with the disease, highlighting the potential genes involved in the development of Brugada Syndrome 1 The analysis of exosome coding and noncoding RNAs, participating in a variety of basic cellular functions, could also evidence potentially important pathophysiologic effects both in cardiac cells as well as on the release of electrical stimuli.
The study will be performed in a cohort of 44 patients (prospective study) and results will be validated in a cohort of 100 patients (validation study)
Time Frame
week 48
Title
Stratification risk
Description
Development of stratification risk system for Brugada type 1 Syndrome by the integration of ECG Machine Learning algorithms and biomarkers. In particular, the module will combine the peculiar ECG patterns associated with BrS (coved ST, QRS fragmentation, T segment depression, broad P wave with PQ prolongation)(outcome 1-4) and omic (genes) and exosome markers (coding and noncoding RNAs)(outcome 5) with the aim to improve patient risk stratification.
Specifically, gene expression modulation (expressed as % respect to control population) of Na+ (e.g., Nav1.5, Nav1.3, Nav2.1), Ca2+ (e.g. Cav3.1, HCN3) and K+ channels (e.g.,TWIK1, Kv4.3) will be evaluated.
The study will be performed in a cohort of 44 patients (prospective study) and results will be validated in a cohort of 100 patients (validation study).
Time Frame
week 64
10. Eligibility
Sex
All
Minimum Age & Unit of Time
14 Years
Maximum Age & Unit of Time
65 Years
Accepts Healthy Volunteers
Accepts Healthy Volunteers
Eligibility Criteria
Inclusion Criteria:
Brugada patients: patients with Brugada Syndrome 1 spontaneous or induced by the ajmaline test; patients with non-diagnostic electrocardiographic pattern for Brugada Syndrome 1 or negative in the presence of high clinical suspicion (family history for Brugada Syndrome, patients who survived cardiac arrest without organic heart disease)
Control patients: patients with frequent premature ventricular complex and normal left and right ventricular function; patients with suspected Brugada Syndrome 1 not confirmed by ajmaline test
Exclusion Criteria:
organic heart disease or diseases interfering with protocol completion
lack of signed informed consent
pregnancy
acute coronary artery disease, heart failure in the previous 3 months
severe renal or liver failure
Central Contact Person:
First Name & Middle Initial & Last Name or Official Title & Degree
Giorgio Iervasi, Dr.
Phone
+390503153302
Email
segreteria.direzione@ifc.cnr.it
Overall Study Officials:
First Name & Middle Initial & Last Name & Degree
Federico Vozzi, Ph.D.
Organizational Affiliation
Istituto di Fisiologia Clinica
Official's Role
Principal Investigator
Facility Information:
Facility Name
Azienda USL Toscana Sud Est - U.O.C Cardiologia
City
Arezzo
State/Province
Tuscany
ZIP/Postal Code
52100
Country
Italy
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Pasquale Giovanni Notarstefano, Dr.
Phone
+3905752551
Email
pasqualenotarstefano@gmail.com
Facility Name
Azienda Ospedaliera Universitaria Careggi - SOD Aritmologia
City
Firenze
State/Province
Tuscany
ZIP/Postal Code
50134
Country
Italy
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Paolo Pieragnoli, Dr.
Phone
+390557946216
Email
paolopieragnoli@virgilio.it
Facility Name
Azienda Ospedaliero Universitaria Pisana - Cardiologia 2
City
Pisa
State/Province
Tuscany
ZIP/Postal Code
56100
Country
Italy
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Giulio Zucchelli, Dr.
Phone
+39050993043
Email
g.zucchelli@ao-pisa.toscana.it
Facility Name
Fondazione Toscana Gabriele Monasterio
City
Pisa
State/Province
Tuscany
ZIP/Postal Code
56124
Country
Italy
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Marcello Piacenti, Dr.
Phone
+390503153443
Email
marcello.piacenti@ftgm.it
Facility Name
Istituto di Fisiologia Clinica IFC-CNR
City
Pisa
State/Province
Tuscany
ZIP/Postal Code
56124
Country
Italy
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Federico Vozzi, Ph.D.
