Objective:To construct an prediction model based on magnetic resonance imaging (MRI) machine learning algorithm and radiomics and investigate its application value in predicting lymphovascular invasion (LVI) status of rectal cancer without lymph node metastasis.Methods:The retrospective cohort study was conducted. The clinicopathological data of 204 rectal cancer patients without lymph node metastasis who were admitted to Gansu Provincial Hospital from February 2016 to January 2024 were collected. There were 123 males and 81 females, aged (61±7)years. All 204 patients were randomly divided into the training dataset of 163 cases and the testing dataset of 41 cases by a ratio of 8∶2 using the electronic computer randomization method. The training dataset was used to construct the prediction model, and the testing dataset was used to validate the prediction model. The clinical prediction model, radiomics model and joint prediction model were constructed based on the selected clinical and/or imaging features. Measurement data with normal distribution were represented as Mean± SD. Count data were described as absolute numbers, and the chi-square test or Fisher exact probability were used for comparison between the groups. Comparison of ordinal data was conducted using the nonparameter rank sum test. The inter-class correlation coefficient (ICC) was used to evaluate the consistency of the radiomics features of the two doctors, and ICC >0.80 was good consistency. Univariate analysis was conducted by corres-ponding statistic methods. Multivariate analysis was conducted by Logistic stepwise regression model. The receiver operating characteristic (ROC) curve was drawn, and the area under the curve (AUC), Delong test, decision curve and clinical impact curve were used to evaluate the diagnostic efficiency and clinical utility of the model. Result:(1) Analysis of factors affecting LVI status of patients. Of the 204 rectal cancer patients without lymph node metastasis, there were 71 cases with positive of LVI and 133 cases with negative of LVI. Results of multivariate analysis showed that gender, platelet (PLT) count and carcinoembryonic antigen (CEA) were independent factors affecting LVI status of rectal cancer without lymph node metastasis in training dataset [ odds ratio=2.405, 25.062, 2.528, 95% confidence interval ( CI) as 1.093-5.291, 2.748-228.604, 1.181-5.410, P<0.05]. (2) Construction of clinical prediction model. The clinical prediction model was conducted based on the results of multivariate analysis including gender, PLT count and CEA. Results of ROC curve showed that the AUC, accuracy, sensitivity and specificity of clinical prediction model were 0.721 (95% CI as 0.637-0.805), 0.675, 0.632 and 0.698 for the training dataset, and 0.795 (95% CI as 0.644-0.946), 0.805, 1.000 and 0.429 for the testing dataset. Results of Delong test showed that there was no significant difference in the AUC of clinical prediction model between the training dataset and the testing dataset ( Z=-0.836, P>0.05). (3) Construction of radiomics model. A total of 851 radiomics features were extracted from 204 patients, and seven machine learning algorithms, including logistic regression, support vector machine, Gaussian process, logistic regression-lasso algorithm, linear discriminant analysis, naive Bayes and automatic encoder, were used to construct the prediction model. Eight radiomics features were finally selected from the optimal Gaussian process learning algorithm to construct a radiomics prediction model. Results of ROC curve showed that the AUC, accuracy, sensitivity and specificity of radiomics prediction model were 0.857 (95% CI as 0.800-0.914), 0.748, 0.947 and 0.642 for the training dataset, and 0.725 (95% CI as 0.571-0.878), 0.634, 1.000 and 0.444 for the testing dataset. Results of Delong test showed that there was no significant difference in the AUC of radiomics prediction model between the training dataset and the testing dataset ( Z=1.578, P>0.05). (4) Construction of joint prediction model. The joint prediction model was constructed based on the results of multivariate analysis and the radiomics features. Results of ROC curve showed that the AUC, accuracy, sensitivity and specificity of radiomics prediction model were 0.885 (95% CI as 0.832-0.938), 0.791, 0.912 and 0.726 for the training dataset, and 0.857 (95% CI as 0.731-0.984), 0.854, 0.714 and 0.926 for the testing dataset. Results of Delong test showed that there was no significant difference in the AUC of joint prediction model between the training dataset and the testing dataset ( Z=0.395, P>0.05). (5) Performance comparison of three prediction models. Results of the Hosmer-Lemeshow goodness-of-fit test showed that all of the clinical prediction model, radiomics prodiction model and joint prediction model having good fitting degree ( χ2=1.464, 12.763, 10.828, P>0.05). Results of Delong test showed that there was no signifi-cant difference in the AUC between the clinical prediction model and the joint prediction model or the radiomics model ( Z=1.146, 0.658, P>0.05), and there was a significant difference in the AUC between the joint prediction model and the radiomics model ( Z=2.001, P<0.05). Results of calibra-tion curve showed a good performance in the joint prediction model. Results of decision curve and clinical impact curve showed that the performance of joint prediction model in predicting LVI status of rectal cancer without lymph node metastasis was superior to the clinical prediction model and the radiomics model. Conclusions:The clinical prediction model is constructed based on gender, PLT count and CEA. The radiomics predictive model is constructed based on 8 selected radiomics features. The joint prediction model is constructed based on the clinical prediction model and the radiomics predictive model. All of the three models can predict the LVI status of rectal cancer with-out lymph node metastasis, and the joint prediction model has a superior predictive performance.

