Objective To explore the clinical value of artificial intelligence (AI) quantitative parameters in distinguishing pathological grades of stageⅠ invasive adenocarcinoma (IAC). Methods Clinical data of patients with clinical stageⅠ IAC admitted to Yantaishan Hospital Affiliated to Binzhou Medical University from October 2018 to May 2023 were retrospectively analyzed. Based on the 2021 WHO pathological grading criteria for lung adenocarcinoma, IAC was divided into gradeⅠ, grade Ⅱ, and grade Ⅲ. The differences in parameters among the groups were compared, and logistic regression analysis was used to evaluate the predictive efficacy of AI quantitative parameters for grade Ⅲ IAC patients. Parameters were screened using least absolute shrinkage and selection operator (LASSO) regression analysis. Three machine learning models were constructed based on these parameters to predict grade Ⅲ IAC and were internally validated to assess their efficacy. Nomograms were used for visualization. Results A total of 261 IAC patients were included, including 101 males and 160 females, with an average age of 27-88 (61.96±9.17) years. Six patients had dual primary lesions, and different lesions from the same patient were analyzed as independent samples. There were 48 patients of gradeⅠ IAC, 89 patients of grade Ⅱ IAC, and 130 patients of grade Ⅲ IAC. There were statitical differences in the AI quantitive parameters such as consolidation/tumor ratio (CTR), ect among the three goups. (P<0.05). Univariate analysis showed that the differences in all variables except age were statistically significant (P<0.05) between the group gradeⅠ+grade Ⅱand the group grade Ⅲ . Multivariate analysis suggested that CTR and CT standard deviation were independent risk factors for identifying grade Ⅲ IAC, and the two were negatively correlated. Grade Ⅲ IAC exhibited advanced TNM staging, more pathological high-risk factors, higher lymph node metastasis rate, and higher proportion of advanced structure. CTR was positively correlated with the proportion of advanced structures in all patients. This correlation was also observed in grade Ⅲ but not in gradeⅠand grade ⅡIAC. CTR and CT median value were selected by using LASSO regression. Logistic regression, random forest, and XGBoost models were constructed and validated, among which, the XGBoost model demonstrated the best predictive performance. Conclusion Cautious consideration should be given to grade Ⅲ IAC when CTR is higher than 39.48% and CT standard deviation is less than 122.75 HU. The XGBoost model based on combined CTR and CT median value has good predictive efficacy for grade Ⅲ IAC, aiding clinicians in making personalized clinical decisions.

Objective: To systematically evaluate the detection rate of prenatal depression in Chinese women, so as to provide the reference for mental health care during pregnancy among women. Methods: Publications pertaining to the detection rate of prenatal depression in Chinese women were retrieved from international and national databases from inception to July 30, 2023, including CNKI, Wanfang Data, VIP, PubMed and other databases. The Stata 17.0 software was used for meta analysis, sensitivity analysis was performed using the leave-one-out method, and the publication bias was evaluated using funnel plot and Egger's test. Results: A total of 5 687 publications were retrieved, and 60 studies were finally included, with 58 in Chinese and 2 in English, 51 of medium quality and 9 of high quality, and 114 168 participants. The results of meta-analysis showed that the overall detection rate of prenatal depression in Chinese women was 23.7% (95%CI: 20.0%-27.5%). The detection rates of prenatal depression in the first, second and third trimesters were 22.1% (95%CI: 15.5%-28.6%), 16.3% (95%CI: 12.0%-20.6%) and 19.9% (95%CI: 16.0%-23.7%), in Eastern and Midwestern China were 19.7% and 27.5%, and in women with an education level of junior high school or below and high school or above were 27.2% and 17.9%, respectively, with statistically significant differences (all P<0.05). Sensitivity analysis showed that the study results were stable. There were publication bias in the results of overall detection rate of prenatal depression, and detection rates in the second and third trimester. Conclusions The overall detection rate of prenatal depression in Chinese women ranges from 20.0% to 27.5%. There are differences in the detection rate of prenatal depression in different pregnancies, with the highest detection rate in the first trimester.

