Israel Medical Association Journal

Artificial Intelligence (AI), particularly large language models (LLMs) like OpenAI's ChatGPT, has shown potential in various medical fields, including pediatrics. We evaluated the utility and integration of LLMs in pediatric medicine. We conducted a search in PubMed using specific keywords related to LLMs and pediatric care. Studies were included if they assessed LLMs in pediatric settings, were published in English, peer-reviewed, and reported measurable outcomes. Sixteen studies spanning pediatric sub-specialties such as ophthalmology, cardiology, otology, and emergency medicine were analyzed. The findings indicate that LLMs provide valuable diagnostic support and information management. However, their performance varied, with limitations in complex clinical scenarios and decision-making. Despite excelling in tasks requiring data summarization and basic information delivery, the effectiveness of the models in nuanced clinical decision-making was restricted. LLMs, including ChatGPT, show promise in enhancing pediatric medical care but exhibit inconsistent performance in complex clinical situations. This finding underscores the importance of continuous human oversight. Future integration of LLMs into clinical practice should be approached with caution to ensure they supplement, rather than supplant, expert medical judgment.

Background: On 7 October 2023, an armed conflict erupted between Hamas and Israel, leading to numerous combat casualties.

Objectives: To describe computed tomography (CT) findings of combat casualties at a tertiary medical center during the first 3 months of the conflict.

Methods: A retrospective observational study was conducted on patients admitted between 7 October 2023 and 7 January 2024. Adults with conflict-related trauma who underwent chest, abdomen, and pelvis (body) trauma protocol CT scans were included.

Results: Of 272 patients who underwent body trauma protocol CT, 112 combat-related adults were included, mean age of 27 years and one female. In total, 82 patients (73%) underwent additional scans of the head and neck or extremities. Fractures were observed in 53 patients (47%). Vascular injuries were present in 40 patients (35%). Limb injuries were most common, affecting 37 patients (33%), which prompted a protocol update. Lung injuries were the most common in body CT: 30 patients (27%). Head and neck injuries were seen in 21 patients (18%). Multisystem trauma was present in 24 patients (21%). A total of 83 patients (74%) underwent surgery, mostly orthopedic/soft tissue surgeries (63%); 15 (13%) underwent abdominal surgery, with bowel injuries confirmed in eight cases.

Conclusions: CT scans are an important tool in conflict trauma management. Limb injuries were the most frequent, necessitating protocol adjustments. Lung injuries were the most common body injury; 21% of patients had multisystem trauma. Most patients required surgery.

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.

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.

In this study, we analyzed computed tomography (CT) radiological findings from trauma treated at a single hospital in the aftermath of the terror attack in Israel on 7 October 2023. The study includes images from 34 consecutive patients, consisting of 33 males and 1 female, ranging in age from 19 to 68 years. The majority of these patients underwent both chest-abdominal-pelvic (76%) and head and neck CT scans (64.7%). Key findings highlight a high incidence of head and neck injuries (55.9%), chest trauma (44.1%), and various injuries such as soft tissue lacerations (100%), fractures particularly skull fractures at 32.4%, and brain hemorrhages (23.5%). The limitations of this study include its single-center scope and the focus on stable patients, which may bias the representation of injury types. This case series provides critical insights into the radiological impacts of large-scale terror events, emphasizing the importance of comprehensive preparedness and research in the field of mass-casualty incident response.

Background: Computed tomography (CT) is the main diagnostic modality for detecting pancreatic adenocarcinoma.

Objectives: To assess the frequency of missed pancreatic adenocarcinoma on CT scans according to different CT protocols.

Methods: The medical records of consecutive pancreatic adenocarcinoma patients were retrospectively collected (12/2011–12/2015). Patients with abdominal CT scans performed up to a year prior to cancer diagnosis were included. Two radiologists registered the presence of radiological signs of missed cancers. The frequency of missed cancers was compared between portal and pancreatic/triphasic CT protocols.

Results: Overall, 180 CT scans of pancreatic adenocarcinoma patients performed prior to cancer diagnosis were retrieved; 126/180 (70.0%) were conducted using pancreatic/triphasic protocols and 54/180 (30.0%) used portal protocols. The overall frequency of missed cancers was 6/180 (3.3%) in our study population. The frequency of missed cancers was higher with the portal CT protocols compared to the pancreatic/triphasic protocols: 5/54 (9.3%) vs. 1/126 (0.8%), P = 0.01. CT signs of missed cancers included small hypodense lesions, peri-pancreatic fat stranding, and dilated pancreatic duct with a cut-off sign.

