Objective Focusing on gynecological surgery,we constructed a prediction model for surgical duration by extracting features from unstructured surgical planning texts and integrating multimodal data via artificial intelligence technology.Methods The clinical data of 34 614 patients who underwent gynecologic surgeries at West China Second University Hospital,Sichuan University between January 2022 and October 2024 were collected.An embedding-transformer model was constructed to convert surgical planning texts into a one-dimensional numerical feature,referred to as the step feature.The predictive value of the step feature was assessed by comparing the performance improvements of linear regression,random forest,eXtreme Gradient Boosting(XGBoost),support vector regression,K-nearest neighbor regression,and artificial neural network algorithms in two scenarios—with and without the step feature as an input.The out-of-sample prediction accuracy of the models was assessed using mean absolute error(MAE),root mean squared error(RMSE),and R-squared(R2).Furthermore,the model interpretability was examined using SHapley Additive exPlanations(SHAP)values.Results SHAP results showed that the step feature had the highest predictive contribution.Temporal factors in surgical scheduling also influenced gynecological surgery duration.The XGBoost model demonstrated optimal performance on the test set,significantly improving prediction accuracy with a 40.43%increase in R2,while reducing MAE and RMSE by 21.27%and 20.13%,respectively,compared to the baseline model without the step feature.Conclusion The embedding-transformer model developed in this study effectively extracts features from surgical planning texts and enhances the predictive performance of machine learning models.The XGBoost prediction model can assist hospital administrators in implementing more refined management of gynecological surgeries and improving the utilization efficiency of surgical resources.

Objective:To explore the risk factors for urethral stricture after transperineal anastomotic urethroplasty (TAU) by retrospectively analyzing patient data and to develop a nomogram to predict the risk of recurrence before the surgery.Methods:Clinical data of patients who underwent TAU because of post-traumatic urethral stricture from January 2016 to December 2017 in West China Hospital, Sichuan University were reviewd. A total of 78 patients were included in the retrospective analysis, with 13 of them having recurrence. The patients in the recurrence group had a median age of 49.8 and 76.9% (10/13) of them had membranous urethral stricture. The proximal urethra end was located above the superior margin of the pubic ramus (higher stricture site) in 53.8%(7/13)of patients in the recurrence group and the length of the stricture measured in the operation was (2.19±0.22) cm. In the non-recurrence group, the median age was (44.8±13.6) years old, 58.5% (38/65) of them had membranous urethral stricture, 21.5% (14/65) had higher stricture site, and the length of the stricture was (2.03±0.11) cm. Both univariate and multivariate logistics analyses were performed to evaluate the risk factors of recurrence of urethral stricture 5 years after surgery. The nomogram was built based on the multivariate logistics analysis. The Concordance Index (C-index), Receiver Operating Characteristic(ROC) curve and Calibration curve were used to evaluate the nomogram.Results:Univariate logistics analysis showed that higher stricture site, history of urethral dilation, smoking, diabetes and total serum protein may be associated with recurrence after surgery. Multivariate logistics analysis further confirmed that higher stricture site ( OR=34.64, 95% CI 3.71-754.53), history of urethral dilation( OR=13.15, 95% CI 1.27-210.00), smoking ( OR=13.75, 95% CI 2.15-166.05) and diabetes ( OR=64.98, 95% CI 3.80-1957.60) were independent risk factors for recurrent urethral stricture while higher total serum protein before surgery was related to lower recurrence risk ( OR=0.78, 95% CI 0.62-0.93). A nomogram was built based on the results. The C-index of the nomogram was 0.923(95% CI 0.908-0.938), the area under curve (AUC) was 0.923 (95% CI 0.855-0.991), and the Brier Score was 0.079. Conclusion:Higher stricture site, history of urethral dilation before surgery, smoking, diabetes and lower total serum protein before surgery are associated with higher recurrence TAU of post-traumatic urethral stricture patients. With the nomogram developed, prediction of the risk of recurrence could be achieved prior surgery.

