Israel Medical Association Journal

Background: Advancements in artificial intelligence (AI) and natural language processing (NLP) have led to the development of language models such as ChatGPT. These models have the potential to transform healthcare and medical research. However, understanding their applications and limitations is essential.

Objectives: To present a view of ChatGPT research and to critically assess ChatGPT's role in medical writing and clinical environments.

Methods: We performed a literature review via the PubMed search engine from 20 November 2022, to 23 April 2023. The search terms included ChatGPT, OpenAI, and large language models. We included studies that focused on ChatGPT, explored its use or implications in medicine, and were original research articles. The selected studies were analyzed considering study design, NLP tasks, main findings, and limitations.

Results: Our study included 27 articles that examined ChatGPT's performance in various tasks and medical fields. These studies covered knowledge assessment, writing, and analysis tasks. While ChatGPT was found to be useful in tasks such as generating research ideas, aiding clinical reasoning, and streamlining workflows, limitations were also identified. These limitations included inaccuracies, inconsistencies, fictitious information, and limited knowledge, highlighting the need for further improvements.

Conclusions: The review underscores ChatGPT's potential in various medical applications. Yet, it also points to limitations that require careful human oversight and responsible use to improve patient care, education, and decision-making.

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 in ophthalmology is used for automatic diagnosis, data analysis, and predicting responses to possible treatments. The potential challenges in the application and assimilation of artificial intelligence include technical challenges of the algorithms, the ability to explain the algorithm, and the ability to diagnose and manage the medical course of patients. Despite these challenges, artificial intelligence is expected to revolutionize the way ophthalmology will be practiced. In this review, we compiled recent reports on the use and application of deep learning in various fields of ophthalmology, potential challenges in clinical deployment, and future directions.

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.

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.

Background: The coronavirus disease 2019 (COVID-19) pandemic caused significant global turmoil, including changes in social and societal conduct such as lockdowns, social isolation, and extensive regulations. These changes can be major sources of stress. The first wave of the pandemic (April–May 2020) was a time of global uncertainty. We evaluated symptom severity among 29 Israeli children and adolescents with obsessive-compulsive disorder (OCD). Our previous study found that most of these participants did not experience an exacerbation of symptoms.

Objective: To re-evaluate the OCD symptoms of 18 participants from the original group of 29 children and adolescents during three time points: before the pandemic, during the first wave, and 2 years later.

Methods: Obsessive-compulsive symptoms (OCS) were assessed using the Clinical Global Impression Scale (CGI), a functional questionnaire, and the Obsessive-Compulsive Inventory-child version (OCI-CV).

Results: OCS in patients did not change significantly during the three time points. Participants reported minimal changes in their general functioning 2 years after the outbreak of COVID-19 and showed minimal change in OCI-CV scale scores.

Conclusions: Our results indicated clinical stability of OCD symptoms among most of the participants.

Background: Pregnant women are at higher risk for severe coronavirus disease 2019 (COVID-19). Since the release of the BNT162b2 messenger RNA vaccine (Pfizer/BioNTech), there has been accumulated data about the three vaccine doses. However, information regarding obstetric and neonatal outcomes of pregnant women vaccinated with the third (booster) vaccine is limited and primarily retrospective.

Objectives: To evaluate the obstetric and early neonatal outcomes of pregnant women vaccinated during pregnancy with the COVID-19 booster vaccine compared to pregnant women vaccinated only by the first two doses.

Methods: We conducted a cross-sectional study of pregnant women who received the BNT162b2 vaccine during pregnancy. Obstetric and neonatal outcomes were compared between pregnant women who received only the first two doses of the vaccine to those who also received the booster dose.

Results: Overall, 139 pregnant women were vaccinated during pregnancy with the first two doses of the vaccine and 84 with the third dose. The third dose group received the vaccine earlier during their pregnancy compared to the two doses group (21² vs. 31⁵ weeks, respectively, P < 0.001). No differences in obstetric and early neonatal outcomes between the groups were found except for lower rates of urgent cesarean delivery in the third dose group (adjusted odds ratio 0.21; 95% confidence interval 0.048–0.926, P = 0.039).

Conclusions: Compared to the first two doses of the BNT162b2 vaccine given in pregnancy, the booster vaccination is safe and not associated with an increased rate of adverse obstetric and early neonatal outcomes.

Background: The Gaza–Israeli conflict poses challenges for unbiased reporting due to its complexity and media bias. We explored recent scientific publications to understand scholarly discourse and potential biases surrounding this longstanding geopolitical issue.

Objectives: To conduct a descriptive bibliometric analysis of PubMed articles regarding the recent Gaza–Israeli conflict.

Methods: We reviewed 1628 publications using keywords and medical subject headings (MeSH) terms related to Gaza, Hamas, and Israel. We focused on articles written in English. A team of researchers assessed inclusion criteria, resolving disagreements through a third researcher.

Results: Among 37 publications, Lancet, BMJ, and Nature were prominent journals. Authors from 12 countries contributed, with variety of publication types (46% correspondence, 32% news). Pro-Gaza perspectives dominated (43.2%), surpassing pro-Israel (21.6%) and neutral (35.1%) viewpoints. Pro-Gaza articles exhibited higher Altmetric scores, indicating increased social media impact. Pro-Israel publications were predominantly authored by Israelis.

Conclusions: The prevalence of pro-Gaza perspectives underscores challenges in maintaining impartiality. Higher social media impact for pro-Gaza publications emphasizes the need for nuanced examination. Addressing bias is crucial for a comprehensive understanding of this complex conflict and promoting balanced reporting.

Background: Ventricular assist devices (VADs) play a critical and increasing role in treating end-stage heart failure in pediatric patients. A growing number of patients are supported by VADs as a bridge to heart transplantation. Experience with VADs in the pediatric population is limited, and experience in Israel has not been published.

Objectives: To describe this life-saving technology and our experience with VAD implantation in children with heart failure, including characteristics and outcomes.

Methods: We conducted a retrospective chart review of all patients who underwent VAD implantation at Schneider Children's Medical Center from 2018 to 2023.

Results: We analyzed results of 15 children who underwent VAD implantation. The youngest was 2.5 years old and weighed 11 kg at implantation. In eight patients, HeartMate 3, a continuous-flow device, was implanted. Seven patients received Berlin Heart, a pulsatile-flow device. Three children required biventricular support; 11 underwent heart transplants after a median duration of 169 days. Two patients died due to complications while awaiting a transplant; two were still on VAD support at the time of submission of this article. Successful VAD support was achieved in 86.6% of patients. In the last 5 years,79%  of our heart transplant patients received VAD support prior to transplant.

Conclusions: Circulatory assist devices are an excellent bridge to transplantation for pediatric patients reaching end-stage heart failure. VADs should be carefully selected, and implantation techniques tailored to patient's weight and diagnosis at a centralized pediatric cardiac transplantation center. Israeli healthcare providers should be cognizant of this therapeutic alternative.

On Saturday, 7 October 2023, the Jewish holiday of Simchat Torah, our entire country woke to a reality of the worst terror attacks it has ever known, despite its long history of wars and terror. These horrific attacks included killing and burning babies, children, women, men, and the elderly; raping women; beheading babies; destroying settlements; and kidnapping more than 240 civilians and soldiers. The severe traumatic events created different circles of those exposed to trauma. In each group, the intensity of the trauma was different and had different characteristics.

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.

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.