Objective To explore the effectiveness of the generative large language model MedGo in nursing decision-making for elderly patients with multimorbidity. Methods A quasi-randomized controlled trial study was conducted involving 6 junior nurses, 6 senior nurses and the MedGo model from January 1, 2025 to March 31, 2025 at the Emergency Internal Medicine Ward of Shanghai East Hospital Affiliated to Tongji University. Clinical data of 120 elderly patients with multimorbidity were analyzed to compare the performance of the three groups in four tasks (nursing diagnosis assessment, nursing intervention formulation, complication identification, and complication prevention) from three evaluation dimensions: decision-making time consumption, decision accuracy, and decision-making quality. Results In terms of decision-making time, the senior nurse group completed all four tasks faster than the junior nurse group (P＜0.01), and the MedGo group completed all four tasks faster than the junior nurse group (P＜0.001) and the senior nurse group (P＜0.001). In terms of decision-making accuracy, senior nurse group scored higher than junior nurse group in all four tasks (P＜0.001), while the MedGo group outperformed the senior nurse group only in complication identification (P＜0.001). In terms of decision-making quality, the MedGo group scored higher than junior nurse group (P＜0.001) and senior nurse group (P＜0.001) in all four tasks. Conclusions The MedGo model demonstrates advantages of high efficiency, accuracy, and quality in nursing decision-making for elderly patients with multimorbidity; senior nurses outperform junior nurses in decision-making, providing diverse references for clinical nursing decision-making.

AIM:To evaluate the optimal timing of preoperative intravitreal anti vascular endothelial growth factor(VEGF)therapy in proliferative diabetic retinopathy(PDR)using intraoperative fluorescein angiography(IOFA).METHODS:A retrospective case series study was conducted on patients who underwent vitrectomy for PDR with vitreous hemorrhage(VH)at Sichuan Provincial People's Hospital from January 2023 to February 2025. Patients were divided into three groups according to the interval between intravitreal conbercept injection and surgery: Group A(3 d before surgery), Group B(7 d before surgery), and Group C(14 d before surgery). IOFA was used to assess the number and size of retinal neovascularization(NV). Additional data were collected including preoperative best corrected visual acuity(BCVA), vitreous hemorrhage grading, operative time, frequency of intraoperative endodiathermy, duration of high perfusion pressure, vitreoretinal adhesion grade, postoperative BCVA, and central macular thickness(CMT). Multidimensional analyses were performed.RESULTS:This study enrolled a total of 91 patients(94 eyes)with PDR accompanied by vitreous hemorrhage. Among them, Group A consisted of 31 patients(31 eyes; 18 males, 13 females; mean age 53.26±12.38 y), Group B consisted of 34 patients(37 eyes; 21 males, 13 females; mean age 51.61±14.16 y), and Group C consisted of 26 patients(26 eyes; 18 males, 8 females; mean age 51.00±12.02 y), with baseline characteristics comparable among the three groups(all P>0.05). Comparative analysis of NV visualized via IOFA revealed that both the number and size of NVs were significantly lower in Groups B and C than in Group A(all P<0.0167), while no statistically significant differences were observed between Groups B and C(both P>0.05). No significant differences were found among the three groups regarding other intraoperative parameters, including operation time, frequency of electrocoagulation application, duration of high perfusion pressure, or grading of vitreoretinal adhesion(all P>0.05).CONCLUSION:IOFA confirms that preoperative anti-VEGF therapy administered 7 or 14 d before surgery is more effective than a 3 d interval in suppressing retinal NV activity in PDR patients.

OBJECTIVE To evaluate the long-term cost-effectiveness of insulin degludec and insulin aspart （IDegAsp） in patients with type 2 diabetes mellitus （T2DM） in China. METHODS A cost-effectiveness analysis was conducted from the perspective of the Chinese healthcare system， using the CORE diabetes model to simulate long-term （20-year） health and economic outcomes. Baseline cohort characteristics and treatment effect data were derived from the CREATE study. The prices of glucose- lowering drugs were obtained from medical insurance payment standards and the average winning bid prices in the follow-up round of the specialized centralized procurement for insulin， while the daily dosages were derived from the CREATE study. The costs of complications and utility values were obtained from published literature， with a discount rate of 5%. One-way sensitivity analysis， scenario analysis， and probabilistic sensitivity analysis were performed to verify the robustness of the results. RESULTS Patients switching from previous once-daily basal insulin regimens to IDegAsp therapy gained an incremental 0.190 quality-adjusted life year （QALY） with direct medical cost savings of 42 163.58 yuan. For those switching from premixed insulin therapies， IDegAsp treatment provided 0.130 incremental QALY and reduced direct healthcare costs by 41 129.11 yuan. The outcome was significantly influenced by the discount rate and the cost of complications. Probabilistic sensitivity analysis and scenario analysis confirmed the robustness of these findings. CONCLUSIONS Switching from previous daily basal insulin or premixed insulin regimens to IDegAsp in Chinese patients with T2DM can improve patients’ long-term health outcomes and achieve cost savings， making it a more cost-effective treatment option.

