Objective: To construct and compare risk prediction models for severe hand-foot-mouth disease (HFMD), analyze the influencing factors of severe HFMD, so as to provide a reference for early identification and intervention of severe HFMD. Methods: HFMD patients who were hospitalized in a hospital in Zhengzhou City from November 2018 to December 2021 were selected as study subjects. Demographic information, clinical symptoms, and laboratory test indicators were collected. The subjects were randomly divided into a training set and a validation set at a 7∶3 ratio. According to the Guidelines for Diagnosis and Treatment of Hand-Foot-Mouth Disease (2018 Edition), the patients were divided into a mild HFMD group and a severe HFMD group. Variables with statistically significant differences between the two groups were identified as predictive variables. Random forest model, linear support vector machine (LSVM) model, and logistic regression model were constructed. The predictive performance of the three models was evaluated using accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC). Results: A total of 1 650 HFMD patients were included, including 1 094 males (66.30%) and 556 females (33.70%). The mean age was (1.97±1.17) years. There were 1 293 cases in the mild HFMD group (78.36%) and 357 cases in the severe HFMD group (21.64%). The accuracy of random forest model, LSVM model, and logistic regression model in predicting severe HFMD were 95.76%, 88.28%, and 88.08%, respectively. The sensitivity were 94.55%, 59.09%, and 58.18%, respectively. The specificity were 96.10%, 96.66%, and 96.66%, respectively. The AUC values were 0.981, 0.895, and 0.899, respectively. The random forest model results showed that the top three important predictors for severe HFMD were neutrophil ratio, alanine aminotransferase, and platelet count. Conclusions The constructed random forest model demonstrates good predictive performance and can be applied in predicting severe HFMD. It is recommended to pay attention to changes in neutrophil ratio, alanine aminotransferase, and platelet count in HFMD patients, which can assist in early identification and intervention of severe HFMD.

Objective:To develop an artificial intelligence (AI)-based automatic scoring model for magnetic resonance imaging-detected extramural vascular invasion (AI-mrEMVI) and evaluate its performance and prognostic value in patients with rectal cancer.Methods:In this multicenter retrospective cohort study, a total of 2 501 rectal cancer patients from seven centers between November 2012 and December 2020 were included and divided into completely independent training ( n=1 830) and validation ( n=671) cohorts. A nnUNet-based AI-mrEMVI scoring model was constructed. Manual mrEMVI scores assigned by two radiologists served as the reference standard for accessing the accuracy of the AI-mrEMVI scoring. Kaplan-Meier survival analysis and Cox regression were used to evaluate the prognostic stratification ability of the AI-mrEMVI scores. The concordance index (C-index) was calculated to evaluate prognostic performance. Results:In the validation cohort, the manual mrEMVI scores were 0-2 in 425 patients (63.3%), 3 in 89 (13.4%), and 4 in 157 (23.4%). The AI-mrEMVI model identified 0-2 in 375 patients (55.9%), 3 in 95 (14.2%), and 4 in 201 (30.0%), with an overall accuracy of 81.1% (544/671, 95% CI 77.9%-84.0%). The 3-year disease-free survival (DFS) rates for patients with AI-mrEMVI scores of 0-2, 3, and 4 were 85.2%, 70.0%, and 58.2%, respectively, and the 5-year overall survival (OS) rates were 87.2%, 81.6%, and 62.6%, respectively (DFS: χ2=48.74, P<0.001; OS: χ2=30.04, P<0.001). Multivariable Cox regression showed that for DFS, AI-mrEMVI scores of 3 and 4 were associated with hazard ratios ( HR) of 1.75 (95% CI 1.11-2.77, P=0.016) and 2.65 (95% CI 1.86-3.78, P<0.001), respectively. For OS, an AI-mrEMVI score of 4 was associated with an HR of 2.56 (95% CI 1.62-4.03, P<0.001). The C-index values of the AI-mrEMVI scoring model for predicting DFS and OS were 0.647 (95% CI 0.608-0.686) and 0.650 (95% CI 0.598-0.702), respectively. Conclusion:The proposed AI-mrEMVI automatic scoring model demonstrated high diagnostic accuracy and performed favorably in predicting DFS and OS prognostic risk in patients with rectal cancer.

