Objective To develop and validate a machine learning model integrating serum tumor markers with multiparametric magnetic resonance imaging(mpMRI)-derived scores for discriminating prostate cancer(PCa)from benign prostatic hyperplasia(BPH)in men with a total prostate-specific antigen(tPSA)of 4-10 ng/mL, so as to optimize prostate biopsy decisions. Methods A retrospective analysis was conducted on the clinical data of 85 PCa patients and 204 BPH patients treated in our hospital during Jan. 2022 and May 2025. All patients underwent prostate biopsy to obtain the pathological results. The data collected were analyzed using univariate and multivariate logistic regression to determine the independent risk factors for PCa. Model performance was assessed in terms of discrimination, calibration, and clinical utility using receiver operating characteristic(ROC)curves, calibration plots, and decision curve analysis(DCA). A classification and regression tree(CART)algorithm was further developed to derive biopsy decision rules. The area under the ROC curve(AUC)of the logistic and CART models were compared to select the optimal predictive model, which was subsequently visualized using SHAP values. Results Age, free prostate-specific antigen(fPSA), fPSA/tPSA(f/tPSA)ratio, and Prostate Imaging-Reporting and Data System(PI-RADS)scores differed significantly between the PCa and BPH groups(P＜0.05). Univariate and multivariate logistic regression identified age, f/tPSA ratio, and PI-RADS scores as independent influencing factors(P＜0.05). A logistic model incorporating these variables achieved an AUC of 0.785(95%CI:0.724-0.846, P＜0.05), with a sensitivity of 70.6% and specificity of 77.9%. The model showed excellent calibration. DCA indicated a positive net benefit when the risk threshold exceeded 7%. The CART model yielded an AUC of 0.769(95%CI:0.717-0.821), with the sensitivity of 63.5% and specificity of 79.9%. Within threshold probabilities of 5%-56%, the CART model provided higher net benefit. When the risk threshold reached 55%, the number of diagnosed cases of PCa began to converge with the actual number. Conclusion Compared with the CART model, the logistic model based on f/tPSA, PI-RADS score and age has a higher diagnostic efficacy for PCa and is the optimal model.

Object:To explore the feasibility of using artificial intelligence for quality control of echocardiographic images.Methods:Retrospectively，5 000 two-dimensional echocardiographic video images within the period from 2021 to 2023 were randomly retrieved from the echocardiography database of Nanjing Drum Tower Hospital，Affiliated Hospital of Medical School，Nanjing University. Among these selected images，1 559 of them were apical views. The physician team formulated the scoring rules，which specifically included four scoring criteria：gain，scaling ratio，cardiac axis angle，and structure. Subsequently，the data were labeled with view classification and image quality scores. The labeled data were further partitioned into the training set（ n = 643），the validation set（ n = 276），and the test set（ n = 640）. The training and validation sets were utilized for constructing the models for view classification and quality assessment，while the test set was employed to verify the models' effectiveness. The view classification module was implemented using the SlowFast model，and the quality assessment module involved algorithms such as ResNet，Video Swin Transformer，SSD，and U-Net. Results:The average accuracy，precision，recall rate and F1 score of the classification model in identifying each apical view were 0.987 1，0.983 0，0.987 1 and 0.984 9 respectively，and the inference time was（333.4 ± 105.4）ms. The average accuracies of the quality assessment module in terms of gain，scaling ratio，cardiac axis angle and display of main structures were 0.915 1，0.928 2，0.938 7 and 0.965 6 respectively，and the overall scoring accuracy was 0.912 7.Conclusions:The echocardiogram quality control system developed in this research can effectively classify and evaluate the quality of two-dimensional images of the apical views in echocardiograms. Moreover，it guarantees the objectivity，timeliness and high-efficiency of quality control，which has reference value for the establishment of the echocardiogram quality control system.

Object:To explore the feasibility of using artificial intelligence for quality control of echocardiographic images.Methods:Retrospectively，5 000 two-dimensional echocardiographic video images within the period from 2021 to 2023 were randomly retrieved from the echocardiography database of Nanjing Drum Tower Hospital，Affiliated Hospital of Medical School，Nanjing University. Among these selected images，1 559 of them were apical views. The physician team formulated the scoring rules，which specifically included four scoring criteria：gain，scaling ratio，cardiac axis angle，and structure. Subsequently，the data were labeled with view classification and image quality scores. The labeled data were further partitioned into the training set（ n = 643），the validation set（ n = 276），and the test set（ n = 640）. The training and validation sets were utilized for constructing the models for view classification and quality assessment，while the test set was employed to verify the models' effectiveness. The view classification module was implemented using the SlowFast model，and the quality assessment module involved algorithms such as ResNet，Video Swin Transformer，SSD，and U-Net. Results:The average accuracy，precision，recall rate and F1 score of the classification model in identifying each apical view were 0.987 1，0.983 0，0.987 1 and 0.984 9 respectively，and the inference time was（333.4 ± 105.4）ms. The average accuracies of the quality assessment module in terms of gain，scaling ratio，cardiac axis angle and display of main structures were 0.915 1，0.928 2，0.938 7 and 0.965 6 respectively，and the overall scoring accuracy was 0.912 7.Conclusions:The echocardiogram quality control system developed in this research can effectively classify and evaluate the quality of two-dimensional images of the apical views in echocardiograms. Moreover，it guarantees the objectivity，timeliness and high-efficiency of quality control，which has reference value for the establishment of the echocardiogram quality control system.