Objective:To propose a preliminary method for real-time assessment of pilot situational awareness based on assessing pilot′s visual gaze behavior during spatial orientation flight simulation.Methods:Fighter pilots who met the criteria were randomly selected by drawing lots. An eye-tracker was used to collect eye-track feature data from pilots in a flight simulator. The lightweight YOLOv8n model was used to detect the area of interest (AOI) in the training to construct the AOI gaze sequence feature data. The pilot′s illusory experiences and recovery from complex situations were recorded, and those were scored by the situation awareness global assessment technique to obtain such 3 situational awareness assessment levels as excellent, good, and fair which were used as labeled data. A transformer and inception module fusion situation awareness (Ti-SA) model was developed to extract and learn the features of eye-tracking time-series data and AOI gaze time-series data and was compared with other commonly used models in the field of multidimensional time-series classification.Results:Thirty fighter pilots were enrolled, all male, aged 23-38 years old, with flying hours of 300-2 200 h, were included in the study. Nineteen temporal features of pilots′ eye movement trajectories were obtained by eye-tracker. By situation awareness global assessment, 12 pilots were scored to excellent level, 15 to good level and 3 to fair level. When Ti-SA model was applied to the experimental dataset, the accuracy was 92.18%, the precision was 92.95%, the recall was 95.49%, and the F1 score was 94.20%, which were better than other commonly used models in the field of multidimensional time-series classification.Conclusions:The study indicates that the proposed dataset construction method and Ti-SA model can effectively assess the level of pilot situational awareness in spatial orientation flight simulation.

The seventy-two grid palm technique is an important theoretical source of traditional Chinese medicine hand diagnosis. Starting from the ecological medical model， we analyse the seventy-two grid palm technique， and believe that its diagnosis of human body integrates biological， ecological， psychological， social and other factors， and each factor is based on physiological and pathological theories， and its external social interpretation of the nature of the human body is inseparable from health state. It is proposed that the seventy-two grid palm technique should be integrated with the ecological and natural viewpoints based on the biomedical models or bio-psycho-social medical models， and the research should be conducted from the perspective of the ecological medical model， in order to promote the development of hand diagnosis.

Objective:To establish a predictive model of the first cesarean delivery in multiparous women based on the situation of two consecutive pregnancies.Methods:The data of patients with two consecutive deliv-eries of single live birth and the previous delivery was vaginal delivery in the First Affiliated Hospital of Soochow U-niversity during the second delivery time range from January 1,2018 to December 31,2021 were retrospectively analyzed.According to whether the second pregnancy occurred cesarean section,the patients were divided into two groups(vaginal delivery group and cesarean section group).Univariate,stepwise,and multiple Logistic re-gression analyses were used to screen the influencing factors of multipara's first cesarean section delivery,and the prediction model was established.R language was used to build the model's nomogram and calibration curve.The bootstrap resampling method was used for internal verification.After establishing the model,clinical data of patients with two consecutive births of single live birth between January 1,2022 and April 1,2023 were retrospec-tively collected for external verification of the model.Results:①A total of 2709 patients were included in this study for modeling,of which 6.31％(171/2709)underwent cesarean section for the first time.603 cases were included for external verification.②According to univariate,stepwise and multivariate Logistic regression analysis,all the variables affecting the first delivery by cesarean section were screened out,including:abnormal labor in previous labor,age of current delivery,assisted reproductive technology,hypertension disorder complicating pregnancy,pregnancy with thrombocytopenia,oligohydramnios,excessive amniotic fluid,macrosomia,fetal growth restriction,abnormal fetal position,fetal distress,all of the above variables P＜0.05 and incorporated into the final prediction model.③The AUC of this model was 0.949(95％CI 0.928-0.969),and the calibration curve showed that the model intercept was 0 and the slope was 1.Hosmer-Lemeshow test had a P＞0.05,indicating that the model had a high accuracy.④The AUC of external validation was 0.958,the slope of the calibration curve was 0.972,and the Hosmer-Lemeshow test had a P of 0.49.Conclusions:The prediction model of the first delivery by cesarean section during the second pregnancy has been established.The prediction efficiency of the model is good,and it can provide a tool for the individualized evaluation of menstrual women in clinical work.