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.

With the wide application of artemisinin and its derivatives,its safety has become particularly important.Previous studies have shown that artemisinin and its derivatives have adverse reactions such as nausea,vomiting and diarrhea in clinical use,but they are all within the controllable range.In animal experiments,it has toxic effects on kidney,liver,heart,nerve,blood,embryo and DNA at a high dose.Toxicity and adverse reactions can be alleviated or eliminated by combining medication or changing the drug administration mode,solvent and preparation type.This article mainly discusses the drug safety,toxicity mechanism and attenuation countermeasures of artemisinin and its derivatives,in order to improve the understanding of the potential toxicity of artemisinin and its derivatives and provide reference for the safe use of the drug in clinic.

Objective To summarize the preliminary application results of ultrasound-guided biliary drainage tube replacement, present the corresponding technical points, and discuss the operation strategy and clinical application value. Methods The clinical data of 60 patients who underwent ultrasound-guided biliary drainage tube replacement in Qilu Hospital of Shandong University between August 2014 and August 2020 were retrospectively analyzed. The operation procedure, clinical applications, and postoperative complications were summarized and analyzed. Results Fifty-eight of the 60 patients (96.67%) were successfully replaced with drainage tubes along the original sinus. Among them, dilated sinus tracts of 47 patients were placed with coarse-grade drainage tubes, and dilated sinus tracts of the remaining 11 patients were placed with the original type of drainage tubes, with the mean operation time of 15.8(12.0-19.0) min under local anesthesia. In total, bile was drained from 28 patients receiving PTCD drainage, 23 patients receiving gallbladder drainage, and 9 patients receiving T-tube drainage. The post-operation evaluation revealed that the drainage situation has improved, with a 100% effective rate. No obvious abnormality was found in the postoperative follow-up visit. Conclusion The replacement of drainage tube under ultrasound guidance is simple, safe and feasible, and it provides further promotion in clinical practice with sufficient data support.

The incidence of psoriasis in the world is increasing year by year. With the deepening of the understanding of self-management efficacy, the research on self-management efficacy of psoriasis patients at home and abroad is increasing. This article reviews the concepts, contents, influencing factors and intervention of self-management efficacy in patients with psoriasis, so as to provide a reference for improving the self-management efficacy of patients with psoriasis.

Objective: To investigate risk factors and epidemiological characteristics of bacillary dysentery outbreaks in three schools, and to provide scientific basis for the prevention and control of the epidemic in the future. Methods: Case definition was established. All suspected, possible and confirmed cases of all students and faculty members from 3 schools (A, B, C) were selected for epidemiological investigation. Control group was used for case-control analysis, and relevant samples were collected for laboratory testing. Results: A total of 132 cases were found in 3 schools, all of which were from students, with the incidence rate of 17.74%. The morbidity in kindergarten A was 20.00%, in center primary school B it was 21.74%, and in junior middle school C it was 11.61%. Cohort studies and casecontrol studies suggested that schools are exposed places and that washing hands with raw water in schools was possible risk factor [OR(95%CI) =4.50(1.01-20.11)]. Nine stool samples were tested in laboratory, among which 8 were positive for Shigella(88.99%), and Shigella was detected in the end nodes of school s pipeline network, the water samples from canteen bucket, and the floor drains of sewer pipe. Conclusion The bacillary dysentery outbreaks in 3 schools was caused by Shigella, which may be due to fecal contamination of domestic water in 3 schools before the start of the school year. It is suggested to strengthen the management of centralized water supply and construction in rural areas, intensify the supervision at all levels, and sanitation and disinfection before school opens at all levels.