Objective:To develop an artificial intelligence (AI)-based automatic scoring model for magnetic resonance imaging-detected extramural vascular invasion (AI-mrEMVI) and evaluate its performance and prognostic value in patients with rectal cancer.Methods:In this multicenter retrospective cohort study, a total of 2 501 rectal cancer patients from seven centers between November 2012 and December 2020 were included and divided into completely independent training ( n=1 830) and validation ( n=671) cohorts. A nnUNet-based AI-mrEMVI scoring model was constructed. Manual mrEMVI scores assigned by two radiologists served as the reference standard for accessing the accuracy of the AI-mrEMVI scoring. Kaplan-Meier survival analysis and Cox regression were used to evaluate the prognostic stratification ability of the AI-mrEMVI scores. The concordance index (C-index) was calculated to evaluate prognostic performance. Results:In the validation cohort, the manual mrEMVI scores were 0-2 in 425 patients (63.3%), 3 in 89 (13.4%), and 4 in 157 (23.4%). The AI-mrEMVI model identified 0-2 in 375 patients (55.9%), 3 in 95 (14.2%), and 4 in 201 (30.0%), with an overall accuracy of 81.1% (544/671, 95% CI 77.9%-84.0%). The 3-year disease-free survival (DFS) rates for patients with AI-mrEMVI scores of 0-2, 3, and 4 were 85.2%, 70.0%, and 58.2%, respectively, and the 5-year overall survival (OS) rates were 87.2%, 81.6%, and 62.6%, respectively (DFS: χ2=48.74, P<0.001; OS: χ2=30.04, P<0.001). Multivariable Cox regression showed that for DFS, AI-mrEMVI scores of 3 and 4 were associated with hazard ratios ( HR) of 1.75 (95% CI 1.11-2.77, P=0.016) and 2.65 (95% CI 1.86-3.78, P<0.001), respectively. For OS, an AI-mrEMVI score of 4 was associated with an HR of 2.56 (95% CI 1.62-4.03, P<0.001). The C-index values of the AI-mrEMVI scoring model for predicting DFS and OS were 0.647 (95% CI 0.608-0.686) and 0.650 (95% CI 0.598-0.702), respectively. Conclusion:The proposed AI-mrEMVI automatic scoring model demonstrated high diagnostic accuracy and performed favorably in predicting DFS and OS prognostic risk in patients with rectal cancer.

Objective To establish an ultra-high performance liquid chromatography with quadrupole time-of-flight mass spectrometry(UPLC-QTOF-MS)method for identifying the active ingredients of Zhizi Houpu decoction,and to predict its material basis and mechanism of anti-insomnia effects using network pharmacology.Methods The chemical components of Zhizi Houpu decoction were identified according to UHPLC-QTOF-MS ion fragmentation rule combined with compound library and literature review.Components with oral bioavailability(OB)≥30％and drug-like properties(DL)≥0.18 were selected to construct the Zhizi Houpu decoction-active ingredients-target network.The STRING database and the Database for Annotation,Visualization,and Integrated Discovery(DAVID)were used to screen key target proteins.Subsequently,enrichment analysis was performed for biological processes,molecular functions,cellular components,and signaling pathways.Results A total of 107 chemical components were identified,including 35 compounds related to insomnia and 11 anti-insomnia targets such as AKT serine/threonine kinase 1,tumor protein 53,and prostaglandin-endoperoxide synthase 2.Gene Ontology functional enrichment analysis indicated that Zhizi Houpo decoction may exert its effects through cellular components such as the presynaptic membrane,dendrite,and plasma membrane,by participating in biological processes like chemical synaptic transmission,G protein signaling pathway,and neuron apoptosis,and by regulating molecular functions such as G protein-coupled serotonin receptor activity.Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis revealed that its anti-insomnia effects were mainly concentrated in pathways such as neuroactive ligand-receptor interaction,calcium signaling pathway,serotonergic synapse,and cyclic adenosine monophosphate signaling pathway.Conclusion The anti-insomnia effect of Zhizi Houpo decoction is the result of a synergistic action involving multiple components,multiple targets,and multiple pathways.Its material basis and mechanism of action are primarily related to regulating biological processes such as neurotransmitter metabolism,synaptic function,neuronal apoptosis,and inflammatory response.