Objective:To establish a predictive model of the first cesarean delivery in multiparous women based on the situation of two consecutive pregnancies.Methods:The data of patients with two consecutive deliv-eries of single live birth and the previous delivery was vaginal delivery in the First Affiliated Hospital of Soochow U-niversity during the second delivery time range from January 1,2018 to December 31,2021 were retrospectively analyzed.According to whether the second pregnancy occurred cesarean section,the patients were divided into two groups(vaginal delivery group and cesarean section group).Univariate,stepwise,and multiple Logistic re-gression analyses were used to screen the influencing factors of multipara's first cesarean section delivery,and the prediction model was established.R language was used to build the model's nomogram and calibration curve.The bootstrap resampling method was used for internal verification.After establishing the model,clinical data of patients with two consecutive births of single live birth between January 1,2022 and April 1,2023 were retrospec-tively collected for external verification of the model.Results:①A total of 2709 patients were included in this study for modeling,of which 6.31％(171/2709)underwent cesarean section for the first time.603 cases were included for external verification.②According to univariate,stepwise and multivariate Logistic regression analysis,all the variables affecting the first delivery by cesarean section were screened out,including:abnormal labor in previous labor,age of current delivery,assisted reproductive technology,hypertension disorder complicating pregnancy,pregnancy with thrombocytopenia,oligohydramnios,excessive amniotic fluid,macrosomia,fetal growth restriction,abnormal fetal position,fetal distress,all of the above variables P＜0.05 and incorporated into the final prediction model.③The AUC of this model was 0.949(95％CI 0.928-0.969),and the calibration curve showed that the model intercept was 0 and the slope was 1.Hosmer-Lemeshow test had a P＞0.05,indicating that the model had a high accuracy.④The AUC of external validation was 0.958,the slope of the calibration curve was 0.972,and the Hosmer-Lemeshow test had a P of 0.49.Conclusions:The prediction model of the first delivery by cesarean section during the second pregnancy has been established.The prediction efficiency of the model is good,and it can provide a tool for the individualized evaluation of menstrual women in clinical work.

Objective:To establish a predictive model of the first cesarean delivery in multiparous women based on the situation of two consecutive pregnancies.Methods:The data of patients with two consecutive deliv-eries of single live birth and the previous delivery was vaginal delivery in the First Affiliated Hospital of Soochow U-niversity during the second delivery time range from January 1,2018 to December 31,2021 were retrospectively analyzed.According to whether the second pregnancy occurred cesarean section,the patients were divided into two groups(vaginal delivery group and cesarean section group).Univariate,stepwise,and multiple Logistic re-gression analyses were used to screen the influencing factors of multipara's first cesarean section delivery,and the prediction model was established.R language was used to build the model's nomogram and calibration curve.The bootstrap resampling method was used for internal verification.After establishing the model,clinical data of patients with two consecutive births of single live birth between January 1,2022 and April 1,2023 were retrospec-tively collected for external verification of the model.Results:①A total of 2709 patients were included in this study for modeling,of which 6.31％(171/2709)underwent cesarean section for the first time.603 cases were included for external verification.②According to univariate,stepwise and multivariate Logistic regression analysis,all the variables affecting the first delivery by cesarean section were screened out,including:abnormal labor in previous labor,age of current delivery,assisted reproductive technology,hypertension disorder complicating pregnancy,pregnancy with thrombocytopenia,oligohydramnios,excessive amniotic fluid,macrosomia,fetal growth restriction,abnormal fetal position,fetal distress,all of the above variables P＜0.05 and incorporated into the final prediction model.③The AUC of this model was 0.949(95％CI 0.928-0.969),and the calibration curve showed that the model intercept was 0 and the slope was 1.Hosmer-Lemeshow test had a P＞0.05,indicating that the model had a high accuracy.④The AUC of external validation was 0.958,the slope of the calibration curve was 0.972,and the Hosmer-Lemeshow test had a P of 0.49.Conclusions:The prediction model of the first delivery by cesarean section during the second pregnancy has been established.The prediction efficiency of the model is good,and it can provide a tool for the individualized evaluation of menstrual women in clinical work.