Objective:To investigate the diagnostic and prognostic value of the growth differentiation factor 15 (GDF15) and the procalcitonin (PCT) in sepsis.Methods:A total number of 137 patients with sepsis (considered as the sepsis group) and 59 patients with inflammatory infection but not diagnosed as sepsis (the non-sepsis group) received treatment in intensive care unit of Renming Hospital of Wuhan University were collected from July 2020 to January 2021, and 62 cases of healthy physical examination (control group) were simultaneously chosen as control. Sepsis patients were divided into two groups (death group [ n=48] and survival group [ n=89]) according to their 28-day′s survival. The serum levels of GDF15, PCT, C-reactive protein (CRP), interleukin-6 (IL-6) and interleukin-10 (IL-10) were examined, and the levels of each index, was dynamically monitored on the 1st, 3rd and 7th day after admission. The differences of the two indicators between different groups were compared by non-parametric test. The correlation between GDF15 and PCT was analyzed by Spearman correlation test. The receiver operating characteristic (ROC) curve was drawn to evaluate the diagnostic and prognostic value of the two indicators for sepsis. Results:The levels of GDF15 in the sepsis group, non-sepsis group and control group were 3.22 (1.39, 6.31) μg/L, 0.84 (0.21, 1.66) μg/L and 0.11 (0.09, 0.13) μg/L, respectively. The levels of PCT were 13.10 (1.99, 50.25) μg/L, 0.24 (0.13, 0.68) μg/L and 0.05 (0.03, 0.10) μg/L, respectively. The levels of CRP were 115.80 (26.40, 184.07) mg/L, 24.20 (11.30, 53.20) mg/L and 0.50 (0.50, 2.76) mg/L, respectively. The levels of IL-6 were 68.26 (21.59, 255.46) ng/L, 33.20 (10.81, 89.27) ng/L and 8.82 (7.33, 11.23) ng/L, respectively. The levels of IL-10 were 11.30 (5.88, 25.50) ng/L, 9.34 (5.65, 16.90) ng/L and 4.94 (4.31, 5.31) ng/L, respectively. The GDF15, PCT, CRP and IL-6 of the sepsis group were significantly higher than those of the non-sepsis group (The U values were 67.681, 86.034, 44.164 and 38.934, respectively, with P values less than 0.05) and the control group (The U values were 136.475, 138.667, 120.701 and 100.886, respectively, with P values less than 0.001). There was no significant difference in IL-10 between sepsis group and nonsepsis group, but it was higher than that of control group ( U=80.221, P<0.001). There was a positive correlation between GDF15 and PCT in patients with sepsis, and the spearman correlation coefficient was 0.234 ( P=0.006). The GDF15 of the death group and the survival group were 5.49 (3.60, 8.25) μg/L and 2.03 (1.06, 3.69) μg/L, and the PCT levels were 26.45 (11.23, 94.25) μg/L and 9.08 (1.33, 22.75) μg/L, respectively. GDF15 and PCT in the death group were significantly higher than those in the survival group ( U values were 3 305.500 and 3 060.000, respectively, and P values were both less than 0.001). The GDF15 and PCT levels in the death group were higher than those in the survival group on the 1st, 3rd and 7th day of dynamic monitoring ( P<0.05), however, the level of CRP and IL-10 were not significantly different ( P>0.05). The level of IL-6 in the death group was not significantly different from that of the death group on 1st day, but was higher than that of the survival group on the 3rd and 7th day ( P<0.05). The area under the curve (AUC) of GDF15, PCT, CRP, IL-6 and IL-10 alone and in the combined diagnosis of sepsis were 0.899, 0.938, 0.874, 0.789, 0.698 and 0.962, respectively. The combined detection of AUC was better than a single index; the GDF15, PCT, CRP, IL-6 and IL-10 alone and combined detection of sepsis prognosis AUC were 0.774, 0.716, 0.522, 0.623, 0.520 and 0.839, respectively, the combined detection of AUC is also better than single index. Conclusions:GDF15 and PCT have good clinical reference value in the differential diagnosis and prognosis of sepsis. The combination of indicators has a higher clinical value. GDF15 may become a biomarker for the diagnosis and prognosis of sepsis.