OBJECTIVE To investigate ameliorative effects and mechanisms of two probiotics(Bacillus subtilis,Lactobacillus acidophilus)combined with Aurantii Fructus Immaturus(AFI)on functional dyspepsia(FD)in rats.METHODS Rats were randomly divided into blank group,model group,positive control group(domperidone group,2.7 mg/kg),AFI group(9 g/kg),L.acidophilus group(5×107 cfu/kg),B.subtilis group(5×107 cfu/kg),L.acidophilus+AFI group(L.acidophilus 5×107 cfu/kg+AFI 9 g/kg),and B.subtilis+AFI group(B.subtilis 5×107 cfu/kg+AFI 9 g/kg),with 8 rats in each group.Except for the blank group,FD model was established by tail-clamping stimulation+hunger and satiety disorder+swimming exhaustion in other groups.After modeling,each group was given the corresponding drug/probiotic suspensions/physiological saline intragastrically,once a day,for 14 consecutive days.After the last medication,gastric emptying rate and the rate of propulsion of the small intestine in rats were measured;the levels of brain-gut peptide-related indicators[gastrin(GAS),substance P(SP),vasoactive intestinal peptide(VIP),somatostatin(SS)and cholecystokinin(CCK)]in the serum of rats were measured.The pathological morphology of the gastric antrum tissue and duodenal tissue was observed.Cecal contents from the rats were collected for gut microbiota sequencing analysis.The protein expression levels of tyrosine kinase receptor c-Kit and stem cell factor(SCF)in the gastric antrum tissue,as well as Toll-like receptor 4(TLR4),myeloid differentiation factor 88(MyD88),and nuclear factor κB(NF-κB)in the duodenal tissue of the rats were detected.RESULTS Compared with the blank group,model group showed significantly lower gastric emptying rate,small intestinal propulsion rate,serum levels of GAS and SP,relative abundance of Firmicutes,Ace,Chao and Sobs indexes of the gut microbiota,and protein levels of SCF and c-Kit in gastric antrum(P＜0.05),while serum levels of VIP,SS and CCK,relative abundance of Bacteroidetes,as well as protein expressions of TLR4,MyD88,and NF-κB,were significantly higher(P＜0.05).The histological structure of the gastric antrum tissue appeared basically normal;however,abnormalities were observed in the duodenal structure,with a significant infiltration of inflammatory cells visible.Compared with the model group,all treatment groups significantly modulated most of the above indexes(P＜0.05).The histological structure of the gastric antrum tissue was normal.Except for the B.subtilis group and the B.subtilis+AFI group,the pathological states of the duodenum in the remaining rats gradually recovered.Compared with each single drug group,most of above indexes in rats from each combination group showed further improvement(P＜0.05).CONCLUSIONS The combination of AFI with two probiotics can improve gastrointestinal motility in FD rats,and the effect is superior to that of using the drugs alone.The specific underlying mechanisms may be related to the activation of the SCF/c-Kit signaling pathway and the inhibition of the TLR4/MyD88/NF-κB signaling pathway.

Objective To investigate the application value of transumbilical single-port total laparoscopic hysterectomy by conventional instrument without uterine-lifting in the treatment of cervical lesions.Methods We selected 60 cases of total laparoscopic hysterectomy due to cervical high-grade squamous intraepithelial lesion(HSIL)or cervical cancer stage ⅠA1 from December 2021 to June 2023.According to the patients'preference,30 cases of single-port laparoscopy through the umbilicus and 30 cases of multi-port laparoscopy were performed,both using conventional instruments without uterine-lifting.The surgical indicators of the two groups were compared.Results No conversion to open surgery occurred in both groups,and no intraoperative injuries to the urinary system,bowel,or major blood vessels occurred.As compared with the multi-port group,the single-port group had significantly reduced amount of bleeding during surgery[(54.6±20.5)ml vs.(67.5±27.0)ml,P = 0.041],earlier anal exhaust time[(27.6±8.0)h vs.(32.2±9.0)h,P =0.040],and shorter total hospitalization time[(4.4±1.5)d vs.(5.1±1.2)d,P = 0.044].There were no significant differences in uterine weight,surgical time,and postoperative complications between the two group(P>0.05).The healing of the abdominal wall puncture wounds in both groups of patients were satisfied.There were no short-term complications related to the puncture device(such as puncture wound infection and bleeding)or long-term complications(such as umbilical hernia and incisional hernia).Conclusion Transumbilical single-port total laparoscopic hysterectomy without uterine-lifting presents advantages of less intraoperative bleeding,faster postoperative recovery,and almost no scarring,with complications similar to traditional laparoscopic surgery.

