Large language models (LLMs) such as ChatGPT, Claude, Llama, and Qwen are emerging as transformative technologies for the diagnosis and treatment of various diseases. With their exceptional long-context reasoning capabilities, LLMs are proficient in clinically relevant tasks, particularly in medical text analysis and interactive dialogue. They can enhance diagnostic accuracy by processing vast amounts of patient data and medical literature and have demonstrated their utility in diagnosing common diseases and facilitating the identification of rare diseases by recognizing subtle patterns in symptoms and test results. Building on their image-recognition abilities, multimodal LLMs (MLLMs) show promising potential for diagnosis based on radiography, chest computed tomography (CT), electrocardiography (ECG), and common pathological images. These models can also assist in treatment planning by suggesting evidence-based interventions and improving clinical decision support systems through integrated analysis of patient records. Despite these promising developments, significant challenges persist regarding the use of LLMs in medicine, including concerns regarding algorithmic bias, the potential for hallucinations, and the need for rigorous clinical validation. Ethical considerations also underscore the importance of maintaining the function of supervision in clinical practice. This paper highlights the rapid advancements in research on the diagnostic and therapeutic applications of LLMs across different medical disciplines and emphasizes the importance of policymaking, ethical supervision, and multidisciplinary collaboration in promoting more effective and safer clinical applications of LLMs. Future directions include the integration of proprietary clinical knowledge, the investigation of open-source and customized models, and the evaluation of real-time effects in clinical diagnosis and treatment practices.
Humans ; Large Language Models ; Tomography, X-Ray Computed

Objective:To explore the adverse reactions and its risk factors during bowel preparation prior to colonoscopy.Methods:The clinical data of 1 727 patients who underwent colonoscopy at the First Affiliated Hospital of Air Military Medical University from September 2019 to March 2021 were analyzed retrospectively. The primary endpoint was the incidence of adverse reactions during bowel preparation. The risk factors of adverse reactions were identified by logistic regressions.Results:The incidence of overall adverse reactions was 54.9% (948/1 727). The incidences of nausea, vomiting, and abdominal discomfort were 38.6% (666/1 727) , 10.2% (177/1 727), 25.9% (447/1 727), respectively. Multivariate logistic regression analysis showed that being female ( OR=1.77, 95% CI: 1.45-2.17, P<0.001), history of abdominal surgery ( OR=1.38, 95% CI:1.08-1.75, P=0.009), inflammatory bowel disease ( OR=1.77, 95% CI: 1.08-2.91, P=0.024) were independent risk factors for adverse reactions during bowel preparation. Female gender ( OR=2.37, 95% CI: 1.66-3.38, P=0.001) and history of abdominal or pelvic surgery ( OR=1.45, 95% CI: 1.02-2.06, P=0.038) were independent risk factors for vomiting, while body mass index ≥25 kg/㎡( OR=0.48, 95% CI: 0.28-0.80, P=0.005) and age≥60 years ( OR=0.58, 95% CI: 0.38-0.89, P=0.013) were protective factors for vomiting during bowel preparation. Conclusion:A significant portion of patients experience adverse reactions during bowel preparation for colonoscopy. The risk factors of adverse reactions include female, history of abdominal surgery and inflammatory bowel disease. Female and a history of abdominal surgery are independent risk factors for vomiting, while obesity and old age are protective factors for vomiting during bowel preparation.