Objective:To establish a predictive model of the first cesarean delivery in multiparous women based on the situation of two consecutive pregnancies.Methods:The data of patients with two consecutive deliv-eries of single live birth and the previous delivery was vaginal delivery in the First Affiliated Hospital of Soochow U-niversity during the second delivery time range from January 1,2018 to December 31,2021 were retrospectively analyzed.According to whether the second pregnancy occurred cesarean section,the patients were divided into two groups(vaginal delivery group and cesarean section group).Univariate,stepwise,and multiple Logistic re-gression analyses were used to screen the influencing factors of multipara's first cesarean section delivery,and the prediction model was established.R language was used to build the model's nomogram and calibration curve.The bootstrap resampling method was used for internal verification.After establishing the model,clinical data of patients with two consecutive births of single live birth between January 1,2022 and April 1,2023 were retrospec-tively collected for external verification of the model.Results:①A total of 2709 patients were included in this study for modeling,of which 6.31％(171/2709)underwent cesarean section for the first time.603 cases were included for external verification.②According to univariate,stepwise and multivariate Logistic regression analysis,all the variables affecting the first delivery by cesarean section were screened out,including:abnormal labor in previous labor,age of current delivery,assisted reproductive technology,hypertension disorder complicating pregnancy,pregnancy with thrombocytopenia,oligohydramnios,excessive amniotic fluid,macrosomia,fetal growth restriction,abnormal fetal position,fetal distress,all of the above variables P＜0.05 and incorporated into the final prediction model.③The AUC of this model was 0.949(95％CI 0.928-0.969),and the calibration curve showed that the model intercept was 0 and the slope was 1.Hosmer-Lemeshow test had a P＞0.05,indicating that the model had a high accuracy.④The AUC of external validation was 0.958,the slope of the calibration curve was 0.972,and the Hosmer-Lemeshow test had a P of 0.49.Conclusions:The prediction model of the first delivery by cesarean section during the second pregnancy has been established.The prediction efficiency of the model is good,and it can provide a tool for the individualized evaluation of menstrual women in clinical work.

Objective:To establish a predictive model of the first cesarean delivery in multiparous women based on the situation of two consecutive pregnancies.Methods:The data of patients with two consecutive deliv-eries of single live birth and the previous delivery was vaginal delivery in the First Affiliated Hospital of Soochow U-niversity during the second delivery time range from January 1,2018 to December 31,2021 were retrospectively analyzed.According to whether the second pregnancy occurred cesarean section,the patients were divided into two groups(vaginal delivery group and cesarean section group).Univariate,stepwise,and multiple Logistic re-gression analyses were used to screen the influencing factors of multipara's first cesarean section delivery,and the prediction model was established.R language was used to build the model's nomogram and calibration curve.The bootstrap resampling method was used for internal verification.After establishing the model,clinical data of patients with two consecutive births of single live birth between January 1,2022 and April 1,2023 were retrospec-tively collected for external verification of the model.Results:①A total of 2709 patients were included in this study for modeling,of which 6.31％(171/2709)underwent cesarean section for the first time.603 cases were included for external verification.②According to univariate,stepwise and multivariate Logistic regression analysis,all the variables affecting the first delivery by cesarean section were screened out,including:abnormal labor in previous labor,age of current delivery,assisted reproductive technology,hypertension disorder complicating pregnancy,pregnancy with thrombocytopenia,oligohydramnios,excessive amniotic fluid,macrosomia,fetal growth restriction,abnormal fetal position,fetal distress,all of the above variables P＜0.05 and incorporated into the final prediction model.③The AUC of this model was 0.949(95％CI 0.928-0.969),and the calibration curve showed that the model intercept was 0 and the slope was 1.Hosmer-Lemeshow test had a P＞0.05,indicating that the model had a high accuracy.④The AUC of external validation was 0.958,the slope of the calibration curve was 0.972,and the Hosmer-Lemeshow test had a P of 0.49.Conclusions:The prediction model of the first delivery by cesarean section during the second pregnancy has been established.The prediction efficiency of the model is good,and it can provide a tool for the individualized evaluation of menstrual women in clinical work.