Objective To explore the guiding value of thromboelastography(TEG)in the formulation of personalized anticoagulation regimen after knee arthroscopy.Methods A total of 50 patients who underwent knee arthroscopy in our hos-pital from April to August 2023 were randomly divided into two groups.Twenty-seven patients with routine anticoagulation were selected as the control group,and 23 patients with personalized anticoagulation were selected as the experimental group.Conventional anticoagulation was a prophylactic dose of low molecular weight heparin calcium(LMWHC)selected according to body weight,once a day to 7 days after surgery.Personalized anticoagulation was performed according to the prophylactic dose of LMWHC until postoperative day 3.On postoperative day 3,LMWHC was changed to aspirin according to the TEG return index(MA>70 mm,α Angle>72°,K value<1 min),and the initial prophylactic dose was 100 mg/d.LMWHC was changed to rivaroxaban when R<5 min,and the prophylactic dose was 10 mg/d until postoperative day 7.Pa-tients with hypocoagulation or subcutaneous ecchymosis stopped the drug first,and if it was further aggravated,component blood transfusion was performed according to the TEG results.The difference of Caprini score in perioperative period,the correlation between TEG and CCT on postoperative day 1,and the accuracy of predicting thrombosis on postoperative day 7 were compared between the two groups using the receiver operating characteristic curve(ROC).Results There was a sig-nificant difference in Caprini score between the two groups at 7 days after operation(P<0.05),suggesting that the adjust-ment of anticoagulant drugs in the experimental group was effective at 3 days after operation.Pearson correlation evaluation showed that there was a strong positive correlation between maximum coagulation intensity(MA)in TEG and platelet(Plt)in CCT at day 1 after surgery(P<0.05).Thrombosis was found in the control group at 7 days after operation,all of which were CMVT and disappeared after therapeutic antithrombotic therapy.MA was included in the ROC curve for model analysis.The area under the ROC curve(AUC)of the control group was 0.819,and the AUC of the experimental group was 0.508.It was found that the control group model had higher accuracy in predicting the formation of CMVT.Conclusion Individu-alized anticoagulation under TEG monitoring can effectively reduce the occurrence of CMVT after knee arthroscopy,which has guiding value for anticoagulation and thrombosis prevention.

Objective:To investigate the characteristics of voice-personality perception in blind persons and its relationship with their self-evaluation of personality.Methods:A total of 68 blind persons and 68 sighted peers were respectively recruited to rated 30 short voice recordings on traits of voice-personality perception(including maturi-ty,sunshine,cuteness,indolence,seriousness,simpleness and honestness,gentleness,kindness,self-confidence and optimism).Meanwhile,data on self-evaluations of the above participants and speakers in those recordings,along with acquaintance's ratings on speakers'personality were collected.Results:The research found that compared to sighted peers,blind individuals had a lower voice-personality rating on speakers in traits of sunshine,seriousness,gentleness,kindness,self-confidence and optimism(Ps＜0.005).It also detected that the voice-personality ratings on these speakers by blind individuals had a greater deviation from the rating by these speakers/acquaintances in sunshine;gentleness;kindness and optimism(Ps＜0.005).Meanwhile,blind individuals had lower self-rating on personality in sunshine and optimism(Ps＜0.005).Furthermore,self-ratings of sunshine from blind individuals were positively associated with their voice-personality ratings of optimism on speakers(r=0.28,P＜0.05),and their self-ratings of optimism were positively related to their voice-personality ratings of sunshine and self-confi-dence on speakers(r=0.27,0.28,Ps＜0.05).Conclusion:The study shows that blind individuals have lower voice-personality ratings on others than their sighted peers,which might be due to some of their more negative per-sonality characteristics.

