Israel Medical Association Journal

In the grand theater of modern medicine, artificial intelligence (AI) has swiped the lead role, with a performance so riveting it deserves an Oscar, or at least a Nobel. From the intricate labyrinths of our arteries to the profound depths of our peepers, AI is the new maestro, conducting symphonies of data with the finesse of a seasoned virtuoso [1,2].

Artificial intelligence (AI) has emerged as a transformative group of technologies in the field of medicine. Specifically in cardiology, numerous applications have materialized, and these are developing exponentially. AI-based risk prediction models leverage machine learning algorithms and large datasets to probe multiple variables, aid in the identification of individuals at high risk for adverse events, facilitate early interventions, and enable personalized risk assessments. Unique algorithms analyze medical images, such as electrocardiograms, echocardiograms, and cardiac computed tomography scans to enable rapid detection of abnormalities and aid in the accurate identification of cardiac pathologies. AI has also shown promise in guiding treatment decisions during coronary catheterization. In addition, AI has revolutionized remote patient monitoring and disease management by means of wearable and implantable sensing technologies. In this review, we discussed the field of cardiovascular genetics and personalized medicine, where AI holds great promise. While the applications of AI in cardiology are promising, challenges such as data privacy, interpretability of the findings, and multiple matters regarding ethics need to be addressed. We presented a succinct overview of the applications of AI in cardiology, highlighting its potential to revolutionize risk prediction, diagnosis, treatment, and personalized patient care.

Background: The evaluation of syncope in emergency departments (EDs) and during hospitalization can be ineffective. The European Society of Cardiology (ESC) guidelines were established to perform the evaluation based on risk stratification.

Objectives: To investigate whether the initial screening of syncope adheres to the recent ESC guidelines.

Methods: Patients with syncope who were evaluated in our ED were included in the study and retrospectively classified based on whether they were treated according to ESC guidelines. Patients were divided into two groups according to the ESC guideline risk profile: high risk or low risk.

Results: The study included 114 patients (age 50.6 ± 21.9 years, 43% females); 74 (64.9%) had neurally mediated syncope, 11 (9.65%) had cardiac syncope, and 29 (25.45%) had an unknown cause. The low-risk group included 70 patients (61.4%), and the high-risk group included 44 (38.6%). Only 48 patients (42.1%) were evaluated according to the ESC guidelines. In fact, 22 (36.7%) of 60 hospitalizations and 41 (53.2%) of 77 head computed tomography (CT) scans were not mandatory according to guidelines. The rate of unnecessary CT scans (67.3% vs. 28.6%, respectively, P = 0.001) and unnecessary hospitalization (66.7% vs. 6.7%, respectively, P < 0.02) were higher among low-risk patients than high-risk patients. Overall, a higher percentage of high-risk patients were treated according to guidelines compared to low-risk patients (68.2% vs. 25.7% respectively, P < 0.0001).

Conclusions: Most syncope patients, particularly those with a low-risk profile, were not evaluated in accordance with the ESC guidelines.

Background: Sodium-glucose cotransporter-2 inhibitors (SGLT2i) and glucagon-like peptide-1 receptor agonists (GLP1-RA) are new antidiabetic drugs that are recommended by current guidelines as a class I novel glucose-lowering treatment that improves cardiovascular outcome in type 2 diabetes mellitus (T2DM), particularly in patients with cardiovascular disease.

Objectives: To evaluate adherence to the current guidelines for treatment with SGLT2i and GLP1-RA drugs in patients referred to ambulatory consultant cardiology clinics with pre-existing T2DM.

Methods: We studied consecutive new patients with a pre-existing diagnosis of T2DM who were referred to the Clalit Health Services ambulatory consultant cardiology clinic over a 6-month period. The recorded information included demographics, co-morbidities, and prescribed drugs at patient admission.

Results: During the study period, 1782 patients visited our outpatient cardiology clinic. At screening, T2DM was present in 428 patients (24%); 77 (18%) were being treated with SGLT2i, and 39 (9.1%) with GLP1-RA. Patients receiving SGLT2i and GLP1-RA were younger and had more coronary artery disease, lower mean left ventricular ejection fraction, and higher mean estimated glomerular filtration rates than those who were not receiving these drugs. HbA1C was > 7 in 205 (47.9%) patients and > 7.5 in 136 patients (31.8%). Body mass index was > 30 kg/m² in 231 (54%) patients.

Conclusions: GLP1-RA and SGLT2i drugs were found to be administered more frequently than previously reported, but they are not yet satisfactorily prescribed.

Advances in Lymphoma management have resulted in significant improvements in patient outcomes over the last 50 years. Despite these developments, cardiotoxicity from lymphoma treatments remains an important cause of mortality and morbidity in this cohort of patients. We outlined the most common cardiotoxicities associated with lymphoma treatments and their respective investigation and management strategies, including the role of cardiac pre-assessment and late effects monitoring.

Background: Syncope is a common reason for emergency department (ED) visits; however, the decision to admit or discharge patients after a syncopal episode remains challenging for emergency physicians. Decision rules such as the Boston Syncope Criteria have been developed in an attempt to aid clinicians in identifying high-risk patients as well as those who can be safely discharged, but applying these rules to different populations remains unclear.

Objectives: To determine whether the Boston Syncope Criteria are valid for emergency department patients in Israel.

Methods: This retrospective cohort convenience sample included patients who visited a tertiary care hospital in Jerusalem from August 2018 to July 2019 with a primary diagnosis of syncope. Thirty-day follow-up was performed using a national health system database. The Boston Syncope Criteria were retrospectively applied to each patient to determine whether they were at high risk for an adverse outcome or critical intervention, versus low risk and could be discharged.