Conclusions: The frequency of missed pancreatic adenocarcinoma is higher on portal CT protocols. Physicians should consider the cancer miss rate on different CT protocols.

Background: Jejunal disease is associated with worse prognosis in Crohn's disease. The added value of diffusion weighted imaging for evaluating jejunal inflammation related to Crohn's Disease is scarce.

Objectives: To compare diffusion weighted imaging, video capsule endoscopy, and inflammatory biomarkers in the assessment of Crohn's disease involving the jejunum.

Methods: Crohn's disease patients in clinical remission were prospectively recruited and underwent magnetic resonance (MR)-enterography and video capsule endoscopy. C-reactive protein and fecal-calprotectin levels were obtained. MR-enterography images were evaluated for restricted diffusion, and apparent diffusion coefficient values were measured. The video capsule endoscopy-based Lewis score was calculated. Associations between diffusion weighted imaging, apparent diffusion coefficient, Lewis score, and inflammatory biomarkers were evaluated.

Results: The study included 51 patients, and 27/51 (52.9%) with video capsule endoscopies showed jejunal mucosal inflammation. Sensitivity and specificity of restricted diffusion for video capsule endoscopy mucosal inflammation were 59.3% and 37.5% for the first reader, and 66.7% and 37.5% for the second reader, respectively. Diffusion weighted imaging was not statistically associated with jejunal video capsule endoscopy inflammation (P = 0.813).

Conclusions: Diffusion weighted imaging was not an effective test for evaluation of jejunal inflammation as seen by video capsule endoscopy in patients with quiescent Crohn's disease.

Background: Perivascular cuffing as the sole imaging manifestation of pancreatic ductal adenocarcinoma (PDAC) is an under-recognized entity.

Objectives: To present this rare finding and differentiate it from retroperitoneal fibrosis and vasculitis.

Methods: Patients with abdominal vasculature cuffing were retrospectively collected (January 2011 to September 2017). We evaluated vessels involved, wall thickness, length of involvement and extra-vascular manifestations.

Results: Fourteen patients with perivascular cuffing were retrieved: three with celiac and superior mesenteric artery (SMA) perivascular cuffing as the only manifestation of surgically proven PDAC, seven with abdominal vasculitis, and four with retroperitoneal fibrosis. PDAC patients exhibited perivascular cuffing of either or both celiac and SMA (3/3). Vasculitis patients showed aortitis with or without iliac or SMA cuffing (3/7) or cuffing of either or both celiac and SMA (4/7). Retroperitoneal fibrosis involved the aorta (4/4), common iliac (4/4), and renal arteries (2/4). Hydronephrosis was present in 3/4 of retroperitoneal fibrosis patients. PDAC and vasculitis demonstrated reduced wall thickness in comparison to retroperitoneal fibrosis (PDAC: 1.0 ± 0.2 cm, vasculitis: 1.2 ± 0.5 cm, retroperitoneal fibrosis: 2.4 ± 0.4 cm; P = 0.002). There was no significant difference in length of vascular involvement (PDAC: 6.3 ± 2.1 cm, vasculitis: 7.1 ± 2.6 cm, retroperitoneal fibrosis: 8.7 ± 0.5 cm).

Conclusions: Celiac and SMA perivascular cuffing can be the sole finding in PDAC and may be indistinguishable from vasculitis. This entity may differ from retroperitoneal fibrosis as it spares the aorta, iliac, and renal arteries and demonstrates thinner walls and no hydronephrosis.

Gallbladder metastasis is an extremely rare entity [1]. It is mainly secondary to melanoma but has also been reported as originating from breast cancer, renal cell carcinoma, and gastric cancer. Its diagnosis is often late in the advanced stage of the disease with the involvement of other organ systems [2].

We present a case of a patient who developed gastric cancer gallbladder metastasis. These findings are usually incidental on pathology of cholecystectomy specimens [1]. In our case, the metastatic lesion was demonstrated on magnetic resonance imaging (MRI) prior to surgery. Of note, the lesion had a similar enhancement pattern to the primary tumor.

