Objective To develop a neural network-based deep learning model for predicting postoperative recurrence in thyroid tumor patients and validate the model with external datasets for providing clinicians with a reliable decision support tool.Methods An artificial neural network structure was adopted in the study,with thyroid tumor data from the SEER database serving as the training set.External validation was conducted with open-source data from the University of California,Irvine(UCIrvine),and the data from 100 patients at a general tertiary hospital in Hunan province.The model's accuracy and reliability in predicting recurrence were evaluated through multiple performance metrics.Results Experimental results showed that the model outperformed Logistic model in recurrence prediction,with accuracy,recall rate,precision and F1 score reaching 0.915 3,0.981 8,0.921 1 and 0.947 4 in internal validation.Moreover,the model achieved accuracies,recall rates,precisions,F1 scores and ROC_AUC values of 0.832 9,0.945 5,0.841 4,0.890 4 and 0.78 on the UCIrvine validation set,while 0.870 0,0.880 0,0.862 7,0.871 3 and 0.80 on the local validation set.Conclusion This neural network-based predictive model exhibits excellent performance in thyroid tumor recurrence prediction,providing clinicians with a valuable decision support tool that can help optimize postoperative treatment plans and improve patient prognosis management.

Objective: To analyze the timeliness of antir-etroviral therapy (ART) and its influencing factors among newly reported HIV/AIDS cases in Wenzhou City, Zhejiang Province from 2016 to 2023, so as to provide a reference for improving the ART effect of HIV/AIDS cases. Methods: Newly reported HIV/AIDS cases in Wenzhou City from 2016 to 2023 were selected as the research subjects. Demographic information, the situation of the first CD4+ T lymphocyte (CD4 cell) test, baseline CD4 cell count, and ART situation were collected through the Chinese Disease Prevention and Control Information System. The timely rate of ART was analyzed, and the influencing factors for timely ART among HIV/AIDS cases were analyzed using a multivariable logistic regression model. Results: A total of 4 500 newly reported HIV/AIDS cases in Wenzhou City from 2016 to 2023 were included, among which 3 679 were males, accounting for 81.76%, and 821 were females, accounting for 18.24%. The median age was 46.24 (interquartile range, 26.23) years. Among these cases, 3 606 received timely ART, with a timely rate of 80.13%. The timely rate of ART increased from 57.54% in 2016 to 91.97% in 2023 (P<0.05). Multivariable logistic regression analysis showed that unmarried/divorced/widowed (OR=0.769, 95%CI: 0.641-0.922), detainees (OR=0.492, 95%CI: 0.269-0.900), untimely first CD4 cell test (OR=0.278, 95%CI: 0.234-0.330), baseline CD4 cell count ≥200 cells/µL (OR=0.709, 95%CI: 0.595-0.843) or undetected (OR=0.131, 95%CI: 0.080-0.213) were associated with a lower timeliness for ART among HIV/AIDS cases. Conclusion From 2016 to 2023, the timely rate of ART among newly reported HIV/AIDS cases in Wenzhou City showed an upward trend, which was mainly affected by marital status, case source, timeliness of the first CD4 cell test, and baseline CD4 cell count.

Objective To develop and validate a nomogram model that integrates systemic inflammatory markers to predict the likelihood of pelvic lymph node metastasis(PLNM)in prostate cancer patients prior to surgery.Methods This study retrospectively analyzed the clinical data and preoperative inflammatory markers—including neutrophil-to-lymphocyte ratio(NLR),platelet-to-lymphocyte ratio(PLR),systemic immune-inflammation index(SII),and monocyte-to-lymphocyte ratio(MLR)—of patients diagnosed with prostate cancer.Univariate and multi-variate logistic regression analyses were conducted to identify markers that were significantly associated with PLNM.Based on the results of the multivariate analysis,a nomogram was developed and its predictive accuracy was assessed using receiver operating characteristic curves(ROC)and calibration plots.Results Among the 334 enrolled patients with prostate cancer,107 were identified with PLNM.Univariate analysis revealed statistically significant differences in free prostate-specific antigen(fPSA),Gleason score,NLR,PLR,MLR,and SII between the PLNM and non-pelvic lymph node metastasis(NPLNM)groups(P<0.05).Multivariate analysis confirmed that fPSA,Gleason score,and SII were independent predictors of PLNM(P<0.05).A nomogram incorporating these predic-tors exhibited strong discriminative ability,with an area under the ROC curve(AUC)of 0.79(95%CI:0.73～0.84).Calibration analysis further demonstrated good consistency between the predicted and observed probabilities of PLNM.Conclusions This study successfully developed a nomogram model based on systemic inflammatory markers for preoperative prediction of pelvic lymph node metastasis in prostate cancer.Owing to its user-friendly design and high predictive accuracy,this tool may serve as a valuable complementary method to conventional imaging techniques,thereby supporting personalized treatment decision-making.

