Background: The latest advancement of artificial intelligence (AI) is generative pretrained transformer large language models (LLMs). They have been trained on massive amounts of text, enabling humanlike and semantical responses to text-based inputs and requests. Foreshadowing numerous possible applications in various fields, the potential of such tools for medical data integration and clinical decision-making is not yet clear. Objective: In this study, we investigate the potential of LLMs in report-based medical decision-making on the example of acute ischemic stroke (AIS), where clinical and image-based information may indicate an immediate need for mechanical thrombectomy (MT). The purpose was to elucidate the feasibility of integrating radiology report data and other clinical information in the context of therapy decision-making using LLMs. Methods: A hundred patients with AIS were retrospectively included, for which 50% (50/100) was indicated for MT, whereas the other 50% (50/100) was not. The LLM was provided with the computed tomography report, information on neurological symptoms and onset, and patients’ age. The performance of the AI decision-making model was compared with an expert consensus regarding the binary determination of MT indication, for which sensitivity, specificity, and accuracy were calculated. Results: The AI model had an overall accuracy of 88%, with a specificity of 96% and a sensitivity of 80%. The area under the curve for the report-based MT decision was 0.92. Conclusions: The LLM achieved promising accuracy in determining the eligibility of patients with AIS for MT based on radiology reports and clinical information. Our results underscore the potential of LLMs for radiological and medical data integration. This investigation should serve as a stimulus for further clinical applications of LLMs, in which this AI should be used as an augmented supporting system for human decision-making.

Background: Nonsurgical treatment of uncomplicated appendicitis is a reasonable option in many cases despite the sparsity of robust, easy access, externally validated, and multimodally informed clinical decision support systems (CDSSs). Developed by OpenAI, the Generative Pre-trained Transformer 3.5 model (GPT-3) may provide enhanced decision support for surgeons in less certain appendicitis cases or those posing a higher risk for (relative) operative contra-indications. Our objective was to determine whether GPT-3.5, when provided high-throughput clinical, laboratory, and radiological text-based information, will come to clinical decisions similar to those of a machine learning model and a board-certified surgeon (reference standard) in decision-making for appendectomy versus conservative treatment. Methods: In this cohort study, we randomly collected patients presenting at the emergency department (ED) of two German hospitals (GFO, Troisdorf, and University Hospital Cologne) with right abdominal pain between October 2022 and October 2023. Statistical analysis was performed using R, version 3.6.2, on RStudio, version 2023.03.0 + 386. Overall agreement between the GPT-3.5 output and the reference standard was assessed by means of inter-observer kappa values as well as accuracy, sensitivity, specificity, and positive and negative predictive values with the “Caret” and “irr” packages. Statistical significance was defined as p < 0.05. Results: There was agreement between the surgeon’s decision and GPT-3.5 in 102 of 113 cases, and all cases where the surgeon decided upon conservative treatment were correctly classified by GPT-3.5. The estimated model training accuracy was 83.3% (95% CI: 74.0, 90.4), while the validation accuracy for the model was 87.0% (95% CI: 66.4, 97.2). This is in comparison to the GPT-3.5 accuracy of 90.3% (95% CI: 83.2, 95.0), which did not perform significantly better in comparison to the machine learning model (p = 0.21). Conclusions: This study, the first study of the “intended use” of GPT-3.5 for surgical treatment to our knowledge, comparing surgical decision-making versus an algorithm found a high degree of agreement between board-certified surgeons and GPT-3.5 for surgical decision-making in patients presenting to the emergency department with lower abdominal pain.

In clinical routine CT-angiography is frequently used to detect hemorrhage and to locate its source. Many centers use a triple phase protocol consisting of non-contrast, arterial and portal venous phase scan. The aim of this study was to clarify the added value of the non-contrast CT scan in detection of hemorrhage and to provide evidence for or against its usage. We retrospectively included all patients between 2014 and 2020 who underwent triphasic CT angiography for suspected bleeding and interventional angiography within 6 h of CT confirming bleeding. Two experienced observers re-evaluated all CT scans and established consensus on whether the bleeding could confidently be detected without the non-enhanced CT scan. Additionally, we recorded data on radiation exposure. We included 75 patients (44 male, 31 female, median age 64 years) in the final dataset. Of all bleedings 33 (43 %) were GI bleedings. After consensus reading, non-enhanced CT scan was deemed helpful in only 3 cases (5.2 %) with all of these being GI bleeding. Non-enhanced series contributed substantially to the overall radiation exposure (mean DLP_{non contrast} 927.9 mGy*cm, mean DLP_arterial 631.3 mGy*cm, mean DLP_{portal venous} 915.0 mGy*cm). Our results suggest that in the vast majority of cases non-contrast CT is not necessary to detect hemorrhage. Omission of non-enhanced CT scans results in relevant dose reduction. However, in few cases non-contrast scan can be helpful to exclude false positive findings in particular in suspected gastrointestinal bleeding.

