Evaluating the accuracy of ChatGPT-4 in predicting ASA scores: A prospective multicentric study ChatGPT-4 in ASA score prediction.

BACKGROUND: This study investigates the potential of ChatGPT-4, developed by OpenAI, in enhancing medical decision-making processes, particularly in preoperative assessments using the American Society of Anesthesiologists (ASA) scoring system. The ASA score, a critical tool in evaluating patients' health status and anesthesia risks before surgery, categorizes patients from I to VI based on their overall health and risk factors. Despite its widespread use, determining accurate ASA scores remains a subjective process that may benefit from AI-supported assessments. This research aims to evaluate ChatGPT-4's capability to predict ASA scores accurately compared to expert anesthesiologists' assessments. METHODS: In this prospective multicentric study, ethical board approval was obtained, and the study was registered with clinicaltrials.gov (NCT06321445). We included 2851 patients from anesthesiology outpatient clinics, spanning neonates to all age groups and genders, with ASA scores between I-IV. Exclusion criteria were set for ASA V and VI scores, emergency operations, and insufficient information for ASA score determination. Data on patients' demographics, health conditions, and ASA scores by anesthesiologists were collected and anonymized. ChatGPT-4 was then tasked with assigning ASA scores based on the standardized patient data. RESULTS: Our results indicate a high level of concordance between ChatGPT-4 predictions and anesthesiologists' evaluations, with Cohen's kappa analysis showing a kappa value of 0.858 (p = 0.000). While the model demonstrated over 90% accuracy in predicting ASA scores I to III, it showed a notable variance in ASA IV scores, suggesting a potential limitation in assessing patients with more complex health conditions. DISCUSSION: The findings suggest that ChatGPT-4 can significantly contribute to the medical field by supporting anesthesiologists in preoperative assessments. This study not only demonstrates ChatGPT-4's efficacy in medical data analysis and decision-making but also opens new avenues for AI applications in healthcare, particularly in enhancing patient safety and optimizing surgical outcomes. Further research is needed to refine AI models for complex case assessments and integrate them seamlessly into clinical workflows.

Successful results of early nucleos(t)ide analogue treatment for liver transplantation candidates with severe acute hepatitis B infection.

BACKGROUND: Early treatment of severe acute hepatitis B virus (HBV) infection with nucleos(t)ide analogues may prevent progression to acute liver failure (ALF). PATIENTS AND METHODS: The charts of 24 patients who were treated for severe acute HBV infection (either INR ≥ 1.5 or INR≥ 1.4 and total bilirubin ≥ 20 mg/dL at the referring institution or after admission) between April 2021 and May 2023 (inclusive) were evaluated retrospectively. Twelve patients were women; median [range] age: 48 [35-68]. Entecavir (0.5 mg/day) (n = 16) or tenofovir disoproxil fumarate (245 mg/day) (n =8) were used depending on availability. RESULTS: Two patients required liver transplant which was performed successfully in one (no suitable donor for the other). Deterioration to ALF was prevented in 22 of the 24 cases (92%); these patients could be discharged after median (range) 12 (5-24) days following initiation of the antiviral drug. There was no significant difference in efficacy between the two antiviral agents. The anti-HBsAg antibody became positive in 16 patients (73%); one other patient became HBsAg negative at 1 month after discharge but was lost to follow up. Five patients (23%) are still HBsAg positive but all except one have started treatment in the last 6 months. One of the recently treated 4 patients stopped taking the antiviral drug at his own will and one has become anti-HIV antibody positive during follow up. CONCLUSION: Early treatment of severe acute HBV infection with entecavir or tenofovir disoproxil fumarate prevents the need for liver transplant and consideration of living donors.

Assessment of the factors that affect fast-track or early extubation following pediatric cardiac surgery.

Background: This study aims to evaluate the early extubation rate and the factors affecting early extubation in pediatric patients undergoing cardiac surgery. Methods: Between August 1st, 2020 and December 1st, 2021, a total of 528 pediatric patients (264 males, 264 females; median age: 4 months; range, 2 days to 24 months) who were followed in the pediatric cardiac intensive care unit after congenital heart surgery were retrospectively analyzed. Demographic and clinical characteristics of the patients including operation and intensive care data were obtained from the medical records. Patients included in the study were categorized into three groups as the group of patients who were extubated in the operating room (fast-track extubation), the group of patients who were extubated in the first 6 h of the operation (early extubation), the group of patients who were extubated after the postoperative 6 h or the group of patients who were not extubated or died (delayed extubation). Results: Sixty-eight (12.9%) cases had fast-tract extubation, 124 (23.6%) cases had early extubation, and 335 (63.6%) cases had delayed extubation. The median age of the patients in the delayed extubation group was three months, which was significantly lower than those of the other groups (p<0.05). Reintubation rates were 1.5% in the fast-tract extubation group, 2.5% in early extubation group, and 9% in delayed extubation group (p<0.05). The median intensive care unit stay was 3, 5, and 10 days, respectively (p<0.05). Length of hospitalization was significantly higher in the delayed extubation group compared to the other groups (p<0.05). Neonatal age group, Risk Adjustment for Congenital Heart Surgery 1 score >4, Society of Thoracic Surgeons- European Association for Cardio-Thoracic Surgery mortality category >3, cardiopulmonary bypass time >100/min, vasoactive inotrope score >8, acute kidney injury >2, and low weight were found to be independent risk factors for delayed extubation. Conclusion: Fast-track and early extubation can be successfully applied with low reintubation rates in selected cases with congenital heart surgery. Age, body weight, presence of genetic syndrome, operational risk category, and procedure time may affect the extubation time.