Objective To investigate the colonization characteristics of staphylococcus aureus(SA)and methicillin-resistant staphylococcus aureus(MRSA)and their correlation with postoperative surgical site infection(SSI)in orthopedic inpatients,and to ana-lyze the related factors affecting their colonization.Methods Nasal swab and pharyngeal swab samples of 420 patients hospitalized in the Department of Orthopedics,Tongde Hospital of Zhejiang Province from January 2020 to October 2022 were collected.Polymerase chain re-action(PCR)was used to detect the positive colonization of SA and MRSA,and clinical data of patients were obtained.x2 test was used to analyze the correlation between SA positive colonization and postoperative SSI.Univariate and multivariate Logistic regression analysis were used to explore the related factors affecting SA colonization.Results Among 420 patients,19 patients were positive for SA,and the overall SA colonization positive rate was 4.5％.17 patients were positive for MRSA,and the overall MRSA colonization positive rate was 4.0％.There was no statistically significant difference in postoperative SSI between SA colonization positive and SA colonization negative patients(P＞0.05).Thus,there was no significant correlation between SA colonization and the occurrence of postoperative SSI.Univari-ate Logistic regression analysis showed that age and body mass index(BMI)were influencing factors for SA colonization,while multivari-ate Logistic regression analysis showed that BMI was the risk factor for SA colonization,and the higher the BMI,the higher the colonization risk.Age was the protective factor for SA colonization,and the risk of SA colonization decreased with increasing age.Conclusion SA colonization in orthopedic inpatients does not increase the risk of postoperative SSI,and preoperative SA decolonization that increases the patient's medical cost is unnecessary.BMI is the risk factor for SA colonization in orthopedic inpatients,and age is the protective factor.SA colonization of orthopedic inpatients has regional attributes,and each region needs to make medical plans according to its regional SA colonization epidemiological characteristics.

Objective:To construct a non-invasive pre-hospital screening model and early based on artificial intelligence algorithms to provide the severity of stroke in patients, provide screening, guidance and early warning for stroke patients and their families, and provide data support for clinical decision-making.Methods:A retrospective study was conducted. The clinical information of stroke patients ( n = 53?793) were extracted from the Yidu cloud big data server system of the Second Affiliated Hospital of Dalian Medical University from January 1, 2001 to July 31, 2023. Combined with the results of single factor screening and the opinions of experts with senior professional titles in neurology, the input variable was determined, and the output variable was the National Institutes of Health Stroke Scale (NIHSS) representing the severity of the disease at admission. Python 3.7 was used to build DeepFM algorithm model, and five data mining models including Logistic regression, CART decision tree, C5.0 decision tree, Bayesian network and deep neural network (DNN) were built at the same time. The original data were randomly divided into 80% training set and 20% test set, which were used to train and test the models, adjust the parameters of each model, respectively calculate the accuracy, sensitivity and F-index of the six models, carry out the comprehensive comparison and evaluation of the model. The receiver operator characteristic curve (ROC curve) and calibration curve were drawn, compared the prediction performance of DeepFM model and the other five algorithms. In addition, the data of stroke patients ( n = 1?028) were extracted from Dalian Central Hospital for external verification of the model. Results:A total of 14?015 stroke patients with complete information were selected, including 11?212 in the training set and 2?803 in the testing set. After univariate screening, 14 indicators were included to construct the model, including gender, age, recurrence, physical impairment, facial problems, speech disorders, head reactions, disturbance of consciousness, visual disorders, abnormal cough and swallowing, high risk factor, family history, smoking history and drinking history. DeepFM model adopted the two-order crossover feature. The number of hidden layers in DNN layer was 3. Dropout was used to discard the neurons in the neural network. Rule was used as the activation function. Each layer used Dense full connection. The objective function was random gradient descent. The number of iterations was 15. There were 133?922 training parameters in total. Comparing the predictive value of the six models showed that the accuracy of DeepFM model was 0.951, the sensitivity was 0.992, the specificity was 0.814, the F-index was 0.950, and the area under the curve (AUC) was 0.916. The accuracy of the other five data mining models were between 0.771-0.780, the sensitivity were between 0.978-0.987, the F-index were between 0.690-0.707, and the AUC were between 0.568-0.639. The calibration curve of the DeepFM model was more aligned with the ideal curve than the other five data mining models. Suggesting that the prediction performance of DeepFM model was the best. External validation was conducted on the DeepFM model, and its accuracy was 0.891, indicating good generalization performance of the model.Conclusion:The pre-hospital non-invasive screening prediction model based on DeepFM can accurately predict the severity grading of stroke patients, and has potential application value in rapid screening and early clinical decision-making of stroke.

Objective:To systematically review qualitative research on maternal participation in skin-to-skin contact experience during cesarean delivery, the promotion of skin-to-skin contact in cesarean section.Methods:We searched databases including the PubMed, Embase, Web of Science, Cochrane Library, Ebsco, SinoMed, Wan Fang, CNKI, VIP. All of the qualitative research on the real experience of skin-to-skin contact from the participation of caesarean section women were collected. The search time limit was from the establishment of the databases to May 2022. The JBI Critical Appraisal Tool for qualitative studies from Australia was used to evaluate the methodology quality of the included research, and the meta-aggregation was used to conduct the synthesis.Results:Totally 11 qualified studies were included and integrated into 49 valuable findings. Similar results were summarized into 12 groups, and 4 integrated results were synthesized, including the needs of cesarean section mothers; positive experience after skin-to-skin contact in caesarean section; skin-to-skin contact practice strengthen the role of mothers and promotes breastfeeding; difficulties and challenges of skin-to-skin contact during cesarean section.Conclusions:Skin-to-skin contact positively affects mother and infant delivered by cesarean section. Medical staff need to pay attention to the feelings and needs of cesarean section women participating in skin-to-skin contact, optimize information, environment, and humanistic support, and improve skin-to-skin contact practices. Medical institutions should rationally allocate obstetric resources to alleviate the difficulties faced by skin-to-skin contact practices.

