Large Language Model Capabilities in Perioperative Risk Prediction and Prognostication.

Importance: General-domain large language models may be able to perform risk stratification and predict postoperative outcome measures using a description of the procedure and a patient's electronic health record notes. Objective: To examine predictive performance on 8 different tasks: prediction of American Society of Anesthesiologists Physical Status (ASA-PS), hospital admission, intensive care unit (ICU) admission, unplanned admission, hospital mortality, postanesthesia care unit (PACU) phase 1 duration, hospital duration, and ICU duration. Design, Setting, and Participants: This prognostic study included task-specific datasets constructed from 2 years of retrospective electronic health records data collected during routine clinical care. Case and note data were formatted into prompts and given to the large language model GPT-4 Turbo (OpenAI) to generate a prediction and explanation. The setting included a quaternary care center comprising 3 academic hospitals and affiliated clinics in a single metropolitan area. Patients who had a surgery or procedure with anesthesia and at least 1 clinician-written note filed in the electronic health record before surgery were included in the study. Data were analyzed from November to December 2023. Exposures: Compared original notes, note summaries, few-shot prompting, and chain-of-thought prompting strategies. Main Outcomes and Measures: F1 score for binary and categorical outcomes. Mean absolute error for numerical duration outcomes. Results: Study results were measured on task-specific datasets, each with 1000 cases with the exception of unplanned admission, which had 949 cases, and hospital mortality, which had 576 cases. The best results for each task included an F1 score of 0.50 (95% CI, 0.47-0.53) for ASA-PS, 0.64 (95% CI, 0.61-0.67) for hospital admission, 0.81 (95% CI, 0.78-0.83) for ICU admission, 0.61 (95% CI, 0.58-0.64) for unplanned admission, and 0.86 (95% CI, 0.83-0.89) for hospital mortality prediction. Performance on duration prediction tasks was universally poor across all prompt strategies for which the large language model achieved a mean absolute error of 49 minutes (95% CI, 46-51 minutes) for PACU phase 1 duration, 4.5 days (95% CI, 4.2-5.0 days) for hospital duration, and 1.1 days (95% CI, 0.9-1.3 days) for ICU duration prediction. Conclusions and Relevance: Current general-domain large language models may assist clinicians in perioperative risk stratification on classification tasks but are inadequate for numerical duration predictions. Their ability to produce high-quality natural language explanations for the predictions may make them useful tools in clinical workflows and may be complementary to traditional risk prediction models.

Anesthesiology Performance Improvement and Reporting Exchange (ASPIRE) Quality Metrics in Patients Undergoing Decompressive Craniectomy and Endoscopic Clot Evacuation after Spontaneous Supratentorial Intracerebral Hemorrhage: A Retrospective Observational Study.

BACKGROUND: We report adherence to 6 Anesthesiology Performance Improvement and Reporting Exchange (ASPIRE) quality metrics (QMs) relevant to patients undergoing decompressive craniectomy or endoscopic clot evacuation after spontaneous supratentorial intracerebral hemorrhage (sICH). METHODS: In this retrospective observational study, we describe adherence to the following ASPIRE QMs: acute kidney injury (AKI-01); mean arterial pressure < 65 mm Hg for less than 15 minutes (BP-03); myocardial injury (CARD-02); treatment of high glucose (> 200 mg/dL, GLU-03); reversal of neuromuscular blockade (NMB-02); and perioperative hypothermia (TEMP-03). RESULT: The study included 95 patients (70% male) with median (interquartile range) age 55 (47 to 66) years and ICH score 2 (1 to 3) undergoing craniectomy (n=55) or endoscopic clot evacuation (n=40) after sICH. In-hospital mortality attributable to sICH was 23% (n=22). Patients with American Society of Anesthesiologists physical status class 5 (n=16), preoperative reduced glomerular filtration rate (n=5), elevated cardiac troponin (n=21) and no intraoperative labs with high glucose (n=71), those who were not extubated at the end of the case (n=62) or did not receive a neuromuscular blocker given (n=3), and patients having emergent surgery (n=64) were excluded from the analysis for their respective ASPIRE QM based on predetermined ASPIRE exclusion criteria. For the remaining patients, the adherence to ASPIRE QMs were: AKI-01, craniectomy 34%, endoscopic clot evacuation 1%; BP-03, craniectomy 72%, clot evacuation 73%; CARD-02, 100% for both groups; GLU-03, craniectomy 67%, clot evacuation 100%; NMB-02, clot evacuation 79%, and; TEMP-03, clot evacuation 0% with hypothermia. CONCLUSION: This study found variable adherence to ASPIRE QMs in sICH patients undergoing decompressive craniectomy or endoscopic clot evacuation. The relatively high number of patients excluded from individual ASPIRE metrics is a major limitation.