Results: A total of 198 patients fulfilled the inclusion criteria and completed follow-up. Of these, 21 patients had either an adverse outcome or critical intervention. The rule detected 20/21 with a sensitivity of 95%, a specificity of 66%, and a negative predictive value of 99%.

Conclusions: The Boston Syncope Criteria may be useful for physicians in other locations throughout the world to discharge low-risk syncope patients as well as identify those at risk of complications

Background: A patient`s individual chance of being diagnosed with cardiovascular disease can be determined by risk scores.

Objectives: To determine the risk score profiles of patients presenting with a first acute coronary event according to pre-admission risk factors and to evaluate its association with long-term mortality.

Methods: The research was based on a retrospective study of a cohort from the 2010 and 2013 Acute Coronary Syndrome Israeli Surveys (ACSIS). Inclusion criteria included first event and no history of coronary heart disease or cardiovascular disease risk equivalent. The Framingham Risk Score, the European Systematic COronary Risk Evaluation (SCORE), and the American College of Cardiology/American Heart Association/ (ACC/AHA) risk calculator were computed for each patient. The risk profile of each patients was determined by the three scores. The prognostic value of each score for 5 year survival was evaluated.

Results: The study population comprised 1338 patients enrolled in the prospective ACSIS survey. The ACC/AHA score was the most accurate in identifying patients as high risk based on pre-admission risk factors (73% of the subjects). The Framingham algorithm identified 53%, whereas SCORE recognized only 4%. After multivariate adjustment for clinical factors at presentation, we found that no scores were independently associated with 5 year mortality following the first acute coronary event.

Conclusions: Patients with first acute coronary event had a higher pre-admission risk scores according to the ACC/AHA risk algorithm. No risk scores were independently associated with 5 year survival after an event.

Objectives: To investigate the 30 day clinical outcome of the first 300 consecutive patients treated with transfemoral TAVI at the Tel Aviv Medical Center.

Methods: The CoreValve was used in 250 patients and the Edwards-Sapien valve in 50 patients. The mean age of the patients was 83 ± 5.3 years (range 63–98 years) and the mean valve area 0.69 ± 0.18 cm² (range 0.3–0.9 cm²); 62% were women.

Results: The procedural success rate was 100%, and 30 day follow-up was done in all the patients. The average Euro-score for the cohort was 26 ± 13 (range 1.5–67). Total in-hospital mortality and 30 day mortality were both 2.3% (7 patients). Sixty-seven patients (22%) underwent permanent pacemaker implantation after the TAVI procedure, mostly due to new onset of left bundle brunch block and prolonged PR interval or to high degree atrioventricular block. The rate of stroke was 1.7% (5 patients). Forty-one patients (13.7%) had vascular complications, of whom 9 (3%) were defined as major vascular complications (according to the VARC definition).

Conclusions: The 30 day clinical outcome in the first 300 consecutive TAVI patients in our center was favorable, with a mortality rate of 2.3% and low rates of stroke (1.7%) and major vascular complications (3%).

Telemedicine is the application of advanced telecommunication technology for diagnostic, monitoring and therapeutic purposes. It enables data transmission from the patient's whereabouts or his/her primary care provider to a specialized medical call center. Telecardiology is a highly developed medical discipline involving almost every aspect of cardiology, including acute coronary syndromes, arrhythmias, congestive heart failure, sudden cardiac arrest and others. Israel is one of the leading countries in the use of telecardiology, achieving both extended survival, improvement of the patient's quality of life, and significant reduction in health costs. 

Background: Multi-detector computed tomography has advanced enormously and now enables non-invasive evaluation of coronary arteries as well as cardiac anatomy, function and perfusion. However, the role of cardiac MDCT[1] is not yet determined in the medical community and, consequently, many clinically unnecessary scans are performed solely on a self-referral basis.

Objectives: To prospectively evaluate the role of a cardiologist consultation and recommendation prior to the scan, and the influence on the diagnostic yield of cardiac MDCT.

Methods: In our center, a CT service was initiated, but with the prerequisite approval of a cardiologist before performance of the CT. Each individual who wanted and was willing to pay for a cardiac CT was interviewed by an experienced cardiologist who determined whether cardiac MDCT was the most appropriate next test in the cardiovascular evaluation. Subjects were classified into three groups: a) those with a normal or no prior stress test, no typical symptoms and no significant risk factors of coronary artery disease were recommended to perform a stress test or to remain under close clinical follow-up without MDCT; b) those with an equivocal stress test, atypical symptoms and/or significant risk factors were allowed to have cardiac MDCT; and c) those with positive stress test or clinically highly suspected CAD[2] were advised to go directly to invasive coronary angiography. CT findings were categorized as normal CAD (normal calcium score and no narrowings), < 50% and > 50% CAD.

Results: A total of 254 people were interviewed, and in only 39 cases did the cardiologist approve the CT. However, 61 of the 215, despite our recommendation not to undergo CT, decided to have the scan. Assessment of the 100 cases that underwent MDCT showed a statistically significant better discrimination of significant CAD, according to the cardiologist’s recommendation: MDCT not recommended in 3/54 (6%) vs. MDCT recommended in 12/39 (31%) vs. recommended invasive coronary angiography in 4/7 (57%) (P < 0.001).

Conclusions: Detection of coronary calcification, as well as MDCT angiography can provide clinically useful information if applied to suitable patient groups. It is foreseeable that MDCT angiography will become part of the routine workup in some subsets of patients with suspected CAD. Selection of patients undergoing MDCT scans by a cardiologist improves the ability of the test to stratify patients, preventing unnecessary scans in both high and low risk patients