Objective:To explore the adverse reactions and its risk factors during bowel preparation prior to colonoscopy.Methods:The clinical data of 1 727 patients who underwent colonoscopy at the First Affiliated Hospital of Air Military Medical University from September 2019 to March 2021 were analyzed retrospectively. The primary endpoint was the incidence of adverse reactions during bowel preparation. The risk factors of adverse reactions were identified by logistic regressions.Results:The incidence of overall adverse reactions was 54.9% (948/1 727). The incidences of nausea, vomiting, and abdominal discomfort were 38.6% (666/1 727) , 10.2% (177/1 727), 25.9% (447/1 727), respectively. Multivariate logistic regression analysis showed that being female ( OR=1.77, 95% CI: 1.45-2.17, P<0.001), history of abdominal surgery ( OR=1.38, 95% CI:1.08-1.75, P=0.009), inflammatory bowel disease ( OR=1.77, 95% CI: 1.08-2.91, P=0.024) were independent risk factors for adverse reactions during bowel preparation. Female gender ( OR=2.37, 95% CI: 1.66-3.38, P=0.001) and history of abdominal or pelvic surgery ( OR=1.45, 95% CI: 1.02-2.06, P=0.038) were independent risk factors for vomiting, while body mass index ≥25 kg/㎡( OR=0.48, 95% CI: 0.28-0.80, P=0.005) and age≥60 years ( OR=0.58, 95% CI: 0.38-0.89, P=0.013) were protective factors for vomiting during bowel preparation. Conclusion:A significant portion of patients experience adverse reactions during bowel preparation for colonoscopy. The risk factors of adverse reactions include female, history of abdominal surgery and inflammatory bowel disease. Female and a history of abdominal surgery are independent risk factors for vomiting, while obesity and old age are protective factors for vomiting during bowel preparation.

Objective:To explore the influence of pancreatic stents of different lengths on the incidence of post-endoscopic retrograde cholangiopancreatography pancreatitis (PEP).Methods:Data of 299 patients with biliary tract diseases who received endoscopic retrograde cholangiopancreatography (ERCP) and 5 Fr prophylactic pancreatic stents placement at the First Affiliated Hospital of Air Force Medical University from January 2013 to January 2022 were retrospectively analyzed. Patients were divided into the short-stent group (<5 cm, n=163) and the long-stent group (>5 cm, n=136). Baseline data, intraoperative procedures, and postoperative outcomes were compared between the two groups and propensity score matching (PSM) was used for complementary analysis. The primary endpoint was the incidence of PEP. The risk factors for PEP in patients with prophylactic pancreatic stents placement was explored by logistic regression analysis . Results:The overall PEP incidence was 11.0% (33/299). There was no significant difference in the PEP incidence [11.7% (19/163) VS 10.3% (14/136), χ 2=0.140, P=0.708], moderate-to-severe PEP incidence [1.8% (3/163) VS 2.2% (3/136), χ 2=0.000, P=1.000], or spontaneous stent dislodgement rate within two weeks [81.7% (103/126) VS 78.4% (87/111), χ 2=0.421, P=0.516] between the two groups. After PSM, 123 patients were included in each group, and the overall PEP incidence was 8.9% (22/246). There was no significant difference in PEP incidence [8.9% (11/123) VS 8.9% (11/123), χ 2=0.000, P=1.000], moderate-to-severe PEP incidence [0.8% (1/123) VS 1.6% (2/123), χ 2=0.000, P=1.000], or spontaneous stent dislodgement rate within two weeks [80.6% (75/93) VS 78.6% (77/98), χ 2=0.126, P=0.722] between the two groups. Logistic regression analysis showed that normal liver function ( OR=2.36, 95% CI:1.01-5.51, P=0.046) and failed bile duct cannulation ( OR=7.51, 95% CI:2.18-25.96, P=0.001) were independent risk factors for PEP in patients with biliary tract diseases who received prophylactic pancreatic stents placement. Conclusion:Longer 5 Fr pancreatic stents (>5 cm) do not further reduce the overall risk of PEP or moderate-to-severe PEP compared with 5Fr-5 cm stent. Normal liver function and failure of bile duct intubation were independent risk factors for PEP after prophylactic pancreatic stent placement in patients with biliary diseases.

