Israel Medical Association Journal

Artificial intelligence (AI) has emerged as a powerful technology in medicine, with a potential to revolutionize various aspects of disease management. In recent years, substantial progress has been made in the development and implementation of AI algorithms and models for the diagnosis, screening, and monitoring of retinal diseases. We present a brief update on recent advancements in the implementation of AI in the field of retinal medicine, with a focus on age-related macular degeneration, diabetic retinopathy, and retinopathy of prematurity. AI algorithms have demonstrated remarkable capabilities in automating image analysis tasks, thus enabling accurate segmentation and classification of retinal pathologies. AI-based screening programs hold great promise in cost-effective identification of individuals at risk, thereby facilitating early intervention and prevention. Future integration of multimodal imaging data including optical coherence tomography with additional clinical parameters, will further enhance the diagnostic accuracy and support the development of personalized medicine, thus aiding in treatment selection and optimizing therapeutic outcomes. Further research and collaboration will drive the transformation of AI into an indispensable tool for improving patient outcomes and enhancing the field of retinal medicine.

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.

A rise in the incidence of chronic health conditions, notably heart failure, is expected due to demographic shifts. Such an increase places an onerous burden on healthcare infrastructures, with recurring hospital admissions and heightened mortality rates being prominent factors. Efficient chronic disease management hinges on regular ambulatory care and preemptive action. The application of intelligent computational models is showing promise as a key resource in the ongoing management of chronic diseases, particularly in forecasting disease trajectory and informing timely interventions. In this review, we explored a pioneering intelligent computational model by Diagnostic Robotics, an Israeli start-up company. This model uses data sourced from insurance claims to forecast the progression of heart failure. The goal of the model is to identify individuals at increased risk for heart failure, thus enabling interventions to be initiated early, mitigating the risk of disease worsening, and relieving the pressure on healthcare facilities, which will result in economic efficiencies.

Over the last decade the use of artificial intelligence (AI) has reformed academic research. While clinical diagnosis of psoriasis and psoriatic arthritis is largely straightforward, the determining factors of a clinical response to therapy, and specifically to biologic agents, have not yet been found. AI may meaningfully impact attempts to unravel the prognostic factors that affect response to therapy, assist experimental techniques being used to investigate immune cell populations, examine whether these populations are associated with treatment responses, and incorporate immunophenotype data in prediction models. The aim of this mini review was to present the current state of the AI-mediated attempts in the field. We executed a Medline search in October 2023. Selection and presentation of studies were conducted following the principles of a narrative–review design. We present data regarding the impact AI can have on the management of psoriatic disease by predicting responses utilizing clinical or biological parameters. We also reviewed the ways AI has been implemented to assist development of models that revolutionize the investigation of peripheral immune cell subsets that can be used as biomarkers of response to biologic treatment. Last, we discussed future perspectives and ethical considerations regarding the use of machine learning models in the management of immune-mediated diseases.

Large language models have revolutionized natural language processing. The emergence phenomenon is observed in these models and has the potential to revolutionize data processing and management. In this review, we discuss the concept of emergence in artificial intelligence, give detailed examples, and elaborate on the risks and limitations of large language models. The review exposes physicians to large language models, their advantages, and the inherent opportunities. We also describe the limitations and dangers, as these models are expected to impact medicine soon.

9 November 2023: Just one month after the tragic events of 7 October 2023, 240 individuals are still held hostage, ensnared by Hamas. Their medical plight is shrouded in silence. In the heart of Tel Aviv, a sea of health professionals gathers before the International Committee of the Red Cross (ICRC) offices pleading for decisive action. Among the medical pleas for help is the haunting image of a young soldier in dire need of his inhaler [Figure 1]. Ron needs it to live. I, a pediatric pulmonologist intimately familiar with respiratory distress, captured that moment.

A dramatic portrait bust of the physician Gabriele da Fonseca (1586? to 1668) at prayer is considered by art historians to be one of the finest late works of Gian Lorenzo Bernini (1598–1680), the preeminent sculptor of 17th century Rome. This statue is of medical as well as artistic interest. First, Fonseca is shown wearing his physician’s robe, thus celebrating his successful career as a leading medical figure in Rome, holding both Papal and university appointments at the highest level. In addition, the positioning of the statue in a special chapel designed by Bernini highlights Fonseca’s role as an influential participant in the introduction of quinine into Europe as a cure for malaria. Last, an examination of the statue’s hands identifies a number of pathologies and anatomical anomalies that raise interesting questions, regrettably unanswerable given the information presently available, concerning Fonseca’s illnesses and cause of death.