Objective:To investigate the effect of peripheral blood immune cell level changes on the severity of hand,foot and mouth disease(HFMD).Methods:A total of 1 079 patients with mild and severe HFMD diagnosed and treated in The Fifth Affiliated Hospital of Zhengzhou University and Henan Children's Hospital from April 2015 to December 2018 were collected and divided into 5 subgroups according to the time from the onset of symptoms and signs to the first diagnosis.Trend of peripheral blood immune cells in each subgroup with the course of disease was plotted.Spearman coefficient and multiple Logistic regression analysis were used to screen risk factors of severe HFMD with the course of disease.Results:Univariate analysis indicated that levels of T cells,Ts and Th in severe group were lower than those in mild group,while levels of NK cells and B cells were higher than those in mild group(P<0.05).Correlation analysis showed a strong negative correlation between T cells and B cells(rs=-0.687)and NK cells(rs=-0.486).Logistic regression analysis showed that the reduction of immune cells(T cells,Ts,Th,LYM)in the course of disease from 1 to 5 days was statistically significant between mild and severe groups(P<0.05).Proportion of B cells was increased in mild and severe groups from 1～4 days(P<0.05),and NK cells was increased in mild and severe groups on day 2 of the course of disease(P<0.05).Proportion of severe patients living in rural areas with body temperature>39.0℃was significantly higher than that of mild patients(P<0.05).Conclusion:Disease progression of patients with severe HFMD is closely related to the disorder of immune cell regulatory function.Early monitoring of changes in peripheral blood lymphocyte subsets in HFMD patients can determine the progression of se-vere HFMD disease,and attention should be paid to changes in children living in rural areas with body temperature>39.0℃.

Objective:To investigate the effect of peripheral blood immune cell level changes on the severity of hand,foot and mouth disease(HFMD).Methods:A total of 1 079 patients with mild and severe HFMD diagnosed and treated in The Fifth Affiliated Hospital of Zhengzhou University and Henan Children's Hospital from April 2015 to December 2018 were collected and divided into 5 subgroups according to the time from the onset of symptoms and signs to the first diagnosis.Trend of peripheral blood immune cells in each subgroup with the course of disease was plotted.Spearman coefficient and multiple Logistic regression analysis were used to screen risk factors of severe HFMD with the course of disease.Results:Univariate analysis indicated that levels of T cells,Ts and Th in severe group were lower than those in mild group,while levels of NK cells and B cells were higher than those in mild group(P<0.05).Correlation analysis showed a strong negative correlation between T cells and B cells(rs=-0.687)and NK cells(rs=-0.486).Logistic regression analysis showed that the reduction of immune cells(T cells,Ts,Th,LYM)in the course of disease from 1 to 5 days was statistically significant between mild and severe groups(P<0.05).Proportion of B cells was increased in mild and severe groups from 1～4 days(P<0.05),and NK cells was increased in mild and severe groups on day 2 of the course of disease(P<0.05).Proportion of severe patients living in rural areas with body temperature>39.0℃was significantly higher than that of mild patients(P<0.05).Conclusion:Disease progression of patients with severe HFMD is closely related to the disorder of immune cell regulatory function.Early monitoring of changes in peripheral blood lymphocyte subsets in HFMD patients can determine the progression of se-vere HFMD disease,and attention should be paid to changes in children living in rural areas with body temperature>39.0℃.