Objective:To compare the knowledge of endoscopic screening of gastrointestinal cancers between digestive healthcare workers and new chatbots (chatGPT and new Bing).Methods:A test with twenty-three questions of endoscopic screening of gastrointestinal cancers was conducted, focusing on the appropriate age of screening, high-risk factors, the follow-up time, and the advantages and risks of digestive endoscopy. Digestive healthcare workers were invited to complete the test through electronic questionnaires. New Bing and chatGPT were used to answer each question for 10 rounds. The primary endpoint was the correct rate of all answers. The answer accuracy between digestive healthcare workers and new chatbots were compared using variance analysis, and the factors that affected the accuracy of the answers in digestive healthcare workers were explored using univariate and multivariable liner regression analysis.Results:The results of the test completed by 76 digestive healthcare workers (21 residents, 28 digestive nurses, and 27 digestive doctors) were analyzed. The accuracies were 36.4%±10.9%, 34.5%±10.2%, 52.2%± 12.6%, 46.3%±9.8% and 67.1%±9.3% in residents, digestive nurses, digestive doctors, chatGPT, and new Bing, respectively, with significant difference ( F=22.6, P<0.001). The accuracy was highest in new Bing ( P<0.001). The accuracy was comparable between chatGPT and digestive doctors (LSD- t=-1.398, P=0.166), and both higher than that of digestive nurses (LSD- t=2.956, P=0.004; LSD- t=5.955, P<0.001) and residents (LSD- t=2.402, P=0.018; LSD- t=4.951, P<0.001). Furthermore, the accuracy was comparable between digestive nurses and residents (LSD- t=-0.574, P=0.567). Compared with new Bing, digestive doctors had lower accuracy in answering questions related to adverse events of screening, follow-up recommendation of intestinal metaplasia, high risk factors and screening methods for colon cancer ( P<0.05), but higher accuracy in answering questions related to endoscopic adverse events and screening methods for esophageal cancer ( P<0.05). Multivariable liner regression analysis showed that being digestive doctors ( β=11.7, t=3.054, P=0.003) and questionnaire response time (≥7.6 min) ( β=7.8, t=2.894, P=0.005) were independent factors for the answer accuracy of digestive healthcare workers. Conclusion:Compared with digestive healthcare workers, New chatbots—new Bing has higher accuracy in answering gastrointestinal cancer screening-related questions, but performs poorly in answering questions such as adverse events of endoscopy and screening methods for esophageal cancer.

Objective:To evaluate the efficacy and safety of endoscopic retrograde cholangiopancreatography (ERCP) after pancreaticoduodenectomy and endoscopic selection strategies.Methods:Clinical data of 34 patients treated with ERCP after pancreaticoduodenectomy at the Endoscopic Center of the First Affiliated Hospital of Air Force Medical University from January 2013 to December 2021 were retrospectively analyzed. The success rates of endoscopic insertion, diagnosis, treatment and ERCP, and the incidence of adverse events were analyzed.Results:Fifty ERCP treatments were performed in 34 patients. The success rates of endoscopic insertion, diagnosis, treatment, and ERCP after pancreaticoduodenectomy were 92.0% (46/50), 93.5% (43/46), 88.4% (38/43) and 76.0% (38/50), respectively. The success rates of ERCP assisted with colonoscope and balloon-assisted enterosocpe were 76.0% (19/25) and 75.0% (18/24), respectively. There were 3 adverse events, including 1 case of anastomotic mucosa tear during surgery, 1 case of cardiopulmonary arrest and 1 case of postoperative cholangitis.Conclusion:ERCP is effective and safe after pancreaticoduodenectomy in general. ERCP assisted with colonoscope and balloon-assisted colonoscope shows similar success rate after pancreaticoduodenectomy.