The Prevalence and Factors Associated with the Prescription of Opioids for Head/Neck Pain after Elective Craniotomy for Tumor Resection/Vascular Repair: A Retrospective Cohort Study.

Background and objective: There is no report of the rate of opioid prescription at the time of hospital discharge, which may be associated with various patient and procedure-related factors. This study examined the prevalence and factors associated with prescribing opioids for head/neck pain after elective craniotomy for tumor resection/vascular repair. Methods: We performed a retrospective cohort study on adults undergoing elective craniotomy for tumor resection/vascular repair at a large quaternary-care hospital. We used univariable and multivariable analysis to examine the prevalence and factors (pre-operative, intraoperative, and postoperative) associated with prescribing opioids at the time of hospital discharge. We also examined the factors associated with discharge oral morphine equivalent use. Results: The study sample comprised 273 patients with a median age of 54 years [IQR 41,65], 173 females (63%), 174 (63.7%) tumor resections, and 99 (36.2%) vascular repairs. The majority (n = 264, 96.7%) received opioids postoperatively. The opiate prescription rates were 72% (n = 196/273) at hospital discharge, 23% (19/83) at neurosurgical clinical visits within 30 days of the procedure, and 2.4% (2/83) after 30 days from the procedure. The median oral morphine equivalent (OME) at discharge use was 300 [IQR 175,600]. Patients were discharged with a median supply of 5 days [IQR 3,7]. On multivariable analysis, opioid prescription at hospital discharge was associated with pre-existent chronic pain (adjusted odds ratio, aOR 1.87 [1.06,3.29], p = 0.03) and time from surgery to hospital discharge (compared to patients discharged within days 1−4 postoperatively, patients discharged between days 5−12 (aOR 0.3, 95% CI [0.15; 0.59], p = 0.0005), discharged at 12 days and later (aOR 0.17, 95% CI [0.07; 0.39], p < 0.001)). There was a linear relationship between the first 24 h OME (p < 0.001), daily OME (p < 0.001), hospital OME (p < 0.001), and discharge OME. Conclusions: This single-center study finds that at the time of hospital discharge, opioids are prescribed for head/neck pain in as many as seven out of ten patients after elective craniotomy. A history of chronic pain and time from surgery to discharge may be associated with opiate prescriptions. Discharge OME may be associated with first 24-h, daily OME, and hospital OME use. Findings need further evaluation in a large multicenter sample. The findings are important to consider as there is growing interest in an early discharge after elective craniotomy.

Risk factors for a positive neoaortic arch gradient after stage I palliation for hypoplastic left heart syndrome.

BACKGROUND: Providing unobstructed systemic blood flow is one goal of stage I palliation for hypoplastic left heart syndrome. Although clinically significant obstruction is defined when the arch gradient exceeds 15 mm Hg, any positive gradient constitutes obstruction, which may impair ventricular function. We sought to identify risk factors before stage I palliation that result in a positive neoaortic arch gradient before bidirectional Glenn. METHODS: Reviewed were 51 neonates who underwent stage I palliation and subsequent bidirectional cavopulmonary anastomosis procedures for hypoplastic left heart syndrome. Echocardiograms before stage I palliation were reviewed for aortic dimensions. Cardiac catheterization before bidirectional cavopulmonary anastomosis determined the aortic arch gradient and degree of right ventricular dysfunction. RESULTS: Of the 51 patients, 24 (47%) had a negative or absent arch gradient. Patients with a positive gradient had a median gradient of 5 mm Hg (range, 1 to 60 mm Hg). The diameter of the ascending aorta and proximal transverse arch indexed to the descending thoracic aorta (0.5 ± 0.2 vs 0.7 ± 0.4 and 0.4 ± 0.2 vs 0.6 ± 0.2 mm, p = 0.02 and p = 0.01) and lower birth weight (3.1 ± 0.5 vs 3.4 ± 0.4 kg, p = 0.03) were risk factors of a positive neoaortic arch gradient. Further, the degree of arch obstruction was inversely related to the degree of right ventricular function (odds ratio, 1.08; p < 0.01). CONCLUSIONS: Lower birth weight and a smaller aortic diameter confer a higher risk of developing a positive neoaortic arch gradient, resulting in reduced right ventricular function.