OBJECTIVE:To establish a method for simultaneous determination of gallic acid,magnoflorine,ellagic acid,jatrorrhizine hydrochloride,palmatine hydrochloride,berberine hydrochloride and curcumin in Siwei jianghuang decoction powder.METHODS:HPLC method was adopted.The determination was performed on Capcell Pak C18-MG Ⅱ column with mobile phase consisted of acetonitrile-0.1％ phosphoric acid (gradient elution) at the flow rate of 0.8 mL/min.The detection wavelengths were 270 nm (0-60 min,gallic acid,magnoflorine,ellagic acid,jatrorrhizine hydrochloride,palmatine hydrochloride,berberine hydrochloride) and 428 nm (60-70 min,curcumin).The column temperature was set at 30 ℃,and sample size was 10 μL.RESULTS:The linear ranges of gallic acid,magnoflorine,ellagic acid,jatrorrhizine hydrochloride,palmatine hydrochloride,berberine hydrochloride and curcumin were 0.249 6-1.497 6,0.284 0-1.704 0,0.075 6-0.453 6,0.015 9-0.095 9,0.023 6-0.141 6,0.098 2-0.589 0 and 0.060 4-0.362 4 μtg (r≥0.999 8).The limits of detection were 6.24,4.73,7.56,2.36,3.20,6.54,6.04 ng,and the limits of quantitation were 17.47,16.08,20.86,7.31,10.24,19.62,19.32 ng,respectively.RSDs of precision,stability (12 h),reproducibility tests were lower than 2.0％ (n=6).The recoveries were 95.45％-103.47％ (RSD=0.86％-1.98％,n=9).CONCLUSIONS:Established method is simple,accurate,reliable and suitable for simultaneous determination of 7 components such as gallic acid in Siwei jianghuang decoction powder.

OBJECTIVE:To optimize extraction technology of cortex of Berberis dictyophylla by ethanol. METHODS:Using the contents of magnoflorine,jatrorrhizine hydrochloride,palmatine hydrochloride and berberine hydrochloride,the amount of extract as evaluation indexes,the effects of ethanol amount,volume fraction of ethanol and extraction time on extraction technology were investigated by uniform design method-comprehensive scoring method. The extraction methods of first time, second time and third time were investigated by 3 times of uniform design test. The optimal schemes of 3 times of extraction test were determined and validation test was conducted,and the transfer rates were calculated. RESULTS:The optimal technology was as follows as coarse powder of cortex of B. dictyophylla,15-fold 75% ethanol,extracting for 2 times,120 min each time. In validation test,the contents of magnoflorine,jatrorrhizine hydrochloride,palmatine hydrochloride and berberine hydrochloride were 58.96,4.82,3.07,23.29 mg/g after B. dictyophylla was extracted by optimization technology for 2 times. The transfer rates were 93.85%,95.02%,96.28%,94.88%,respectively(RSD=3.87%,2.64%,4.00%,3.91%,n=3). CONCLUSIONS:The optimal ethanol reflux extraction technology of cortex of B.dictyophylla is reasonable and feasible with good stability.

OBJECTIVE: To observe the expression changes of metadherin (MTDH) and matrix metalloproteinase-9 (MMP-9) in the laryngeal squamous cell carcinoma tissues and to investigate the significance. METHOD: The expression of MTDH and MMP-9 in 54 cases of laryngeal squamous cell carcinoma tissues(observation group) and 30 cases of para-carcinoma tissues (control group) was examined by immunohistochemical method, the correlation between them and their correlations with the clinicopathological parameters were analyzed. RESULT: The positive expression rates of MTDH in the observation group and control group were 64.8% (35/54) and 6.7% (2/30), respectively; the positive expression rates of MMP-9 in the observation group and control group were 70.4% (38/ 54) and 13.3% (4/30), respectively; and there was a statistically significant difference between two groups (all P < 0.01). In the laryngeal squamous cell carcinoma tissues, the expression of MTDH protein was related with degree of differentiation, lymph-node metastasis and TNM stage (all P < 0.05); and the expression of MMP-9 protein was related lymph-node metastasis and TNM stage (all P < 0.05). The expression of MTDH was positively correlated with MMP-9 in the laryngeal squamous cell carcinoma tissues (r = 0.371, P < 0.01). CONCLUSION The high expression of MTDH and MMP-9 was closely related to the occurrence, development and metastasis of laryngeal squamous cell carcinoma, joint detection of the two proteins was valuable for early diagnosis and prognosis of laryngeal squamous cell carcinoma.
Carcinoma, Squamous Cell ; diagnosis ; metabolism ; Case-Control Studies ; Cell Adhesion Molecules ; metabolism ; Cell Differentiation ; Head and Neck Neoplasms ; diagnosis ; metabolism ; Humans ; Laryngeal Neoplasms ; diagnosis ; metabolism ; Lymphatic Metastasis ; Matrix Metalloproteinase 9 ; metabolism ; Neoplasm Staging ; Prognosis ; Squamous Cell Carcinoma of Head and Neck