Objective:To summarize the results of surgical treatment for complete atrioventricular septal defect(CAVSD) in early and middle stages.Methods:147 children with CAVSD in Guangzhou Women and Children’s Medical Center from January 2010 to December 2019 were selected, Males 85, females 62, median age of surgery 5 months(1 months-10 years old), median body mass 5.5 kg(2.4-20.9 kg). Complete atrioventricular septal defect was diagnosed by ultrasonic cardiogram before surgery. All the children underwent atrial ventricular valve formation and underwent simultaneous repair.Outpatient follow-up was planned.Ultrasonic cardiogram and electrocardiogram were performed. SPSS 22 statistical software was used for data analysis.Results:All 147 CAVSD patients underwent one-time surgical correction.Early postoperative death occurred in 7 cases(4.76%). The causes of death were: 3 cases of pulmonary hypertension crisis, 3 cases of severe mitral insufficiency(MI), 1 case of postoperative malignant arrhythmia, and the rest of the children were cured and discharged. Permanent pacemaker was installed in 3 patients due to atrioventricular block(AVB). The follow-up time was 1-10 years old, and 2 patients died in late stage: 1 patient did not seek medical treatment in time due to infection, and 1 patient had unknown cause. Five patients underwent secondary surgery: 4 due to severe mitral/tricuspid insufficiency(MI/TI) and 1 due to delayed AVB. The mid-term follow-up showed 9 cases of severe MI and 4 cases of severe TI. Compared with children with surgical age<3 months and ≥3 months, there were statistically significant differences in postoperative ventilator-assisted ventilation time, severe MI before postoperative discharge and total mortality between the two groups( P<0.05). Mid-term follow-up results showed no difference between the two groups. There were statistically significant differences in surgical age, postoperative CICU stay time and total hospital stay between the children with trisomy 21-syndrome and those without trisomy 21-syndrome( P<0.05), and there was no difference between the two groups in mid-term follow-up results. Residual shunt of 1-3 mm VSD was found in 29 cases, 26 cases were closed during follow-up, and 3 cases had smaller residual shunt. Conclusion:Modified single patch technique treatment of CAVSD has good effect, low mortality and low re-operation rate. But age <3 months group, infant mortality was significantly increased, the duration of postoperative mechanical assisted ventilation was prolonged, and the proportion of early postoperative severe MI was high.Severe MI and TI is easy to occur after CAVSD, which requires long-term follow-up and timely treatment. The children with trisomy 21-syndrome were similar to those with normal chromosome except for longer stay in ICU and total hospital stay.

OBJECTIVE To investigate the pharmacological components and mechanism of Qingre huoxue decoction in improving myocardial ischemia-reperfusion injury（MIRI）. METHODS Forty-two rats were randomly divided into sham operation group （normal saline）， model group （normal saline）， Qingre huoxue decoction low-dose， medium-dose and high-dose groups （4.94， 9.88， 19.79 g/kg），Qingre huoxue decoction drug-containing serum group （19.79 g/kg） and blank serum group （normal saline）， with 6 rats in each group. Each group was given corresponding drug/normal saline intragastrically， once a day， for consecutive 2 weeks. Twelve hours after last administration， except for serum groups， MIRI model was induced in other groups （only threading without ligation in sham operation group）. After modeling， cardiac histopathology was observed and apoptosis level was detected. UPLC-MS was used to analyze the samples in Qingre huoxue decoction drug-containing serum group and blank serum group. The main pharmacological components were screened with the help of relevant databases. Multivariate statistical methods were used to analyze the differential metabolites and related metabolic pathways. Validation test was performed based on oxidative stress indicators. RESULTS Qingre huoxue decoction could improve the pathological injury of cardiac tissue and decrease apoptosis rate of cardiac cells in MIRI model rats （P＜0.05）. Qingre huoxue decoction drug-containing serum contained 20 main pharmacological components such as baicalin， succinic acid， baicalein， cryptotanshinone， isoferulic acid， protocatechuic aldehyde. Qingre huoxue decoction could significantly up-regulate the levels of 15 metabolites including L-arginine， L-arginine， citric acid， glutathione， β-D- glucose and L-carnitine， and down-regulated the levels of 14 metabolites including arachidonic acid， 3-phosphate-d-glycerol phosphate， linoleic acid， docosahexaenoic acid， phosphatidylcholine and lysophosphatidylcholine （P＜0.05）. These metabolites were mainly involved in energy metabolism， inflammatory injury， oxidative stress and autophagy. Results of validation tests showed that Qingre huoxue decoction could significantly reduce the levels of malondialdehyde， and increased the levels of superoxide dismutase （except for low-dose group） and glutathione peroxidase significantly （P＜0.05）. CONCLUSIONS Qingre huoxue decoction can improve the injury of cardiac tissue in MIRI model rats. Its pharmacological components include baicalin， cryptotanshinone， isoferulic acid， protocatechualdehyde， etc. Furthermore， it may play a protective role in MIRI by improving myocardial energy metabolism， down-regulating oxidative stress， inhibiting inflammation infiltration.