Objective:To investigate the influence of liver drainage volume on overall survival time in patients with unresectable malignant hilar bile duct obstruction.Methods:Data of 633 patients with unresectable malignant hilar bile duct obstruction (BismuthⅡ-Ⅳ) who underwent endoscopic stent drainage in 3 endoscopy centers from January 2002 to May 2019 were retrospectively analyzed. Main observation indicators included clinical success rate, stent patency, overall survival, the effective liver drainage volume, and complication incidence.Results:The clinical success rates of patients with liver drainage volume <30%, 30%-50%, and >50% were 56.8% (25/44), 77.3% (201/260) and 84.2% (277/329) respectively. The incidences of early cholangitis were 31.8% (14/44), 18.8% (49/260) and 16.1% (53/329). The median stent patency time was 4.5 (95% CI: 1.8-7.2) months, 5.6 (95% CI: 5.0-6.2) months and 6.6 (95% CI: 5.2-8.0) months. The overall survival time was 2.4 (95% CI: 1.8-3.0) months, 4.0 (95% CI: 3.4-4.6) months and 4.9 (95% CI:4.4-5.4) months, respectively. The clinical success rate ( χ 2=8.28, P=0.012), median stent patency period ( χ 2=18.87, P=0.015) and overall survival time ( χ 2=6.93, P=0.024) of 30%-50% liver drainage volume group were significantly higher than those of <30% group. Further multivariate cox regression analysis showed that the disease type (hepatocellular carcinoma VS hilar cholangiocarcinoma: HR=1.50, 95% CI:1.18-1.91, P=0.001; gallbladder carcinoma VS hilar cholangiocarcinoma: HR=1.45, 95% CI:1.14-1.85, P=0.002; metastatic cholangiocarcinoma VS hilar cholangiocarcinoma: HR=1.48, 95% CI:1.08-2.04, P=0.015), bilirubin level >200 μmol/L ( HR=1.35, 95% CI:1.14-1.60, P<0.001),metal stents ( HR=0.67, 95% CI:0.56-0.79, P<0.001), liver drainage volume (volume 30%-50% VS <30%: HR=0.64, 95% CI: 0.45-0.90, P=0.010; volume>50% VS <30%: HR=0.58, 95% CI:0.41-0.81, P=0.002) and anti-tumor therapy ( HR=0.51, 95% CI:0.42-0.61, P<0.001) were independent predictors for overall survival time of patients with unresectable malignant hilar bile duct obstruction. Conclusion:When endoscopic stent drainage is performed for patients with unresectable malignant hilar bile duct obstruction, at least 30% liver volume is required for better overall survival. In addition, the use of metal stent drainage and anti-tumor therapy may increase survival benefits.

Objective:To investigate the risk factors for moderate to severe pancreatitis (PEP) after endoscopic retrograde cholangiopancreatography (ERCP) .Methods:Data of 6 731 patients diagnosed as having biliary and pancreatic diseases with initial papilla who underwent endoscopic retrograde cholangiopancreatography (ERCP) from June 2010 to June 2020 in the First Affiliated Hospital of Air Force Medical University were retrospectively analyzed. Parameters related to intubation and postoperative complications were prospectively collected. The main end point was moderate to severe PEP. Logistic regression analysis was used to explore the risk factors for moderate to severe PEP.Results:The incidence of overall PEP and moderate to severe PEP in 6 731 ERCP patients with initial papilla were 5.3% ( n=359) and 1.0% ( n=68) respectively. Univariate analysis showed that female, indications of ERCP, cannulation method, cannulation time, cannulation attempts, times of inadvertent pancreatic duct cannulation and cannulation with or without trainee involvement were all associated with moderate to severe PEP ( P<0.10). Multivariate analysis showed that female ( OR=2.32, 95% CI:1.28-4.21, P=0.006), non-common bile duct stones indication ( OR=2.04, 95% CI:1.16-3.59, P=0.014), cannulation time ≥5 min ( OR=2.23, 95% CI: 1.20-4.13, P=0.011), inadvertent pancreatic duct cannulation time ≥1 ( OR=1.88, 95% CI: 1.03-3.44, P=0.040) and non-trainee involvement cannulation ( OR=1.81, 95% CI: 1.02-3.22, P=0.043) were independent risk factors for moderate to severe PEP. Conclusion:The independent risk factors for moderate to severe PEP include female, non-common bile duct stones indication, non-trainee involvement cannulation and difficult cannulation. Great importance should be attached to these factors above during the whole perioperative period of ERCP.