Introduction: Acute appendicitis (AA) is a common cause of abdominal pain that can lead to complications like perforation and intra-abdominal abscesses, increasing morbidity and mortality, often requiring emergency surgery. Nevertheless, appendectomy is performed in up to 95% of uncomplicated cases, while complications like perforation and intra-abdominal abscesses increase morbidity and mortality. The current study compares the accuracy of GPT-4.5, DeepSeek R1, and machine learning in assisting with surgical decision-making for patients presenting with lower abdominal pain at the Emergency Department. Methods: In this multicenter retrospective study, 63 histopathologically confirmed appendicitis patients and 50 control patients with right abdominal pain presenting at the Emergency Department at two German hospitals between October 2022 and October 2023 were included. Using each patient’s clinical, laboratory, and radiological findings, DeepSeek (with and without Retrieval-Augmented Generation using 2020 Jerusalem guidelines) was compared in terms of accuracy with GPT-4.5 and a random forest-based machine-learning model, with a board-certified surgeon (reference standard) to determine the optimal treatment approach (laparoscopic exploration/appendectomy versus conservative antibiotic therapy). Results: Accuracy of agreement with board-certified surgeons in the decision-making of appendectomy versus conservative therapy increased non-significantly from 80.5% to 83.2% with DeepSeek and from 70.8 to 76.1% when GPT-4.5 was provided with the World Journal of Emergency Surgery 2020 Jerusalem guidelines on the diagnosis and treatment of acute appendicitis. The estimated machine-learning model training accuracy was 84.3%, while the validation accuracy for the model was 85.0%. Discussion: GPT-4.5 and DeepSeek R1, as well as the machine-learning model, demonstrate promise in aiding surgical decision-making for appendicitis, particularly in resource-constrained settings. Ongoing training and validation are required to optimize the performance of such models.

Background: Nonsurgical treatment in uncomplicated appendicitis is in many cases a reasonable option, despite the sparsity of robust, easy access, externally validated and multimodally informed clinical decision support systems (CDSS). Developed by OpenAI, the Generative Pre trained Transformer 3.5 model (GPT 3), may provide enhanced decision support for surgeons in less certain appendicitis cases or those posing a higher risk for (relative) operative contra indications. Our objective was to determine whether GPT 3.5, when provided high throughput clinical, laboratory and radiological text based information will come to similar clinical decisions as a machine learning model and a board certified surgeon (reference standard) in decision making for appendectomy versus conservative treatment. Methods: In this cohort study we randomly collected patients presenting at the Emergency Department (ED) of two German hospitals (GFO, Troisdorf and University Hospital Cologne) with right abdominal pain between October 2022 and October 2023. Statistical analysis was performed using R, version 3.6.2, on RStudio, version 2023.03.0+386. Overall agreement between GPT 3.5 output and the reference standard was assessed by means of inter observer kappa values as well as accuracy, sensitivity, specificity, positive and negative predictive value with the “Caret” and “irr” package. Statistical significance was defined as p < 0.05. Results: There was agreement between surgeon decision and GPT 3.5 in 102 of 113 cases and all cases where the surgeon decided upon conservative treatment were correctly classified by GPT 3.5. The estimated model training accuracy was 83.3 % (95% CI: 74.0, 90.4), while the validation accuracy for the model was 87.0 % (95% CI: 66.4, 97.2). This in comparison to the GPT 3.5 accuracy of 90.3% (95% CI: 83.2, 95.0), which did not perform significantly better in comparison to the machine learning model (P = 0.21). Conclusions: This to our knowledge first “intended use” for surgical treatment GPT 3.5 study comparing surgical decision making versus algorithm found a high degree of agreement between board certified surgeons and GPT 3.5 for surgical decision making in patients presenting to the emergency department with lower abdominal pain.