Objective: To explore data mining methods and tools for the activity paths of confirmed patients, and provide data analysis tools for epidemic control. Methods: The data used came from the trajectory data of confirmed cases collected by Tencent. The jieba word segmentation and word cloud map function of Python 3.6 were used to calculate the high-frequency vocabulary in the trajectory of confirmed patients. The epidemic prevention and control strategy was developed based on the high-frequency vocabulary. Results: Taking Guangdong Province, the second most confirmed patients in the country, as an example, the key areas of epidemic control obtained through data mining involve Wuhan (epidemiological history), Zhuhai and Guangzhou. The key control activities include family visiting, traveling and shopping. Means of transportation include self-driving, trains and airplanes; the key patients studied were Li and Ding; the symptoms of this patient group were mainly fever and cough. Conclusions The data mining algorithm in this paper can provide an advantageous tool for epidemic prevention and control, also assist frontline personnel to adjust the deployment of epidemic prevention and control according to their priorities.

Objective:To investigate the association between levator hiatus area, pelvic organ prolapse quantification (POP-Q) examination and prolapse symptoms.Methods:The prospective multicenter study enrolled 996 female patients between January 2017 and January 2019. All enrolled patients underwent a standard clinical interview, POP-Q examination and transperineal ultrasound examination. Volume data of pelvic floor ultrasound examinations were obtained at rest, during contraction and during maximal Valsalva maneuver. The association between levator hiatus area, POP-Q examination and prolapse symptoms was analyzed. The performance of levator hiatus area on maximal Valsalva for assessing significant POP(POP-Q stage≥2) and prolapse symptoms were also evaluated.Results:There were significant differences of levator hiatus area at rest, during contraction and during maximal Valsalva among patients with different POP-Q stages (all P<0.001). Levator hiatus area during maximal Valsalva showed the highest correlation with abdominal dragging sensation ( r=0.277, P<0.001). The area under the ROC curve (AUC) of levator hiatus area during maximal Valsalva for significant POP (POP-Q stage≥2) was significantly higher than that for prolapse symptoms (AUC: 0.77 vs 0.69, P<0.001). Conclusions:Levator hiatus area on transperineal has moderate correlation with POP-Q examination and their association is stronger than the correlation between ultrasound findings and prolapse symptoms.

Objective:To investigate the feasibility of transperineal ultrasound in quantitative assessment of posterior compartment prolapse among Chinese women.Methods:The prospective multicenter study enrolled 485 women between January 2017 and January 2019. All patients underwent a standard clinical interview, pelvic organ prolapse quantification (POP-Q) examination and transperineal ultrasound examination. Volume data of transperineal ultrasound examinations were obtained at rest and in maximal Valsalva maneuver.Results:The higher POP-Q stage of posterior compartment, the lower rectal ampulla position in maximal Valsalva maneuver (POP-Q stage=0 vs POP-Q stage=1, P<0.001; POP-Q stage=1 vs POP-Q stage≥2, P<0.001), and the greater rectal ampulla hypermobility (POP-Q stage=0 vs POP-Q stage=1, P<0.001; POP-Q stage=1 vs POP-Q stage≥ 2, P=0.007). The rectal ampulla position at rest and in maximal Valsalva maneuver and rectocele depth were correlated with prolapse symptoms ( r=-0.200, P<0.001; r=-0.252, P<0.001; r=0.086, P=0.045). The corresponding cut-off values of rectal ampulla position in maximal Valsalva in diagnosing posterior compartment prolapse (POP-Q stage ≥1) and clinical significant posterior compartment prolapse (POP-Q stage ≥2) were 7.32 mm below the symphysis pubis and 12 mm below the symphysis pubis, respectively, with the area under the ROC curve as 0.75 and 0.85, respectively. Conclusions:The ultrasonic measurements by transperineal ultrasound is significantly associated with POP-Q examination in posterior compartment, and it is demonstrated as a useful tool in quantitative assessment of the severity of posterior compartment prolapse.