AI-based Echocardiography for Detection of Cardiac Amyloidosis
brief summary
Cardiac amyloidosis is characterized by deposition of misfolded protein in the myocardium causing mainly heart failure symptoms with preserved left ventricular ejection fraction. There are also specific clinical (bilateral carpal tunnel syndrome, polyneuropathy, skin bruising, ruptured biceps tendon…), biomarkers (disproportionally elevated NT-proBNP to the degree of heart failure, persistent elevated troponin, proteinuria..), electrocardiographic (reduced voltage of QRS, atrial fibrillation..) and echocardiographic features (concentric left ventricular hypertrophy, dilated atria, reduced global longitudinal strain with typical pattern of apical sparing, diastolic dysfunction…). Early diagnosis of the disease is crucial to identify patients that may benefit from appropriate treatment. Suspected cardiac amyloidosis on echocardiography or on cardiac magnetic resonance needs to prompt the request of serum free-light chain quantification and serum and urine immunofixation as well as single photon emission computed tomography (SPECT) using bone radiotracers. Echocardiography is the imaging technique of first choice to evaluate patients with dyspnea complaints and suspected heart failure as well as other pathologies. Echocardiography is a technique of first choice to evaluate patients with cardiovascular risk factors such as arterial hypertension and diabetes and many of those patients may have echocardiographic features that can be observed in early phases of cardiac amyloidosis. Currently, identification of patients with cardiac amyloidosis with available echocardiographic tools remains challenging. However, novel artificial intelligence (AI)-based algorithms applied to echocardiographic images for analysis may help the cardiologists in the identification of early phase of cardiac amyloidosis. Early diagnosis of cardiac amyloidosis is key to implement effective therapies that have demonstrated to improve survival. Several studies have demonstrated the accuracy of AI-based algorithms applied to echocardiography for the diagnosis of cardiac amyloidosis. The hypothesis of the present prospective study is to evaluate the accuracy of the AI-based algorithm to identify patients with echocardiographic findings suggestive of cardiac ATTR amyloidosis using as ground truth the subsequent analysis with imaging techniques that permit its diagnosis such as 99mTc-pyrophosphate (PYP) SPECT and cardiac magnetic resonance as well as hematologic tests. If needed, histological confirmation on cardiac or extracardiac tissue could be performed, as recommended by recent consensus document from the Heart Failure Association of the European Society of Cardiology. In addition, this study will help to answer the true prevalence of ATTR cardiac amyloidosis among patients referred to transthoracic echocardiography that present red flags for ATTR cardiac amyloidosis. The AI-based algorithm is the software Us2.ai which has been used in other populations for this purpose, as previously published.
detailed description
Background: Cardiac amyloidosis is characterized by deposition of misfolded protein in the myocardium causing mainly heart failure symptoms with preserved left ventricular ejection fraction. There are also specific clinical (bilateral carpal tunnel syndrome, polyneuropathy, skin bruising, ruptured biceps tendon…), biomarkers (disproportionally elevated NT-proBNP to the degree of heart failure, persistent elevated troponin, proteinuria..), electrocardiographic (reduced voltage of QRS, atrial fibrillation..) and echocardiographic features (concentric left ventricular hypertrophy, dilated atria, reduced global longitudinal strain with typical pattern of apical sparing, diastolic dysfunction…). Early diagnosis of the disease is crucial to identify patients that may benefit from appropriate treatment. Suspected cardiac amyloidosis on echocardiography or on cardiac magnetic resonance needs to prompt the request of serum free-light chain quantification and serum and urine immunofixation as well as single photon emission computed tomography using bone radiotracers.
Hypothesis: The use of artificial intelligence assisted algorithm applied to echocardiographic data may allow identification of suspected cardiac amyloidosis more precisely as compared to cardiologists with expertise in cardiac imaging.
Methods: This project proposal will comprised 3 different phases:
Phase 1: retrospective evaluation of clinically acquired echocardiographic data with reports indicating left ventricular hypertrophy (LV wall thickness ≥12 mm) and/or cardiac amyloidosis. This evaluation will consist of retrieval and analysis of echocardiographic data (around 20K studies) from 2022 to date. The data will be reanalysed by an experienced observer and a currently available artificial intelligence (AI)-based algorithm to detect suspected cardiac amyloidosis. The agreement between the algorithm and the observer will be tested. In those patients in whom the initial observer who reported the echocardiogram considered that there was suspicion of cardiac amyloidosis, the reports of additional test clinically required to confirm or rule out the diagnosis will be retrieved. Accordingly, the accuracy of the observer and the AI-based algorithm will be compared.
Phase 2. Based on the results of Phase 1, which will informed about the prevalence of the condition, we will determine the duration of the prospective assessment of AI-based algorithm assisted echocardiographic image analysis to see if this would augment the capacity of cardiologists to pick up early patients suspected to have cardiac amyloidosis.
official title
AI-based Echocardiography for Detection of Cardiac Amyloidosis in Patients Undergoing Transthoracic Echocardiography With Left Ventricular Hypertrophy