Background: ChatGPT-4 is the latest release of a novel artificial intelligence (AI) chatbot able to answer freely formulated and complex questions. In the near future, ChatGPT could become the new standard for health care professionals and patients to access medical information. However, little is known about the quality of medical information provided by the AI. Objective: We aimed to assess the reliability of medical information provided by ChatGPT. Methods: Medical information provided by ChatGPT-4 on the 5 hepato-pancreatico-biliary (HPB) conditions with the highest global disease burden was measured with the Ensuring Quality Information for Patients (EQIP) tool. The EQIP tool is used to measure the quality of internet-available information and consists of 36 items that are divided into 3 subsections. In addition, 5 guideline recommendations per analyzed condition were rephrased as questions and input to ChatGPT, and agreement between the guidelines and the AI answer was measured by 2 authors independently. All queries were repeated 3 times to measure the internal consistency of ChatGPT. Results: Five conditions were identified (gallstone disease, pancreatitis, liver cirrhosis, pancreatic cancer, and hepatocellular carcinoma). The median EQIP score across all conditions was 16 (IQR 14.5-18) for the total of 36 items. Divided by subsection, median scores for content, identification, and structure data were 10 (IQR 9.5-12.5), 1 (IQR 1-1), and 4 (IQR 4-5), respectively. Agreement between guideline recommendations and answers provided by ChatGPT was 60% (15/25). Interrater agreement as measured by the Fleiss κ was 0.78 (P<.001), indicating substantial agreement. Internal consistency of the answers provided by ChatGPT was 100%. Conclusions: ChatGPT provides medical information of comparable quality to available static internet information. Although currently of limited quality, large language models could become the future standard for patients and health care professionals to gather medical information.

Background: This individual-patient data meta-analysis investigated the effects of enhanced recovery after surgery (ERAS) protocols compared with conventional care on postoperative outcomes in patients undergoing pancreatoduodenectomy.Methods: The Cochrane Library, MEDLINE, Embase, Scopus, and Web of Science were searched systematically for articles reporting outcomes of ERAS after pancreatoduodenectomy published up to August 2020. Comparative studies were included. Main outcomes were postoperative functional recovery elements, postoperative morbidity, duration of hospital stay, and readmission.Results: Individual-patient data were obtained from 17 of 31 eligible studies comprising 3108 patients. Time to liquid (mean difference (MD) −3.23 (95 per cent c.i. −4.62 to −1.85) days; P < 0.001) and solid (−3.84 (−5.09 to −2.60) days; P < 0.001) intake, time to passage of first stool (MD −1.38 (−1.82 to −0.94) days; P < 0.001) and time to removal of the nasogastric tube (3.03 (−4.87 to −1.18) days; P = 0.001) were reduced with ERAS. ERAS was associated with lower overall morbidity (risk difference (RD) −0.04, 95 per cent c.i. −0.08 to −0.01; P = 0.015), less delayed gastric emptying (RD −0.11, −0.22 to −0.01; P = 0.039) and a shorter duration of hospital stay (MD −2.33 (−2.98 to −1.69) days; P < 0.001) without a higher readmission rate.Conclusion: ERAS improved postoperative outcome after pancreatoduodenectomy. Implementation should be encouraged.

Objective: The aim was to analyze the learning curves of minimal invasive liver surgery(MILS) and propose a standardized reporting. Summary Background Data: MILS offers benefits compared to open resections. For a safe introduction along the learning curve, formal training is recommended. However, definitions of learning curves and methods to assess it lack standardization. Methods: A systematic review of PubMed, Web of Science, and CENTRAL databases identified studies on learning curves in MILS. The primary outcome was the number needed to overcome the learning curve. Secondary outcomes included endpoints defining learning curves, and characterization of different learning phases(competency, proficiency and mastery). Results: 60 articles with 12’241 patients and 102 learning curve analyses were included. The laparoscopic and robotic approach was evaluated in 71 and 18 analyses and both approaches combined in 13 analyses. Sixty-one analyses (60%) based the learning curve on statistical calculations. The most often used parameters to define learning curves were operative time (n=64), blood loss (n=54), conversion (n=42) and postoperative complications (n=38). Overall competency, proficiency and mastery were reached after 34 (IQR 19-56), 50 (IQR 24-74), 58 (IQR 24-100) procedures respectively. Intraoperative parameters improved earlier (operative time: competency to proficiency to mastery: −13%, 2%; blood loss: competency to proficiency to mastery: –33%, 0%; conversion rate (competency to proficiency to mastery; −21%, −29%), whereas postoperative complications improved later (competency to proficiency to mastery: −25%, −41%). Conclusions: This review summarizes the highest evidence on learning curves in MILS taking into account different definitions and confounding factors. A standardized three-phase reporting of learning phases (competency, proficiency, mastery) is proposed and should be followed.

Background: Transarterial radioembolization in HCC for LT as downstaging/bridging has been increasing in recent years but some indication criteria are still unclear. Methods: We conducted a systematic literature search of primary research publications conducted in PubMed, Scopus and ScienceDirect databases until November 2022. Relevant data about patient selection, HCC features and oncological outcomes after TARE for downstaging or bridging in LT were analyzed. Results: A total of 14 studies were included (7 downstaging, 3 bridging and 4 mixed downstaging and bridging). The proportion of whole liver TARE was between 0 and 1.6%. Multiple TARE interventions were necessary for 16.7% up to 28% of the patients. A total of 55 of 204 patients across all included studies undergoing TARE for downstaging were finally transplanted. The only RCT included presents a higher tumor response with the downstaging rate for LT of TARE than TACE (9/32 vs. 4/34, respectively). Grade 3 or 4 adverse effects rate were detected between 15 and 30% of patients. Conclusions: TARE is a safe therapeutic option with potential advantages in its capacity to necrotize and reduce the size of the HCC for downstaging or bridging in LT.

Objective: The aim of this study was to evaluate the different phases of the learning curve for robotic distal pancreatectomy (RDP) in international expert centers. Background: RDP is an emerging minimally invasive approach; however, only limited, mostly single-center data are available on its safe implementation, including the learning curve. Methods: Consecutive patients undergoing elective RDP from 16 expert centers across 3 continents were included to assess the learning curve. Based on the first 100 RDPs at each center, 3 cutoffs were used to define the learning curve: operative time for competency, major complications (Clavien-Dindo grade ≥III) for proficiency, and textbook outcome for mastery. Clinical outcomes before and after the cutoffs were compared. Results: The learning curve analysis was conducted on 1109 of 2403 RDPs. Competency, proficiency, and mastery, respectively, were reached after 46, 63, and 73 RDP procedures. After competency, operative time decreased from 245 to 235 minutes ( P = 0.002). Attaining proficiency was reflected by a reduction in the rate of major complications from 20% to 15% ( P = 0.012), and mastery was associated with a higher proportion of patients with textbook outcomes (71% vs 63%; P = 0.028). The postoperative pancreatic fistula rate remained stable along the learning curve, ranging between 18.5% and 21.5%. Previous laparoscopic experience accelerated the learning process by virtue of reduced operative time and an earlier decrease in major complications. Conclusions: Competency, proficiency, and mastery for RDP were reached after 46, 63, and 73 procedures, respectively, at international expert centers. The findings highlight that the learning curves for intraoperative parameters are completed earlier; however, extensive experience is needed to master RDP.