On 7 October 2023, a large-scale invasion by armed Hamas terrorists occurred in southern Israel. Approximately 1500 militants breached the Gaza security barrier using tractors, RPGs, and explosives. Concurrently, the terrorists utilized various means including armed vehicles, motorized paragliders, sea incursions, and a massive rocket attack launched toward Israel. On entering Israeli territory, the militants dispersed and targeted several towns, kibbutzim (collective communities), and Israel Defense Forces (IDF) military bases near Gaza. This strategy resulted in a death toll exceeded 1300 civilians and soldiers. In addition, more than 240 individuals were abducted. This attack occurred in one day. In this article, we introduce the Israeli National Institute of Forensic Medicine, which specialized in forensic analysis during mass casualty incidents, and pivotal role it played on 7 October. We present a detailed discussion on methods, challenges, and adaptations the institute took in response to the event of 7 October.

Background: In the past decade, numerous new imaging and laboratory tests have been implemented that significantly contribute to improved medical diagnostic capabilities. However, inappropriate utilization, which occurs on a large scale, has significant ramifications for both patient care and health systems.

Objectives: To assess the impact of a novel clinical decision support system (CDSS) applied to our electronic medical records on abdominal ultrasonography utilization pattern.

Methods: We conducted a retrospective cohort study comparing patterns of abdominal ultrasound utilization in cases of liver enzyme elevation, with and without CDSS, between February and May in 2017 (before CDSS implementation) and during the same months in 2018 (after CDSS implementation). The following parameters were collected: number of tests ordered according to the guidelines, tests with a diagnostic value, and order forms completed with any data or a diagnostic question. The comparison was conducted using chi-square test.

Results: Of 152 abdominal ultrasound tests, 72 were ordered in the pre-implementation period and 80 in the post-implementation period. The system failed to reach statistical significance regarding the rates of ordered tests according to the guidelines and/or tests with a diagnostic value. However, the use of the CDSS had a statistically significant impact regarding completing the order form with data, including a specific diagnostic question.

Conclusions: The effect of the system on the efficiency of test utilization was partial. However, our findings strongly suggested that CDSS has the potential to promote proper usage of complementary technologies.

Background: Unfractionated heparin is the preferred anticoagulant used during open heart surgeries, including left ventricular assist device (LVAD) implantation. In cases in which patients are heparin-induced thrombocytopenia positive (HIT+), the accepted practice has been to substitute heparin with bivalirudin. This practice may be associated with significant bleeding and adverse outcomes.

Objectives: To review our experience with HIT+ patients who were heparin-induced thrombocytopenia with thrombosis negative (HITT-) and who underwent HeartMate 3 LVAD implantation using heparin intraoperatively rather than bivalirudin.

Methods: From 2016 to 2022, 144 adult patients were implanted with HeartMate 3 LVAD at our center. Among them, 7 were detected as HIT+ but HITT- and therefore were prescribed intraoperatively with heparin and treated pre- and postoperatively with bivalirudin. We reviewed the preoperative, intraoperative, and postoperative characteristics as well as short-term mortality and the complication rates of these HIT+ patients.

Results: The median age of our cohort was 56 years (51–60), 71% were male (n=5), all were INTERMACS Level 1, and most were bridged to transplant (n=6, 86%). The 30-day mortality rate post-implantation was 0%. The average 24-hour chest drain postoperative output was 1502.86 ± 931.34 ml. There were no intraoperative pump thromboses, perioperative thromboses, cerebrovascular accidents, or gastrointestinal bleeding within the first 24 hours postoperative. One patient required a revision due to bleeding.

Conclusions: Intraoperative unfractionated heparin may be administered to patients who are HIT+ and HITT- while undergoing LVAD implantation. However, further investigation is required.

A 42-year-old healthy man collapsed suddenly in the street while walking. The patient received 2 minutes of basic life support until an automatic external defibrillator was brought and detected ventricular fibrillation (VF), which was successfully terminated by a single shock. The patient regained consciousness and was transferred to the hospital.

The patient’s physical examination was normal with no neurologic deficit. Blood pressure was 147/102 mmHg. Brain computed tomography showed normal findings. The first troponin I measurement within 1 hour of the event was in the normal range (19.6 ng/L, normal < 20 ng/L) and rose to 99.9 ng/L after 3 hours.

Background: At the beginning of 2020, the coronavirus disease 2019 (COVID-19) pandemic presented a new burden on healthcare systems.

Objectives: To evaluate the impact of the COVID-19 pandemic on the outcome of non-COVID patients in Israel.

Methods: We conducted a retrospective observational cohort study at a tertiary medical center in Israel. From December 2018 until June 2022, 6796 patients were hospitalized in the internal medicine wards. Patients were grouped based on their admission date: admitted during COVID waves (waves group), admitted between waves (interim group), and admitted during the same months in the previous year (former-year group).

Results: Mortality during hospitalization and 30-day mortality were higher in the waves group compared to the interim and former-year groups (41.4% vs. 30.5% and 24%, 19.4% vs. 17.9% and 12.9%, P < 0.001). In addition, 1-year mortality was higher in the interim group than in the waves and former-year group (39.1 % vs. 32.5% and 33.4%, P = 0.002). There were significant differences in the readmissions, both at 1 year and total number. The waves group had higher rates of mechanical ventilation and noradrenaline administration during hospitalization. Moreover, the waves group exhibited higher troponin levels, lower hemoglobin levels, and more abnormalities in liver and kidney function.

