An Exploratory Analysis of ChatGPT Compared to Human Performance With the Anesthesiology Oral Board Examination: Initial Insights and Implications.

BACKGROUND: Chat Generative Pre-Trained Transformer (ChatGPT) has been tested and has passed various high-level examinations. However, it has not been tested on an examination such as the American Board of Anesthesiology (ABA) Standardized Oral Examination (SOE). The SOE is designed to assess higher-level competencies, such as judgment, organization, adaptability to unexpected clinical changes, and presentation of information. METHODS: Four anesthesiology fellows were examined on 2 sample ABA SOEs. Their answers were compared to those produced by the same questions asked to ChatGPT. All human and ChatGPT responses were transcribed, randomized by module, and then reproduced as complete examinations, using a commercially available software-based human voice replicator. Eight ABA applied examiners listened to and scored the topic and modules from 1 of the 4 versions of each of the 2 sample examinations. The ABA did not provide any support or collaboration with any authors. RESULTS: The anesthesiology fellow's answers were found to have a better median score than ChatGPT, for the module topics scores (P = .03). However, there was no significant difference in the median overall global module scores between the human and ChatGPT responses (P = .17). The examiners were able to identify the ChatGPT-generated answers for 23 of 24 modules (95.83%), with only 1 ChatGPT response perceived as from a human. In contrast, the examiners thought the human (fellow) responses were artificial intelligence (AI)-generated in 10 of 24 modules (41.67%). Examiner comments explained that ChatGPT generated relevant content, but were lengthy answers, which at times did not focus on the specific scenario priorities. There were no comments from the examiners regarding Chat GPT fact "hallucinations." CONCLUSIONS: ChatGPT generated SOE answers with comparable module ratings to anesthesiology fellows, as graded by 8 ABA oral board examiners. However, the ChatGPT answers were deemed subjectively inferior due to the length of responses and lack of focus. Future curation and training of an AI database, like ChatGPT, could produce answers more in line with ideal ABA SOE answers. This could lead to higher performance and an anesthesiology-specific trained AI useful for training and examination preparation.

The Year in Thoracic Anesthesia: Selected Highlights from 2022.

This article reviews research highlights in the field of thoracic anesthesia. The highlights of this year included new developments in the preoperative assessment and prehabilitation of patients requiring thoracic surgery, updates on the use of devices for one-lung ventilation (OLV) in adults and children, updates on the anesthetic and postoperative management of these patients, including protective OLV ventilation, the use of opioid-sparing techniques and regional anesthesia, and outcomes using enhanced recovery after surgery, as well as the use of expanding indications for extracorporeal membrane oxygenation, specialized anesthetic techniques for airway surgery, and nonintubated video-assisted thoracic surgery.

Predictive capabilities of the European registry for patients with mechanical circulatory support right-sided heart failure risk score after left ventricular assist device implantation.

OBJECTIVES: The prediction of right heart failure (RHF) after left ventricular assist device (LVAD) implantation remains a challenge. Recently, risk scores were derived from analysis of the European Registry for Patients with Mechanical Circulatory Support (EUROMACS) data, the EUROMACS-RHF, and the modified postoperative EUROMACS-RHF. The authors assessed the performance characteristics of these 2 risk score formulations in a continuous-flow LVAD cohort at their institution. DESIGN: A retrospective, observational study. SETTING: At a tertiary-care academic medical center. PARTICIPANTS: Adult patients who underwent durable LVAD implantation between 2015 and 2018. INTERVENTIONS: None MEASUREMENTS AND MAIN RESULTS: Early post-LVAD RHF was defined as follows: (1) need for right ventricular assist device, or (2) inotropic or inhaled pulmonary vasodilator support for ≥14 postoperative days. The authors used logistic regression and examined receiver operating characteristic (ROC) curves to evaluate the ability of the 2 risk scores to distinguish between outcome groups. A total of 207 patients met the inclusion criteria. Of the patients, 16% developed RHF (33/207). The EUROMACS-RHF score was not predictive of RHF in the authors' cohort (odds ratio [OR] 1.25; 95% CI [0.99-1.60]; p = 0.06), but the postoperative EUROMACS-RHF CPB score was significantly associated (OR 1.38; 95% CI [1.03-1.89]; p = 0.03). The scores had similar ROC curves, with weak discriminatory performance: 0.601 (95% CI [0.509-0.692]) and 0.599 (95% CI [0.505-0.693]) for EUROMACS-RHF and postoperative EUROMACS-RHF, respectively. CONCLUSIONS: In the authors' single-center retrospective analysis, the EUROMACS-RHF risk score did not predict early RHF. An optimized risk score for the prediction of RHF after LVAD implantation remains an urgent unmet need.

A Devastating Floating Aortic Thrombus and Ketosis-Prone Diabetes.

This article reports a case study of a middle-aged patient diagnosed with Ketosis-Prone Diabetes (KPD) and diabetic ketoacidosis who had a mobile thrombus in the distal aortic arch with catastrophic complications from thrombus embolization. The pathogenesis of the mobile aortic thrombus is currently under investigation, with many risk factors having been found. Based on the patient's limited manifestation of atherosclerosis and the absence of any indications of thrombophilia, KPD and inflammation from uncontrolled hyperglycemia likely played a significant role in the formation of the thrombus. KPD is a subtype of diabetes characterized by the abrupt onset of severe hyperglycemia and ketoacidosis. The inflammation caused by uncontrolled hyperglycemia in KPD patients can lead to endothelial dysfunction and the activation of prothrombotic pathways. There is a lack of consensus regarding the optimal approach for managing a mobile aortic thrombus. The main strategies under consideration are conservative care, including anticoagulation alone, invasive removal of the thrombus, or endovascular intervention.

Intraoperative Hyperkalemia and Ventricular Arrhythmia During Parathyroidectomy: A Case Report.

We present a case of acute hyperkalemia and ventricular arrhythmia during parathyroidectomy in a patient with end-stage renal disease. This case highlights the under-recognized alterations in potassium homeostasis associated with parathyroidectomy and underscores the importance of preoperative optimization.