Israel Medical Association Journal

Background: The field of artificial intelligence (AI) is poised to significantly influence the future of medicine. With the accumulation of vast databases and recent advancements in computer science methods, AI's capabilities have been demonstrated in numerous areas, from diagnosis and morbidity prediction to patient treatment. Establishing an AI research and development unit within a medical center offers multiple advantages, particularly in fostering research and tapping into the immediate potential of AI at the patient's bedside.

Objectives: To outline the steps taken to establish a center for AI and big data within an innovation center at a tertiary hospital in Israel.

Methods: We conducted a retrospective analysis of projects developed in the field of AI at the Artificial Intelligence Center at the Rabin Medical Center, examining trends, clinical domains, and the predominant sectors over a specific period.

Results: Between 2019 and 2023, data from 49 AI projects were gathered. A substantial and consistent growth in the number of projects was observed. Following the inauguration of the Artificial Intelligence Center we observed an increase of over 150% in the volume of activity. Dominant sectors included cardiology, gastroenterology, and anesthesia. Most projects (79.6%) were spearheaded by physicians, with the remainder by other hospital sectors. Approximately 59.2% of the projects were applied research. The remainder were research-based or a mix of both.

Conclusions: Developing technological projects based on in-hospital medical data, in collaboration with clinicians, is promising. We anticipate the establishment of more centers dedicated to medical innovation, particularly involving AI.

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 MitraClip procedure is becoming an acceptable alternative for high-risk patients with mitral regurgitation (MR) due to functional (FMR) or degenerative (DMR) disease and suitable mitral anatomy.

Objectives: To evaluate the results of MitraClip at our institute in carefully selected patients.

Methods: We conducted a retrospective analysis of medical records and echocardiography data from January 2012 to December 2017.

Results: A total of 39 MitraClip procedures in 37 patients (aged 75 ± 12 years, 9 women) was performed. Twenty-four patients presented with FMR, 12 with DMR, and 1 with combined pathology. One-day post-procedure MR was moderate to low in 86.1% of patients, with immediate device success in 88.8%. MR at 1 year was moderate to low in 79% at 1 year. Survival at 1 year was 86% and at 2 years 69.4%. Peri-procedural (< 1 week) death and MitraClip failure occurred in one and three patients, respectively. New York Heart Association score improved to class 1 or 2 in 37% of patients at 1 year vs. one patient at baseline. Post-procedural systolic pulmonary pressure was reduced from 53 (range 48–65) to 43 (range 36–52) mmHg at 1 month with a subsequent plateau at follow-up, to 41 (34–57) mmHg at 6 months, and to 47 (38–50) at 12 months.

Conclusions: MitraClip in severe MR resulted in modest improvement in functional status and pulmonary pressure with a small risk of immediate procedural complications. Outcomes are encouraging considering the natural course of MR and the risks of surgical intervention.

Objectives: To assess the preliminary results of transcatheter mitral valve leaflet repair (TMLR) in a single academic center.

Methods: Data were collected prospectively in the cardiology department of Rabin Medical Center in 2012. Ten consecutive patients (age 69.3 ± 15.9 years, ejection fraction 36.5 ± 9.4) who were poor surgical candidates with severe functional MR underwent general anesthesia, followed by trans-septal puncture and a TMLR procedure using the MitraClip device.

Results: All 10 patients were considered to have severe functional MR prior to TMLR treatment and were all symptomatic; the mean New York Heart Association (NYHA) class was 3.4 ± 0.5. The MR severity was 4 ± 0. There were no immediate complications or failures of the procedure. One patient died on day 5 due to massive gastrointestinal bleeding. Immediately following TMLR all 10 patients showed a profound MR reduction to a mean severity grade of 1.6 ± 0.6. At one month after the procedure, NYHA had decreased to an average of 1.7 ± 1.0 and was at least grade 2 in all but one patient. After 6 months the MR remained ≤ 2 in six of eight patients, with a NYHA average of 1.4 ± 0.5.

Conclusions: The MitraClip procedure was shown to be relatively safe, providing significant clinical benefits to a relatively sick population with severe MR. It is therefore an important alternative to surgery in these high risk patients.

The features of infective endocarditis include both cardiac and non-cardiac manifestations. Neurologic complications are seen in up to 40% of patients with infective endocarditis and are the presenting symptom in a substantial percentage. We describe in detail the clinical scenarios of three patients admitted to our hospital, compare their characteristics and review the recent literature describing neurologic manifestations of infective endocarditis. Our patients demonstrate that infective endocarditis can develop without comorbidity or a valvular defect. Moreover, our patients were young and lacked the most common symptom of endocarditis: fever. The most common neurologic manifestations were focal neurologic deficits and confusion. We conclude that infective endocarditis should always be considered in patients presenting with new-onset neurologic complaints, especially in those without comorbidities or other risk factors. A prompt diagnosis should be reached and antibiotic treatment initiated as soon as possible.