Heart failure affects 1-2% of the adult population in developed countries, increasing to ≥10% in people aged 70 and over. There are numerous underlying causes of heart failure, including vascular heart disease, high output states and disease of the heart muscle (myocardial disease).
Our research team includes medical doctors, electrical and computer engineering professors, and researchers focused on developing technologies to aid in medical diagnosis. The collaboration between multi-disciplinary team-mates from the cardiology department of the American University of Beirut Medical Center (AUBMC), the electrical and computer engineering department at the American University of Beirut (AUB), and researchers from BRIC aims to improve the machine learning outcome for the diagnosis of cardiovascular diseases.
Our group has been working extensively over the last period to develop machine learning based models that incorporate clinical history, electrocardiography (ECG) and echocardiography features to differentiate ischemic from non-ischemic heart failure.
We test different classification algorithms to investigate the value of cardiac strain parameters in predicting the type of myocardial disease; and the value of strain data with or without ECG data to predict type of myocardial disease. If the strain data and other features are used to predict the type of myocardial disease (e.g. ischemic or non-ischemic) using a classification algorithm, this would lead to more rapid elucidation of specific underlying diagnosis by guiding subsequent investigations, e.g. angiography or genetic testing. This would mean:
1- fewer investigations, which would be beneficial for the patient’s well-being and the efficient use of hospital resources and funds
2- a faster diagnosis, meaning appropriate management can be commenced sooner. Furthermore, if the used classification models along with the input data predict outcome and/or specific diagnosis more accurately than previous works, a relevant tool could be developed in which strain and other relevant data could be input to predict diagnosis, guiding investigation and management, thus, improving treatment for patients and their families.
Dr. Mohammed Baydoun
Head of Medical Research Program
Dr. Mohammed Husseini
Prof. Hassan Ghaziri
Dr. Lise Safatly
Prof. Hussein Ismaeel
American University of Beirut Medical Center
Prof. Ali El- Hajj
American University of Beirut
BriefHeart failure affects 1-2% of the adult population in developed countries, increasing to ≥10% in people aged 70 and over.
Our research team includes medical doctors, electrical and computer engineering professors, and researchers focused on developing technologies to aid in medical diagnosis.
We have been working extensively to develop machine learning based models that incorporate clinical history, electrocardiography (ECG) and echocardiography features to aid in the medical diagnosis and prognosis for heart related diseases especially Ischemia and Congestive Heart Failure.
ECG DigitizationECG or EKG is considered as the most practiced method for the diagnosis of heart abnormalities.
To benefit from the printed ECGs of old cohorts of rare diseases, we transform the ECG signal, either scanned or printed, to the raw digital (time, mV) form.
ECG digitization Video
Ischemia PredictionMachine learning allows for improved accuracy in predicting the need for coronary angiography for the diagnosis of ischemic cardiomyopathy.
A cohort of 204 consecutive patients with reduced ejection fraction (EF<50% on echocardiography) with clinical, ECG and echocardiography (including speckle tracking) variables.
We tested several classification algorithms and determined the most relevant variables. These included regional wall motion, the right bundle branch block, in addition to the post-systolic shortening and its deceleration time.
The incorporation of these tools in electronic systems as well as others will facilitate patient care.
Developed a web-based application to predict ischemia, available at:
Retinal Video Analysis for NeurocamWinner of the First Place Position in Stars of Science Season 10 – (Neurocam Dr. Walid Albanna)
Neurocam is a novel portable device to monitor and analyze retinal vessels with the objective to provide early detection of the brain stroke for patients in emergency care units suffering hemorrhage.
Comprehensive Image/Video Processing Software with several capabilities to achieve an automated retinal vessel analysis.
Software provides auto-brightness and auto-focus abilities with a semi-automated positioning system.
Software automatically detects the regions of interest which are part of the main retinal vessels.
Software performs a measurement of the vessels dilation/contraction over a 6 minutes period which helps the medical examiner asses the possible early stroke and provides a decision to help the examiner.
BRIC provided mentoring and technical support (video and image processing) for Neurocam
SmartEx exhibitionThis year, BRIC participated in the SmartEx exhibition that was held from April 25-28, 2018, at the Forum De Beyrouth. As an exhibitor this year, BRIC showcased its latest work in technological innovation, as well as social development.
Available at: https://www.sciencedirect.com/science/article/pii/S1746809420301750
Highest Accuracy in PCG classification: https://archive.physionet.org/users/shared/challenge/2016/top-results.shtml
 Ahmad, Ali, Shareef Mansour, Ali Zgheib, Lise Safatly, Ali El Hajj, Mohammed Baydoun, Hassan Ghaziri, Hussam Aridi, and Hussain Ismaeel. "Using Artificial Intelligence to Uncover Association of Left Atrial Strain with the Framingham Risk Score for Atrial Fibrillation Development." Journal of the American College of Cardiology 75, no. 11S1 (2020): 455-455.
Available at: https://www.jacc.org/doi/full/10.1016/S0735-1097%2820%2931082-2
 Mohammed Baydoun, Lise Safatly, Ossama K. Abou Hassan, Hassan Ghaziri, Ali El Hajj, and Hussain Isma’eel. "High Precision Digitization of Paper-Based ECG Records: A Step Toward Machine Learning." IEEE Journal of Translational Engineering in Health and Medicine 7 (2019): 1-8.
Available at: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8894038