Conclusions: Hospitalized non-COVID patients experienced worse outcomes during the peaks of the pandemic compared to the nadirs and the preceding year, perhaps due to the limited availability of resources. These results underscore the importance of preparing for large-scale threats and implementing effective resource allocation policies.

Background: The French AmbUlatory Cesarean Section (FAUCS) technique was introduced to the Galilee Medical Center in September 2021. FAUCS was performed electively for interested women who meet the criteria.

Objectives: To evaluate the learning curve of senior surgeons performing FAUCS, the procedure short-term outcomes, and complications.

Methods: This retrospective study included 50 consecutive women who underwent FAUCS from September 2021 until March 2022 at our facility. Preoperative, intraoperative, postoperative, and demographic data were retrieved from patient electronic charts.

Results: The mean duration of surgery was 53.26 ± 11.62 minutes. This time decreased as the surgical team's experience increased: from a mean 58.26 ± 12.25 minutes for the first 15 procedures to a mean 51.17 ± 9.73 minutes for subsequent procedures. The mean visual analogue scale score for 24 hours was 1.08 ± 0.84 (on a 10-point scale). The rate of neonatal cord pH < 7.2 was 6%, and there were 11.3% cases of vacuum assisted fetal extraction. In total, 44% of the women were able to mobilize and urinate spontaneously by 4–6 hours. Complications included bladder injury (n=1), endometritis (n=1), and incisional hematoma (n=1). Overall, the maternal satisfaction rate was high; 94% of the women would recommend FAUCS to others.

Conclusions: FAUCS is a feasible procedure with a high satisfaction rate. Following the first 15 procedures performed by one surgical team, the operative time decreased considerably. Further randomized controlled studies are needed to compare this procedure to regular cesarean section and evaluate neonatal outcomes.

Background: The administration of antenatal corticosteroids (ACS) is standard practice for management of threatened preterm birth. Its benefit, especially in small for gestational age (SGA) late preterm, is unclear.

Objectives: To evaluate the impact of ACS on perinatal outcome of late preterm SGA neonates.

Methods: We conducted a retrospective cohort study of all women carrying a singleton gestation who had late preterm delivery (34–36 gestational weeks) of SGA neonates at a single tertiary university-affiliated medical center (July 2012–December 2017). Exclusion criteria included termination of pregnancy, intrauterine fetal death, and birth weight ≥ 10th percentile. Outcomes were compared between ACS and non-ACS treatment prior to delivery. Neonatal composite outcome included neonatal intensive care unit (NICU) admission, respiratory distress syndrome, mechanical ventilation, and transient tachypnea.

Results: Overall, 228 women met inclusion criteria; 102 (44.7%) received ACS and 126 did not (55.3%). Median birth weight among the non-ACS group was significantly higher (1896.0 vs. 1755.5 grams P < 0.001). Rates of NICU and jaundice requiring phototherapy were higher among the ACS group (53.92% vs. 31.74%, P = 0.01; 12.74% vs. 5.55%, P = 0.05, respectively). Composite neonatal outcome was significantly higher among the ACS group (53.92% vs. 32.53%, odds ratio [OR] 2.42, 95% confidence interval [95%CI] 1.41–4.15, P = 0.01). After adjustment for potential confounders, this association remained significant (OR 2.15, 95%CI 1.23–3.78, P = 0.007).

Conclusions: ACS given during pregnancy did not improve respiratory outcome for SGA late preterm neonates. ACS may be associated with a worse outcome.

Background: Websites serve as a source of medical information for a large part of the public, some claim to be a substitute for a physician’s consultation. Many patients meet a physician after conducting internet research. Medical staff are concerned that internet sources of information are unreliable and may lead to erroneous decisions by patients.

Objectives: To examine the reliability of web-based sources of information (through the Google™ search engine) regarding five common orthopedic complaints and injuries.

Method: We performed a search of five common orthopedic complaints and injuries using the Google search engine. The reliability of web-based information was measured by the DISCERN tool, which is a valid and verified tool for examining the reliability of medical information sources to the public. The reliability of 47 websites was examined by two orthopedic surgeons and two senior residents.

Results: The overall average score given to the sites was 2.8, on a scale of 1 to 5. We found that the higher the site appeared in the search results, the higher the quality of its information. Commercial sites scored higher than general internet information sources.

Conclusions: The internet network is a very broad source of information. For those who lack scientific education and training it is not easy to distinguish between reliable and unreliable or biased sources. The trend of searching for medical information and self-healing is increasing. We must strengthen the network with reliable sources by creating official scientific position papers by medical teams and promoting them online.