Objective: To explore the clinical application value of neural network technology,and to screen the clinical early warning indicators of severe hand-foot-mouth disease(HFMD) by constructing a back propagation neural network(BPNN) model. Methods: The clinical data of children with HFMD admitted to the Department of Infectious Diseases and Pediatrics of the First Affiliated Hospital of Xinxiang Medical University from January2019 to January 2023 were collected.The data were divided into 70% training samples and 30 % test samples using SPSS Modeler 18.0.The BPNN model and Logistic model were constructed to compare and evaluate the prediction accuracy and screening effect of the model. Results: The clinical data of 589 children were collected and analyzed,including 324 cases in the mild group and 265 cases in the severe group.The prediction accuracy of the test set(n=178) of BP neural network model and Logistic regression model was 82.02% and 84.83%,respectively.The area under the ROC curve(95% CI) was 0.791(0.749-0.834) and 0.625(0.577-0.674),respectively.Among the predictive variables output by the BPNN model,the top five factors that had the greatest impact on the grouping were highest body temperature,duration of fever,glutamyl transpeptidase,aspartate aminotransferase,and globulin.There were 3 of the top 10 overlaps in the importance of the predictive variables output by the two models,which were the highest body temperature,duration of fever and limb shaking. Conclusion The BPNN model and Logistic regression model perform well in screening and verifying the risk factors of severe hand-foot-mouth disease,but the comprehensive prediction performance of BP neural network model is better.The top five influencing factors of severe HFMD screened by the BPNN model are the highest body temperature,duration of fever,glutamyl transpeptidase,aspartate aminotransferase and globulin.

Objective To investigate the value of transient elastography (FibroScan) and platelet count-to-spleen thickness (PC/ST) ratio in predicting the degree of esophageal and gastric varices (EGV) in liver cirrhosis. Methods A total of 210 patients with liver cirrhosis who underwent FibroScan, color Doppler ultrasound, electronic gastroscopy, and blood biochemical examination within three days after admission to The Fifth Affiliated Hospital of Zhengzhou University from January 2017 to September 2020 were enrolled, and according to the "gold standard" of gastroscopy, the patients were divided into none, mild, moderate, and severe EGV groups. A one-way analysis of variance or the Kruskal-Wallis H test were used for comparison of continuous data between multiple groups. Receiver operating characteristic (ROC) curves were plotted for liver stiffness measurement (LSM), PC/ST ratio, and LSM+PC/ST, and the diagnostic performance of these ROC curves was compared using the Delong method. Results There were significant differences between the none, mild, moderate, and severe EGV groups in LSM ( F =32.00, P < 0.01) and PC/ST ratio ( H =49.58, P < 0.01). For the mild EGV group, LSM, PC/ST ratio, and LSM+PC/ST had an area under the ROC curve (AUC) of 0.762, 0.656, and 0.770, respectively, with a positive predictive value of 75.4%, 60.2%, and 82.5%, respectively, and a negative predictive value of 75.0%, 75.8%, and 65.4%, respectively. For the moderate EGV group, LSM, PC/ST ratio, and LSM+PC/ST had an AUC of 0.841, 0.796, and 0.896, respectively, with a positive predictive value of 86.1%, 68.0%, and 74.1%, respectively, and a negative predictive value of 79.7%, 80.5%, and 90.2%, respectively. For the severe EGV group, LSM, PC/ST ratio, and LSM+PC/ST had an AUC of 0.834, 0.830, and 0.903, respectively, with a positive predictive value of 80.5%, 71.4%, and 79.5%, respectively, and a negative predictive value of 82.5%, 83.6%, and 85.0%, respectively. PC/ST ratio and LSM+PC/ST had significantly different AUC in predicting mild, moderate, and severe EGV ( Z =2.66, P =0.007; Z =2.71, P =0.007; Z =2.37, P =0.018). Conclusion LSM, PC/ST ratio, and LSM+PC/ST have a good predictive value for moderate-to-severe EGV in liver cirrhosis.