Phone
+390503152672
Email
vozzi@ifc.cnr.it
First Name & Middle Initial & Last Name & Degree
Maria-Aurora Morales, Dr.
Phone
+390503153228
Email
morales@ifc.cnr.it
Facility Name
Azienda Usl Toscana Nord Ovest - U.O.C. Cardiologia
City
Viareggio
State/Province
Tuscany
ZIP/Postal Code
55049
Country
Italy
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Gianluca Solarino, Dr.
Phone
+3905846051
Email
gianluca.solarino@uslnordovest.toscana.it
12. IPD Sharing Statement
Plan to Share IPD
No
Citations:
PubMed Identifier
1309182
Citation
Brugada P, Brugada J. Right bundle branch block, persistent ST segment elevation and sudden cardiac death: a distinct clinical and electrocardiographic syndrome. A multicenter report. J Am Coll Cardiol. 1992 Nov 15;20(6):1391-6. doi: 10.1016/0735-1097(92)90253-j.
Results Reference
background
PubMed Identifier
27977610
Citation
Quan XQ, Li S, Liu R, Zheng K, Wu XF, Tang Q. A meta-analytic review of prevalence for Brugada ECG patterns and the risk for death. Medicine (Baltimore). 2016 Dec;95(50):e5643. doi: 10.1097/MD.0000000000005643.
Results Reference
background
PubMed Identifier
29844648
Citation
Vutthikraivit W, Rattanawong P, Putthapiban P, Sukhumthammarat W, Vathesatogkit P, Ngarmukos T, Thakkinstian A. Worldwide Prevalence of Brugada Syndrome: A Systematic Review and Meta-Analysis. Acta Cardiol Sin. 2018 May;34(3):267-277. doi: 10.6515/ACS.201805_34(3).20180302B. Erratum In: Acta Cardiol Sin. 2019 Mar;35(2):192.
Results Reference
background
PubMed Identifier
15898165
Citation
Antzelevitch C, Brugada P, Borggrefe M, Brugada J, Brugada R, Corrado D, Gussak I, LeMarec H, Nademanee K, Perez Riera AR, Shimizu W, Schulze-Bahr E, Tan H, Wilde A. Brugada syndrome: report of the second consensus conference. Heart Rhythm. 2005 Apr;2(4):429-40. doi: 10.1016/j.hrthm.2005.01.005. Erratum In: Heart Rhythm. 2005 Aug;2(8):905.
Results Reference
background
PubMed Identifier
12448445
Citation
Wilde AA, Antzelevitch C, Borggrefe M, Brugada J, Brugada R, Brugada P, Corrado D, Hauer RN, Kass RS, Nademanee K, Priori SG, Towbin JA; Study Group on the Molecular Basis of Arrhythmias of the European Society of Cardiology. Proposed diagnostic criteria for the Brugada syndrome. Eur Heart J. 2002 Nov;23(21):1648-54. doi: 10.1053/euhj.2002.3382. No abstract available.
Results Reference
background
PubMed Identifier
25905440
Citation
Sarquella-Brugada G, Campuzano O, Arbelo E, Brugada J, Brugada R. Brugada syndrome: clinical and genetic findings. Genet Med. 2016 Jan;18(1):3-12. doi: 10.1038/gim.2015.35. Epub 2015 Apr 23.
Results Reference
background
PubMed Identifier
34645390
Citation
Morales MA, Piacenti M, Nesti M, Solarino G, Pieragnoli P, Zucchelli G, Del Ry S, Cabiati M, Vozzi F. The BrAID study protocol: integration of machine learning and transcriptomics for brugada syndrome recognition. BMC Cardiovasc Disord. 2021 Oct 13;21(1):494. doi: 10.1186/s12872-021-02280-3.
Results Reference
derived
Learn more about this trial
Brugada Syndrome and Artificial Intelligence Applications to Diagnosis
We'll reach out to this number within 24 hrs