Infiltrative Cardiomyopathy
Conditions
Brief summary
This study sought to develop an algorithm by collecting echocardiographic image information and related clinical information capable of quantitatively evaluating changes of the myocardium through machine learning. Moreover, the researchers investigate the usefulness of an algorithm for early diagnosis and differential diagnosis of infiltrative cardiomyopathy.
Detailed description
1. Study Design: Multicenter Retrospective Observational Study 2. Study method: If the above selection criteria are met, the index visit echocardiographic images which were performed immediately before or closest to the time of hospitalization for final diagnosis, echocardiographic images of the pre-visit and post-visit from the final diagnosis, and clinical information will be obtained. Chest X-ray, electrocardiogram, and echocardiography images are extracted in raw DICOM format and then analyzed in the core lab (Severance hospital). The characteristics of patients with infiltrative cardiomyopathy are identified through the collection of relevant clinical information, and a method for non-invasive early diagnosis and differential diagnosis of infiltrative cardiomyopathy is developed. 3. Quantative analysis of echocardiographic images using Radiomics * Radiomics is a method of extracting a large number of quantitative image features (300-500 features such as shape, entropy, volume, etc.) from non-invasive medical images (CT, MRI, etc.) and statistically analyzing the features. Its value has been demonstrated through the studies for prediction of breast cancer recurrence and lesion classification. * Using the open source platform PyRadiomics19, we extract the radiomic characteristics for brightness (Energy, Entropy, Mean, Median, etc.) and texture (Gray Level Co-occurrence Matrix Contrast, Difference Variance, Maximal Correlation Coefficient, etc.) from the set region of interest. * The differences between infiltrative cardiomyopathy and normal control are identified using clinical information and radiomics features extracted from echocardiography at the time of the diagnosis visit. The algorithms to distinguish the disease will be developed using machine learning methods such as support vector machine classifier.
Interventions
None listed
Sponsors
Yonsei University
Study design
Observational model
COHORT
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
Inclusion/
Exclusion criteria
1. Selection criteria for screening (1) 18 years old or older (2) Patients with infiltrative cardiomyopathy (the diagnostic name for each of the following diseases) or systemic disease (such as amyloidosis, multiple myeloma, sarcoidosis) (3) Search Period: January 1, 2010-December 31, 2020 2. Criteria for enrolling patients * Patients who are satisfied with at least one of each definition are selected. * Cardiac amyloidosis1,5,11,12 I. 'Definite': Positive myocardial biopsy (Congo-Red positive) II. 'Probable': One of the following imaging findings along with a positive biopsy of tissues other than myocardium A. Positive DPD / PYP scan Grade 2-3 cardiac uptake B. Echocardiography Symmetrical increase in LV and RV wall thickness Dilated LA and RA Granular appearance of myocardium Pericardial effusion Decreased or normal RQS complex voltage despite increased LV wall thickness C. Cardiac magnetic resonance imaging Diffuse subendocardial late Gd-enhancement Elevated native T1 and ECV value III. 'Possible': Two or more of the above imaging findings are satisfied without biopsy findings, and it is suitable for the diagnosis according to all clinical findings ② Cardiac sarcoidosis13,14,15,16 I. 'Definite': If all of the following are satisfied A. Noncaseating, multinucleated giant cell granuloma surrounded by bands of dense collagen fibers in endomyocardial biopsy B. Compatible clinical presentation C. Exclusion of other causes of granulomatous inflammation II. 'Probable': Two or more of the following findings along with a positive biopsy of tissues other than myocardium A. Electrocardiogram High-grade atrioventricular block (including complete atrioventricular block) or fatal ventricular arrhythmia (e.g., sustained ventricular tachycardia and ventricular fibrillation) B. Echocardiography Variable focal LV wall thinning (frequently at the basal septum, lateral wall) Focal wall motion abnormalities do not match coronary artery territory C. Cardiac magnetic resonance imaging Patch, basal and lateral LV wall late Gd-enhancement D. Positron Emission Tomography - Computed Tomography Focal increased FDG-uptake IV. 'Possible': Two or more of the above imaging findings are satisfied without biopsy findings, and it is suitable for the diagnosis according to all clinical findings * Hemochromatosis 17 I. 'Definite': Positive myocardial biopsy Iron deposits within the myocyte II. 'Probable': Non-myocardial tissue biopsy positive or iron overload clinical evidence (such as hereditary hemochromatosis, transfusion-dependent anemia) and the following imaging findings A. Echocardiography Dilated LV with global systolic dysfunction B. Cardiac magnetic resonance imaging Low T2\* value of myocardium Etc ① Fabry disease18,19 I. 'Definite': Positive myocardial biopsy Enlarged myocytes with clusters of concentric glycolipid (myelinoid bodies) within lysosomes II. 'Probable': A-galactosidase A screening test and X-linked genetic test positive, along with the following echocardiographic findings A. Echocardiography Symmetrical increase in LV and RV wall thickness ② Danon disease20 I. 'Definite': Positive for genetic testing or biopsy of myocardial tissue, along with the following echocardiographic findings Symmetrical increase in LV and/or RV wall thickness Decreased LV systolic function ③ Cardiac oxalosis1 I. 'Definite': Positive myocardial biopsy II. 'Probable': The following echocardiographic findings along with a history of massive transfusion or positive biopsy of tissues other than myocardium Symmetrical increase in LV and RV wall thickness Patchy, echodense speckled reflection
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Sensitivity | until June 30, 2022 | Sensitivity (True Positive Rate) refers to the proportion of those who have the infiltrative cardiomyopathy that received a positive result on the diagnostic algorythm by machine learning. |
| Specificity | until June 30, 2022 | Specificity refers to the proportion of those who do not have the infiltrative cardiomyopathy that received a negative result on the test. |
| Area under the curve of the receiver operation characteristics | until June 30, 2022 | — |
Countries
South Korea
Contacts
Primary ContactHyuk-jae Chang
Outcome results
None listed