Objective:To compare the bile bacterial diversity in patients with different types of common bile duct stones (CBDS).Methods:A total of 45 patients with CBDS diagnosed by abdominal ultrasound, abdominal CT and (or) magnetic resonance cholangiopancreatography (MRCP) and treated by endoscopic retrograde cholangiopancreatography (ERCP) in the First Affiliated Hospital of Air Force Medical University from August 2017 to January 2018 were divided into the non-stone (NS) group, the primary cholesterol stone (PCS) group, the primary pigment stone (PPS) group, and the recurrent stone (RS) group. 16S rRNA sequencing was used to analyze the microbile community structure and diversity in bile which was collected before contrast medium injection.Results:Thirty-three patients were in the non-RS group (8 in the NS group, 8 in the PCS group, and 17 in the PPS group) and 12 were in the RS group. The proportion of patients with intra-diverticular papilla [41.67% (5/12) VS 3.03% (1/33), χ2=8.27, P=0.004], loose stones [91.67% (11/12) VS 36.36% (12/33), χ2=10.77, P=0.001] and pigmental stones [100.00% (12/12) VS 51.52% (17/33), χ2=7.04, P=0.008] were significantly higher in the RS group than those in the non-RS group. There was no significant difference in other baseline data ( P>0.05). At the phylum and genus level, the bacterial abundance was similar in the RS and PPS group. Alpha and Beta diversity analysis showed that the microbial diversity was similar between the RS and PPS group, both of which were lower than those in the NS and PCS group ( P<0.05). MetaStat analysis revealed that Helicobacter pylori was the dominant bacteria in the RS group, and Proteobacteria and Escherichia coli were the dominant bacteria in both RS and PPS groups. Conclusion:Bacterial abundance of bile in the RS group is similar to that of the PPS group, but the diversity of biliary bacteria flora in the RS group and PPS group are significantly lower than those in the PCS group and NS group. Helicobacter pylori is the dominant biliary bacteria in the RS group.

Objective:To investigate the outcome and prognostic factors associated with endoscopic retrograde cholangiopancreatography (ERCP) in patients with primary sclerosing cholangitis (PSC).Methods:PSC patients admitted to Xijing Hospital from May 2009 to May 2020 were included. Data of demographics, clinical symptoms, laboratory and imaging tests, and ERCP consultations were collected to explore the population characteristics and clinical efficacy of ERCP treatment, and to follow up disease progression, transplant-free survival, and overall survival .Results:A total of 74 patients with PSC were included in this study, with a median age of 53 years, 54.1% (40/74) male. Patients combined with bile duct dominant stenosis, inflammatory bowel disease (IBD), and another autoimmune liver disease were 32.4% (24/74), 18.9% (14/74), and 17.6% (13/74), respectively, and those undergoing ERCP were 36.5% (27/74). Logistic regression analysis showed that high total bilirubin ( OR=12.33, 95% CI: 1.24-122.63, P=0.032) and bile duct dominant stenosis ( OR=24.67, 95% CI: 3.40-178.88, P=0.002) were independent high-risk factors for ERCP consultation. The operation and clinical success rates of ERCP were both 96.3% (26/27). As of the last follow-up, the proportions of patients progressing to cirrhosis, bile duct cancer, liver transplantation and death were 9.5% (7/74), 4.1% (3/74), 5.4% (4/74) and 18.9% (14/74), respectively. The five-year survival rate of the follow-up patients ( n=54) was 83.3%. The differences in transplant-free survival ( P=0.933) and overall survival ( P=0.608) between ERCP patients and non-ERCP patients were not statistically significant. Transplant-free survival of those who were companied with pruritus ( HR=5.30, 95% CI: 1.50-18.90, P=0.010) was shorter. Conclusion:PSC patients have higher proportion of IBD and less autoimmune liver disease. Higher proportion of patients with higher total bilirubin or bile duct dominant stenosis receive ERCP. While the short-term efficacy of ERCP is satisfactory, the long-term prognosis is still suboptimal. Patients with pruritus have a shorter transplant-free survival.