Objective:To find clues potentially valuable for fighting against infection with human respiratory syncytial virus (HRSV), the differentially expressed genes in HEp-2 cells infected with HRSV were analyzed.Methods:Gene expression profiles of HEp-2 cells infected with HRSV were collected from the public gene expression omnibus (GEO) database. The differentially expressed genes following HRSV infection at each time point of 4, 8, 12, and 15 hours were found using R language. The differentially expressed genes were analyzed by gene ontology (GO), KEGG pathway and protein-protein interaction network (PPI). Genes with relatively high protein interaction in PPI were randomly selected for quantitative reverse transcription-polymerase chain reaction (qRT-PCR) verification at the transcription level from HEp-2 cells after HRSV infection at 4 hours.Results:A total of 101 differentially expressed genes were determined, including 92 upregulated genes and 9 downregulated genes. Function enrichment analysis revealed that HRSV infection could cause significant changes in multiple signaling pathways such as immune response in HEp-2 cells. The results of qRT-PCR were consistent with the trend of transcriptome data.Conclusions:The differentially expressed genes and the change of signaling pathways in HRSV-infected HEp-2 cells is of great significance to the studies on pathogenic mechanism and prevention of HRSV infection.

To analyze correlation among serum homocysteine (Hcy) ,Cysteine C (CysC) levels and severi‐ ty of coronary artery disease .Methods : A total of 220 coronary heart disease (CHD) patients treated in our hospital from Sep 2015 to Dec 2017 were selected as CHD group .According to Gensini score ,CHD group were divided into mild stenosis group (n＝ 63 ) ,moderate stenosis group (n＝ 71 ) and severe stenosis group (n＝ 86 ).Another 200 healthy people were enrolled as healthy control group .Serum Hcy and CysC levels were measured and compared a‐mong all groups .Correlation among serum Hcy , CysC levels and severity of coronary artery disease were analyzed . Results : Compared with healthy control group ,there were significant rise in serum Hcy [ (8.29 ± 1.02) μmol／L vs. (16. 14 ± 3.01) μmol／L] and CysC [ (0. 65 ± 0.11) mg／L vs.(1. 21 ± 0.12) mg／L] levels in CHD group .P＝0. 001 all.Compared with mild stenosis group ,there were significant rise in serum Hcy [(9. 31 ± 1.12) μmol／L vs.(12. 13 ± 3.32) μmol／L vs.(14.61 ± 3.82) μmol／L] and CysC [ (1.05 ± 0.21) mg／L vs.(1. 51 ± 0. 52) mg／L vs.(3.42 ± 1.01) mg／L] levels in moderate stenosis group and severe stenosis group ,and those of severe stenosis group were significantly higher than those of moderate stenosis group , P＝0.001 all.Pearson correlation analysis indicated that serum Hcy ( r＝0.431 , P＝0.004) , CysC ( r＝0.640 , P＝0. 003) levels were significant positively correlated with Gensini score .Conclusion :Serum Hcy and CysC levels is closely correlated with severity of coronary artery disease . Its detect is help for therapeutic effect and prognosis assessment for CHD patients .

Objective To explore the value of anti-Müllerian hormone (AMH) and age in predicting outcomes of patients undergoing in vitro fertilization and embryo transfer treatment. Methods In this retrospective study, 6 328 Chinese patients who underwent the first in vitro fertilization or intracytoplasmic sperm injection and embryo transfer treatment in Henan Provincial People′s Hospital between July 2016 and July 2018 were analyzed. All the patients were categorized into two groups according to pregnancy or not. Baseline data and outcomes of two groups were compared. The regression analysis was conducted to identify the independent factors of clinical pregnancy rates. Furthermore, correlation analysis was performed between AMH and other factors. Results (1) The total clinical pregnancy rate was 56.86% (3 547/6 238). Age, AMH, basal FSH, antral follicle number (AFC), starting dose of gonadotropin (Gn), total doses of Gn, duration of Gn, number of oocytes, transferable cleavage embryos and transferred embryos were significantly different (all P<0.01). (2) Correlation analysis showed that AMH had significant passive correlation with age, basal FSH, starting dose of Gn and total doses of Gn (all P<0.01), while showed significant positive correlation with AFC, body mass index, duration of Gn, number of oocytes and transferable cleavage embryos (all P<0.01). Of all the factors, AMH had the strongest correlation with AFC (P<0.01). (3) Multivariate logistic regression analysis suggested that age was the independent influencing factor of clinical pregnancy rate ( OR=0.938, 95%CI : 0.824-0.952, P<0.01), while AMH not ( OR=1.004, 95%CI : 0.984-1.024, P=0.687). In the subgroups according to age, the advanced group (age>35 years old) had lower clinical pregnancy rate and higher cancellation rate for no available embryos. Conclusions AMH has no predictive value of clinical pregnancy outcomes for patients with in vitro fertilization and embryo transfer treatment, while age has certain predictive value of pregnancy outcomes. AMH level may have indictive value for the evaluation of ovarian reserve.