Objective To investigate the expression of LncRNA RMST in gastric cancer and its value in diagnosis and prognosis.Methods Tumor and adjacent normal tissues were collected and analyzed from 92 gastric cancer patients.The expression of LncRNA RMST in these tissues was measured using RT-qPCR.ROC curve analysis was performed to evaluate the diagnostic value of LncRNA RMST for gastric cancer.Survival curves were plotted to assess the prognostic significance of LncRNA RMST in gastric cancer.Results LncRNA RMST expression was significantly lower in gastric cancer tissues than in normal tissues.Further analysis revealed that LncRNA RMST expression levels decreased progressively with advancing cancer stages and were significantly correlated with tumor size,TNM staging,and lymph node metastasis(P<0.05),with no significant correlation with patient age or gender.Additionally,ROC curve analysis indicated that LncRNA RMST has substantial diagnostic value in gastric cancer,with AUC of 0.76(95%CI:0.69～0.83,P<0.01),sensitivity of 70.31%,and specificity of 71.56%.Survival analysis showed that patients with high LncRNA RMST expression had significantly higher overall survival rates than those with low expression.Conclusion LncRNA RMST plays a critical role in the occurrence,progres-sion,and prognosis of gastric cancer.It may serve as a potential biomarker for the diagnosis and prognosis of gastric cancer,offering new insights for clinical screening and therapeutic strategies.

Objective To develop and validate a nomogram model that integrates systemic inflammatory markers to predict the likelihood of pelvic lymph node metastasis(PLNM)in prostate cancer patients prior to surgery.Methods This study retrospectively analyzed the clinical data and preoperative inflammatory markers—including neutrophil-to-lymphocyte ratio(NLR),platelet-to-lymphocyte ratio(PLR),systemic immune-inflammation index(SII),and monocyte-to-lymphocyte ratio(MLR)—of patients diagnosed with prostate cancer.Univariate and multi-variate logistic regression analyses were conducted to identify markers that were significantly associated with PLNM.Based on the results of the multivariate analysis,a nomogram was developed and its predictive accuracy was assessed using receiver operating characteristic curves(ROC)and calibration plots.Results Among the 334 enrolled patients with prostate cancer,107 were identified with PLNM.Univariate analysis revealed statistically significant differences in free prostate-specific antigen(fPSA),Gleason score,NLR,PLR,MLR,and SII between the PLNM and non-pelvic lymph node metastasis(NPLNM)groups(P<0.05).Multivariate analysis confirmed that fPSA,Gleason score,and SII were independent predictors of PLNM(P<0.05).A nomogram incorporating these predic-tors exhibited strong discriminative ability,with an area under the ROC curve(AUC)of 0.79(95%CI:0.73～0.84).Calibration analysis further demonstrated good consistency between the predicted and observed probabilities of PLNM.Conclusions This study successfully developed a nomogram model based on systemic inflammatory markers for preoperative prediction of pelvic lymph node metastasis in prostate cancer.Owing to its user-friendly design and high predictive accuracy,this tool may serve as a valuable complementary method to conventional imaging techniques,thereby supporting personalized treatment decision-making.

Objective To develop a neural network-based deep learning model for predicting postoperative recurrence in thyroid tumor patients and validate the model with external datasets for providing clinicians with a reliable decision support tool.Methods An artificial neural network structure was adopted in the study,with thyroid tumor data from the SEER database serving as the training set.External validation was conducted with open-source data from the University of California,Irvine(UCIrvine),and the data from 100 patients at a general tertiary hospital in Hunan province.The model's accuracy and reliability in predicting recurrence were evaluated through multiple performance metrics.Results Experimental results showed that the model outperformed Logistic model in recurrence prediction,with accuracy,recall rate,precision and F1 score reaching 0.915 3,0.981 8,0.921 1 and 0.947 4 in internal validation.Moreover,the model achieved accuracies,recall rates,precisions,F1 scores and ROC_AUC values of 0.832 9,0.945 5,0.841 4,0.890 4 and 0.78 on the UCIrvine validation set,while 0.870 0,0.880 0,0.862 7,0.871 3 and 0.80 on the local validation set.Conclusion This neural network-based predictive model exhibits excellent performance in thyroid tumor recurrence prediction,providing clinicians with a valuable decision support tool that can help optimize postoperative treatment plans and improve patient prognosis management.