Background: Acute mesenteric ischemia (AMI) is a medical condition with high levels of morbidity and mortality. However, most patients suspected of AMI will eventually have a different diagnosis. Nevertheless, these patients have a high risk for co-morbidities.

Objectives: To analyze patients with suspected AMI with an alternative final diagnosis, and to evaluate a machine learning algorithm for prognosis prediction in this population.

Methods: In a retrospective search, we retrieved patient charts of those who underwent computed tomography angiography (CTA) for suspected AMI between January 2012 and December 2015. Non-AMI patients were defined as patients with negative CTA and a final clinical diagnosis other than AMI. Correlation of past medical history, laboratory values, and mortality rates were evaluated. We evaluated gradient boosting (XGBoost) model for mortality prediction.

Results: The non-AMI group comprised 325 patients. The two most common groups of diseases included gastrointestinal (33%) and biliary-pancreatic diseases (27%). Mortality rate was 24.6% for the entire cohort. Medical history of chronic kidney disease (CKD) had higher risk for mortality (odds ratio 2.2). Laboratory studies revealed that lactate dehydrogenase (LDH) had the highest diagnostic ability for predicting mortality in the entire cohort (AUC 0.70). The gradient boosting model showed an area under the curve of 0.82 for predicting mortality.

Conclusions: Patients with suspected AMI with an alternative final diagnosis showed a 25% mortality rate. A past medical history of CKD and elevated LDH were associated with increased mortality. Non-linear machine learning algorithms can augment single variable inputs for predicting mortality.

Background: The coronavirus disease-2019 (COVID-19) outbreak had an effect on healthcare.

Objectives: To evaluate the presentation and management of patients with acute appendicitis.

Methods: A retrospective study was conducted of all patients presenting with acute appendicitis to the emergency department of a large tertiary center during March and April 2020. Clinical features, diagnostic workup, and management were compared.

Results: Seventy-four patients presented with acute appendicitis during the pandemic compared to 60 patients during the same time the year before. There were no significant differences in patient demographics: age (P = 0.65), gender (P = 0.73), smoking status (P = 0.48). During COVID-19 patients were more likely to complain of right lower quadrant pain (100% vs. 78.3%, P < 0.01). Rates of surgical treatment was similar (83.8% vs. 81.7%, P = 1); mean operative time was longer during COVID-19 (63 ± 23 vs. 52 ± 26 minutes, P = 0.03). There were no significant differences in intra-operative findings including the presence of appendiceal perforation (16.3% vs. 14.5%, P = 0.8), abscess (6.1% vs. 9.7%, P = 0.73), or involvement of cecum or terminal ileum (14.28% vs. 19.63%, P = 1). Postoperative treatment with antibiotics was more prevalent during COVID-19 (37.1% vs. 18%, P = 0.04). Length of stay (1.82 ± 2.04 vs. 2.74 ± 4.68, P = 0.2) and readmission rates (6% vs. 11.3%, P =0.51) were similar.

Conclusion: The COVID-19 pandemic did not significantly affect the presentation, clinical course, management, and outcomes of patients presenting with acute appendicitis.

Background: The novel coronavirus disease (COVID-19) pandemic changed medical environments worldwide.

Objectives: To evaluate the impact of the COVID-19 pandemic on trauma-related visits to the emergency department (ED).

Methods: A single tertiary center retrospective study was conducted that compared ED attendance of patients with injury-related morbidity between March 2020 (COVID-19 outbreak) and pre-COVID-19 periods: February 2020 and the same 2 months in 2018 and 2019.

Results: Overall, 6513 patients were included in the study. During the COVID-19 outbreak, the daily number of patients visiting the ED for acute trauma declined by 40% compared to the average in previous months (P < 0.01). A strong negative correlation was found between the number of trauma-related ED visits and the log number of confirmed cases of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) in Israel (Pearson's r = -0.63, P < 0.01). In the COVID-19 period there was a significant change in the proportion of elderly patients (7% increase, P = 0.002), admissions ratio (12% increase, P < 0.001), and patients brought by emergency medical services (10% increase, P < 0.001). The number of motor vehicle accident related injury declined by 45% (P < 0.01).

Conclusions: A significant reduction in the number of trauma patients presenting to the ED occurred during the COVID-19 pandemic, yet trauma-related admissions were on the rise