Objective To explore the value of deep learning(DL)models semi-automatic training system for automatic optimization of clinical image quality control of transthoracic echocardiography(TTE).Methods Totally 1 250 TTE videos from 402 patients were retrospectively collected,including 490 apical four chamber(A4C),310 parasternal long axis view of left ventricle(PLAX)and 450 parasternal short axis view of great vessel(PSAXGv).The videos were divided into development set(245 A4C,155 PLAX,225 PSAXGV),semi-automated training set(98 A4C,62 PLAX,90 PSAXGV)and test set(147 A4C,93 PLAX,135 PSAXGV)at the ratio of 5:2:3.Based on development set and semi-automatic training set,DL model of quality control was semi-automatically iteratively optimized,and a semi-automatic training system was constructed,then the efficacy of DL models for recognizing TTE views and assessing imaging quality of TTE were verified in test set.Results After optimization,the overall accuracy,precision,recall,and F1 score of DL models for recognizing TTE views in test set improved from 97.33％,97.26％,97.26％and 97.26％to 99.73％,99.65％,99.77％and 99.71％,respectively,while the overall accuracy for assessing A4C,PLAX and PSAXGV TTE as standard views in test set improved from 89.12％,83.87％and 90.37％to 93.20％,90.32％and 93.33％,respectively.Conclusion The developed DL models semi-automatic training system could improve the efficiency of clinical imaging quality control of TTE and increase iteration speed.

Objective To explore the current status of posttraumatic growth (PTG) among nurses at psychiatric department and analyze its latent profiles and population characteristics. Methods A total of 357 nurses from psychiatric departments of five tertiary Grade A hospitals were selected as the research subjects using the convenience sampling method. The PTG and professional quality of life were studied using the Posttraumatic Growth Inventory and the Chinese version of the Compassion Fatigue Scale. Results The PTG score of the nurses was (56.6±23.2). The scores of compassion satisfaction, burnout, and secondary traumatic stress among nurses were (32.6±7.2), (26.9±5.9), and (26.0±5.4), respectively. The result of potential profile analysis showed that the nurses could be divided into three latent profiles based on PTG levels: low PTG group (34.4%), moderate PTG group (44.0%), and high PTG group (21.6%). The results of multinomial logistic regression analysis showed that the nurses who slept 7-8 hours per day were at higher risk of being in the high PTG group compared with those who slept more than eight hours per day (P<0.05). Psychiatric nurses who took regular exercise were at higher risk of being in the high PTG group compared with those who took irregular exercise (P<0.05). The nurses who had high job satisfaction scores were at higher risk of being in the high PTG group compared with those who had low job satisfaction scores (P<0.01). The nurses with higher compassion satisfaction scores increased the risk of being in the high PTG group compared with those with lower compassion satisfaction scores (P<0.01). The nurses with higher burnout scores increased the risk of being in the low PTG group compared with those with lower burnout scores (P<0.01). Conclusion The PTG characteristics of the nurses exhibit heterogeneity and can be categorized into three distinct profiles. Sleep duration, regular exercise, job satisfaction, compassion satisfaction, and burnout are influencing factors for the PTG latent profiles of nurses working at psychiatric department.

BACKGROUND:Studies have shown that both Panax notoginseng saponins and concentrated growth factor can promote fracture healing,but there are few studies addressing their combined effects on fracture healing.Panax notoginseng saponins may accelerate fracture healing by promoting the release of concentrated growth factor-related factors over a certain period of time. OBJECTIVE:To study the effect of Panax notoginseng saponins on concentrated growth factor release and fracture healing in rats. METHODS:Eighteen 8-week-old Sprague-Dawley rats were numbered and randomly divided into three groups:Panax notoginseng saponins group,model control group and blank group.Panax notoginseng saponins group was fed with Panax notoginseng saponins for 2 weeks.Model control group was given 2 mL of normal saline for 2 weeks and blank group was fed normally.Concentrated growth factor was obtained by the centrifugation method both from the Panax notoginseng saponins group and model control group.After 1 week of normal feeding,all animals underwent modeling for femoral fracture.The Panax notoginseng saponins group and the model control group were implanted with autologous concentrated growth factor,and then the release concentration of growth factors at different time points(1 hour,1,3,5,7,9 and 11 days)were measured by ELISA.Fracture healing was assessed based on postoperative X-ray and hematoxylin-eosin staining of bone tissues. RESULTS AND CONCLUSION:Compared with the model control group,the Panax notoginseng saponins group had higher release concentrations of vascular endothelial growth factor A and transforming growth factor β at 7,9,and 11 days,Platelet-derived growth factor BB at 5,9,and 11 days,and basic fibroblast growth factor at 1-11 days(P<0.01).X-ray examinations indicated that fracture healing in the Panax notoginseng saponins group was better than that in the model control group,and fracture healing in these two groups was better than that in the blank group at 2 months after surgery.Hematoxylin-eosin staining results found that the constituent osteocyte density in the Panax notoginseng saponins group was greater than that in the model control group,and the constituent osteocyte density in these two groups was better than that in the blank group.These findings indicate that Panax notoginseng saponins can increase the concentration of concentrated growth factor-related factors.After intervention with Panax notoginseng saponins,concentrated growth factors are more advantageous in promoting fracture healing in rats.