The comparison of three different acute kidney injury classification systems after congenital heart surgery.

BACKGROUND: We aimed to compare the frequency of acute kidney injury (AKI) and its effects on mortality and morbidity with different classification systems in pediatric patients who had surgery under cardiopulmonary bypass for congenital heart disease. METHODS: This study included children younger than 18 years old who were followed up in the pediatric cardiac intensive care unit between September 1 and December 1, 2020, after congenital heart surgery with cardiopulmonary bypass. Each case was categorized postoperatively in terms of AKI using Pediatric-Modified Risk, Injury, Failure, Loss, and End-Stage (pRIFLE), Acute Kidney Injury Network (AKIN), and Kidney Disease: Improving Global Outcomes (KDIGO). Hospital mortality (developed within the first 30 days postoperatively) and morbidity (longer than 7 days intensive care unit stay) were compared by three model classes. Results were evaluated statistically. RESULTS: One hundred patients were included in the study. The median age was 3 months (1 day-180 months). Acute kidney injury was diagnosed in 49% of the cases according to the pRIFLE classification. It was diagnosed in 31% of the patients by AKIN classification. It was diagnosed in 41% of the patients with the KDIGO criteria. Morbidity was observed in 25% (n = 25) of all cases. The morbidity predictor was 0.800 for pRIFLE, 0.747 for AKIN and 0.853 for KDIGO by receiver operating characteristics analysis. All three categories predicted morbidity significantly (P < 0.001). Mortality was 10% (n = 10) for all groups. The mortality predictor was 0.783 for pRIFLE, 0.717 for AKIN and 0.794 for KDIGO by receiver operating characteristics analysis, and all three categories predicted mortality significantly (P < 0.001). CONCLUSIONS: Regardless of the three methods used, AKI was commonly detected in pediatric patients undergoing congenital heart surgery. pRIFLE classification diagnosed more patients with AKI than AKIN and KDIGO. The KDIGO and pRIFLE classifications were better in predicting hospital mortality.

Continuous Endotracheal Tube Cuff Pressure Control Decreases Incidence of Ventilator-Associated Pneumonia in Patients with Traumatic Brain Injury.

BACKGROUND: Ventilator-associated pneumonia (VAP) is a common cause of morbidity and mortality in intensive care unit (ICU), and among the several preventative strategies described to reduce the incidence of VAP, the most important is the endotracheal tube cuff (ETC) pressure. The present study was conducted on 60 patients who required mechanical ventilation (MV) in the ICU with traumatic brain injury (TBI). METHODS: The patients were randomized into two groups of 30, in which ETC pressure was regulated using a smart cuff manager (SCM) (Group II), or manual measurement approach (MMA) (Group I). Demographic data, MV duration, length of ICU stay and mortality rates were recorded. The clinical pulmonary infection scores (CPISs), C-reactive protein (CRP) values, and the fraction of inspired oxygen (FiO2) and positive end-expiratory pressure (PEEP) values of the groups were compared at baseline, and at hours 48, 72 and 96. RESULTS: In Group I, CPIS values significantly higher than Group II in 48th, 72nd and 96th hours (p < 0.05). In Group I, PEEP values and deep tracheal aspirate (DTA) culture growth rates significantly higher than Group II in 72nd and 96th hours (p < 0.05). CONCLUSION: The continuous maintenance of ETC pressure using SCM reduced the incidence of VAP.

Reverse Trendelenburg position applied prior to pneumoperitoneum prevents excessive increase in optic nerve sheath diameter in laparoscopic cholecystectomy: randomized controlled trial.

The aim of this randomized controlled trial was to determine whether applying the reverse Trendelenburg position before pneumoperitoneum has a preventive effect on increased intracranial pressure using optic nerve sheath diameter (ONSD) measurement as a noninvasive parameter. Seventy-nine patients were allocated to two groups according to whether pneumoperitoneum was applied in the supine position (group S, n = 40) or in the reverse Trendelenburg position (group RT, n = 39). The ONSD was measured at the following time points: T0: before anesthesia; T1: after endotracheal intubation; T2: after pneumoperitoneum in group S and after positioning in group RT; T3: after positioning in group S and after pneumoperitoneum in group RT; T4: 30 min after endotracheal intubation, and T5: after desufflation. The end-tidal carbon dioxide (EtCO2), regional cerebral oxygen saturation (rSO2), peripheral oxygen saturation (SpO2), mean arterial pressure (MAP), heart rate (HR), peak inspiratory pressure (Ppeak), and dynamic compliance (Cdyn) were recorded. Background and perioperative characteristics were similar in both groups. In group S, the ONSD was higher at T2, T3, T4, and T5 than that in group RT (p < 0.001, p = 0.002, p = 0.001, and p = 0.012, respectively). In the same group, the number of patients with an ONSD above 5.8 mm was higher at T2, T3, and T4 (p < 0.001, p = 0.042, p = 0.036, respectively). The rSO2 and SpO2 were not different between the groups. The mean arterial pressure was lower in group RT at T2, and the HR was not different between the groups (p < 0.001). In group S, Ppeak was higher and Cdyn was lower at T2 (p < 0.001). The number of patients with nausea was higher in group S (p = 0.027). The present study demonstrates that applying the reverse Trendelenburg position before pneumoperitoneum prevented an increase in the ONSD in patients undergoing laparoscopic cholecystectomy.Trial registration The trial was registered prior to patient enrollment at https://register.clinicaltrials.gov (NCT04224532, Date of the registration: January 8, 2020).