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.

Background: Completing internal medicine specialty training in Israel involves passing the Israel National Internal Medicine Exam (Shlav Aleph), a challenging multiple-choice test. multiple-choice test. Chat generative pre-trained transformer (ChatGPT) 3.5, a language model, is increasingly used for exam preparation.

Objectives: To assess the ability of ChatGPT 3.5 to pass the Israel National Internal Medicine Exam in Hebrew.

Methods: Using the 2023 Shlav Aleph exam questions, ChatGPT received prompts in Hebrew. Textual questions were analyzed after the appeal, comparing its answers to the official key.

Results: ChatGPT 3.5 correctly answered 36.6% of the 133 analyzed questions, with consistent performance across topics, except for challenges in nephrology and biostatistics.

Conclusions: While ChatGPT 3.5 has excelled in English medical exams, its performance in the Hebrew Shlav Aleph was suboptimal. Factors include limited training data in Hebrew, translation complexities, and unique language structures. Further investigation is essential for its effective adaptation to Hebrew medical exam preparation.

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 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.

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.

Medical imaging data has been at the frontier of artificial intelligence innovation in medicine with many clinical applications. There have been many challenges, including patient data protection, algorithm performance, radiology workflow, user interface, and IT integration, which have been addressed and mitigated over the last decade. The AI products in imaging now fall into three main categories: triage artificial intelligence (AI), productivity AI, and augmented AI, each providing a different utility for radiologists, clinicians, and patients. Adoption of AI products into the healthcare system has been slow, but it is growing. It is typically dictated by return on investment, which can be demonstrated in each use case. It is expected to lead to wider adoption of AI products in imaging into the clinical workflow in the future.

Background: The use of proprotein convertase subtilisin/kexin type 9 monoclonal antibodies (PCSK9 mAbs) is emerging for lowering low-density lipoprotein cholesterol (LDL-C). However, real-world data is lacking for their use among elderly patients.

Objective: To define the characteristics of elderly patients treated with PCSK9 mAbs and to evaluate the efficacy and tolerability compared with younger patients.

Methods: We conducted a retrospective cohort study of elderly patients (≥ 75 years at enrollment) treated with PCSK9 mAbs for primary and secondary cardiovascular prevention. Data were retrieved for demographic and clinical characteristics; indications for treatment; agents and dosages; concomitant lipid lowering treatment; LDL-C levels at baseline, 6, 12 months, and at the end of follow up. Data also included achieving LDL-C target levels and adverse effects.

Results: The cohort included 91 elderly patients and 92 younger patients, mean age 75.2 ± 3.76 and 58.9 ± 7.4 years (P < 0.0001). Most patients (82%, 80%) were in high/very high-risk categories. For almost all (98%, 99%), the indication was statin intolerance, with PCSK9 mAb monotherapy the most prevalent regimen. The average follow-up was 38.1 ± 20.5 and 30.9 ± 15.8 months (P = 0.0258). Within 6 months the LDL-C levels were reduced by 57% in the elderly group and by 59% in the control group (P = 0.2371). Only 53% and 57% reached their LDL-C target levels. No clinically significant side effects were documented.

Conclusion: PCSK9 mAbs have similar effects and are well tolerated among elderly patients as in younger patients.

To the reviewers of 2023, who gave of their time to constructively assess the articles sent to them.

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: There are conflicting data on the significance of hyperuricemia or hyperuricosuria in urolithiasis formation and on the need for medical treatment.

Objectives: To assess the significance of hyperuricemia or hyperuricosuria in urolithiasis formation, particularly when hyperuricemia occurs with normal uricosuria.

Methods: The electronic medical records of patients treated in Haifa and the Western Galilee district of Clalit Health Services, Israel, were retrospectively screened for diagnosis of nephrolithiasis or renal or urinary tract/bladder calculi between February 2014 and April 2019. The diagnosis was confirmed by ultrasonography or computed tomography. The study group included patients with one of these diagnoses. Patients in the control group did not have these diagnoses. The inclusion criterion for all patients was the presence of both serum and urinary uric acid levels.

Results: The study group included 359 patients and the control group 267. After adjustment by logistic regression, we found no significant differences in the prevalence of hyperuricosuria in the study group (14.8%) compared to the control group (9.7%), odds ratio (OR) 1.54 (95% confidence interval [95%CI] 0.74–3.2, P = 0.245). No significant differences between the groups were observed for hyperuricemia prevalence (45.4% vs. 55.1%, respectively, OR 0.82, 95%CI 0.54–1.25, P = 0.355), nor among those without hyperuricosuria (OR 0.83, 95%CI 0.52–1.33, P = 0.438) and after propensity score matching (OR 0.93, 95%CI 0.66–1.3, P = 0.655).

Conclusions: There were no significant differences in hyperuricemia or hyperuricosuria between the two groups of patients or in hyperuricemia among participants without hyperuricosuria.

Background: Pulmonary aspiration is a potentially lethal perioperative complication that can be precipitated by gastric insufflation. Face mask ventilation (FMV), a ubiquitous anesthetic procedure, can cause gastric insufflation. FMV with an inspiratory pressure of 15 cm H₂O provides the best balance between adequate pulmonary ventilation and a low probability of gastric insufflation. There is no data about the effects of FMV > 120 seconds.

Objectives: To investigate the effect of prolonged FMV on gastric insufflation.

Methods: We conducted a prospective observational study at a tertiary medical center with female patients who underwent oocyte retrieval surgery under general anesthesia FMV. Pre- and postoperative gastric ultrasound examinations measured the gastric antral cross-sectional area to detect gastric insufflation. Pressure-controlled FMV with an inspiratory pressure of 15 cm H₂O was continued from the anesthesia induction until the end of the surgery.

Results: The study comprised 49 patients. Baseline preoperative gastric ultrasound demonstrated optimal and good image quality. All supine measurements were feasible. The median duration of FMV was 13 minutes (interquartile range 9–18). In the postoperative period, gastric insufflation was detected in only 2 of 49 patients (4.1%). There was no association between the duration of FMV and delta gastric antral cross-sectional area (β -0.01; 95% confidence interval -0.04 to 0.01, P = 0.31).

Conclusions: Pressure-controlled FMV with an inspiratory pressure of 15 cm H₂O carries a low incidence of gastric insufflations, not only as a bridge to a definitive airway but as an alternative ventilation method for relatively short procedures in selective populations.

Background: Presentation of intoxicated patients to hospitals is frequent, varied, and increasing. Medical toxicology expertise could lead to important changes in diagnosis and treatment, especially in patients presenting with altered mental status.

Objectives: To describe and analyze clinical scenarios during a 1-year period after the establishment of a medical toxicology consultation service (MTCS).

Methods: Cases of 10 patients with altered mental status at presentation were evaluated. Medical toxicology consultation suggested major and significant changes in diagnosis and management.

Results: Of 973 toxicology consultations performed during the study period, bedside consultation was provided for 413 (42%) patients. Of these 413, 88 (21%) presented with some level of altered mental status. We described 10 patients in whom medical toxicology consultation brought about major and significant changes in diagnosis and management.

Conclusions: Benefits may be derived from medical toxicology consultations, especially in patients with altered mental status. Medical toxicology specialists are well positioned to provide high value and expedited patient care.