Objective To investigate the expression of LncRNA RMST in gastric cancer and its value in diagnosis and prognosis.Methods Tumor and adjacent normal tissues were collected and analyzed from 92 gastric cancer patients.The expression of LncRNA RMST in these tissues was measured using RT-qPCR.ROC curve analysis was performed to evaluate the diagnostic value of LncRNA RMST for gastric cancer.Survival curves were plotted to assess the prognostic significance of LncRNA RMST in gastric cancer.Results LncRNA RMST expression was significantly lower in gastric cancer tissues than in normal tissues.Further analysis revealed that LncRNA RMST expression levels decreased progressively with advancing cancer stages and were significantly correlated with tumor size,TNM staging,and lymph node metastasis(P<0.05),with no significant correlation with patient age or gender.Additionally,ROC curve analysis indicated that LncRNA RMST has substantial diagnostic value in gastric cancer,with AUC of 0.76(95%CI:0.69～0.83,P<0.01),sensitivity of 70.31%,and specificity of 71.56%.Survival analysis showed that patients with high LncRNA RMST expression had significantly higher overall survival rates than those with low expression.Conclusion LncRNA RMST plays a critical role in the occurrence,progres-sion,and prognosis of gastric cancer.It may serve as a potential biomarker for the diagnosis and prognosis of gastric cancer,offering new insights for clinical screening and therapeutic strategies.

Objective:To compare the efficacy of endoscopic submucosal dissection (ESD) and modified-endoscopic mucosal resection (M-EMR) for G1 rectal neuroendocrine tumors (RNETs) .Methods:Data of 121 patients with pathologically confirmed G1 RNETs treated with ESD ( n=105) or M-EMR ( n=16) in Nanjing Drum Tower Hospital from January 2017 to September 2020 were retrospectively analyzed. The complete resection rate, complication incidence, hospital stay, treatment cost and other indicators of the two groups were compared by using inverse probability of treatment weighting (IPTW). Results:There were significant differences in tumor number ( χ2=8.76, P=0.003), tumor invasion depth ( χ2=6.96, P=0.008), utilization of metal clips [82.9% (87/105) VS 93.8% (15/16), χ2=8.78, P=0.003], number of metal clips ( χ2=8.41, P=0.016), hemostasis using hot clamp [78.1% (82/105) VS 18.7% (3/16), χ2=20.64, P<0.001], traction procedure [2.9% (3/105) VS 18.7% (3/16), χ2=4.45, P=0.035] and treatment cost (17 568.6 ± 8 911.0 yuan VS 8 120.8±1 528.2 yuan, t=3.65, P<0.001) between the ESD group and the M-EMR group. After verifying the stability of the results using IPTW sensitivity analysis, there was still significant difference in the treatment cost ( t=2.07, P<0.001). Conclusion:Both ESD and M-EMR demonstrate comparable efficacy in treating G1 RNETs; however, M-EMR exhibites lower treatment costs.

Purpose/Significance To analyze the current situation and problems of the development of digital health in China,and to explore how to promote the innovative development of digital health.Method/Process The current situation and main problems of digital health are studied and analyzed by the method of literature research and network survey,and the paths of the innovative development of digital health are devised based on case analysis.Result/Conclusion Digital technology has become the key to breaking down multiple barriers to digital health development.The paper puts forward the specific path of"sharing and cooperative governance platform-indus-trial security system-intelligent supervision mechanism"and the digital technology-based countermeasures to promote innovative devel-opment of the industry.

Purpose/Significance To explore the research status,research hotspots and frontiers in the field of clinical decision sup-port based on electronic medical records(EMR).Method/Process The bibliometric method and CiteSpace 6.2.R2 software are used to draw scientific knowledge graph of country/region distribution,author cooperation,institutional cooperation,keyword co-occurrence and clustering for visualized comparative analysis.Python is used for clustering hotspot mining and analysis.Result/Conclusion The field of clinical decision support based on EMR data shows a rapid development trend,with the United States and China as the main research countries and strong cooperation between domestic and foreign institutions.The keywords mainly involve EMR,artificial intelligence(AI),etc.