Objective: To investigate the profiles of blood amino acid and acylcarnitine in early neonates with neonatal intrahepatic cholestasis caused by citrin deficiency (NICCD) and the sensitivity of newborn screening, and to explore potential biochemical metabolic markers for newborn screening program. Methods: Amino acid and acylcarnitine profiles in dried blood spots of newborn screening program were analyzed by tandem mass spectrometry (MS/MS). A total of 158 651 neonates born in Guangzhou from January 1, 2015 to June 30, 2019 were enrolled in this newborn screening program, and additionally 55 patients with NICCD confirmed by SLC25A13 gene analysis in Guangzhou Women and Children Medical Center were included in this study. NICCD screen-positive was defined as the cutoff value of citrulline (Cit) ≥ 30 μmol/L. The values of blood sampling time of the true positive group and those of the false negative group were compared by t-test. The levels of amino acid and acylcarnitine among different groups, including true positive group (Cit≥30 μmol/L), false negative group (Cit 21-<30 μmol/L and Cit<21 μmol/L) and the normal control group, were analyzed by F test, respectively. Results: Among 158 651 neonates, 39 neonates were positive for NICCD screening. Three of them were confirmed NICCD and 4 cases were found to be false negatives. The positive predictive value was 7.7% and the sensitivity was about 43.0%. Among 55 patients with NICCD, 18 cases (18/55, 32.7%) were true positives and 37 cases (37/55, 67.3%) were false negatives based on the cutoff value of citrulline in the dried blood spots for newborn screening. The blood sampling time was significantly different between true positive group and false negative group ((4.28±1.6) vs. (2.98±0.74) d, t=4.06, P<0.01). The increased levels of tyrosine((176.0±98.4) μmol/L), methionine ((37.0±26.9) μmol/L) and phenylalanine ((133.0±80.9)μmol/L) in Cit≥30 μmol/L group (n=18) were significantly different as compared with those in the other three groups, respectively (F=117.0, 58.5, 135.0, P<0.01). The levels of arginine ( (10.0±9.2) , (11.0±9.3) , (9.0±17.8) μmol/L), valine ( (119.0±29.8) , (107.6±14.1) , (102±68) μmol/L) and leucine ( (167.0±37.1) , (161.0±37.7) , (163.5±180.6) μmol/L) were not statistically significant among groups of Cit≥30 μmol/L(n=18), Cit21-<30 μmol/L(n=7) and Cit<21μmol/L(n=30,P>0.05), but they were significantly higher than those of the normal control group ((4±3), (78±21), (114.0±31.5) μmol/L, n=1 000), respectively(F=30.1, 23.0, 29.8, P<0.01). Alanine (Ala) ( (150±50) , (156.0±30.2), (168±105), (152±52) μmol/L) levels showed no significant difference (F=0.86, P>0.05) but the ratios of Ala/Cit (1.52±1.44, 6.82±1.56, 12.06±7.71, 19.42±6.27) decreased significantly among the four groups (F=69.0, P<0.05). The acylcarnitine levels showed no statistically significant results among the different groups (P>0.05). With Cit≥30 μmol/L and Ala/Cit<7.5 as cutoff values, the number of screen-positive cases reduced from 39 to 22 cases with no additional false negative case. With Cit≥21 μmol/L and Ala/Cit<7.5 as cutoff values the number of screen-positive cases increased to 117 cases with 1 additional true positive. Conclusions The profiles of blood amino acid in early neonates with NICCD present the increased levels of multiple amino acids including citrulline, tyrosine, methionine and phenylalanine, and decreased ratio of Ala/Cit. Taking citrulline and ratio of Ala/Cit as screening markers can improve the positive predictive value appropriately. The limited sensitivity of NICCD newborn screening may be related to early blood sampling time.

Objective To explore the effect of drug injection under bronchoscopy on the retreatment of smear positive cavitary pulmonary tuberculosis. Methods From June 2016 to December 2017,164 cases of pul-monary tuberculosis with smear Yang cavity type were selected,which were divided into 2 groups according to the random digital table method,each groups has 82 cases.The control group received routine treatment,the observa-tion group underwent bronchoscopy with Kangfuxin Liquid combined with drug injection therapy.The clinical effect of the two groups,the changes of lung function before and after treatment and the improvement of clinical symp-toms were compared.Results The clinical curative effect of the treatment group was better than the control group, which difference was statistically significant(P < 0.05). FEV1,FEV1/FVC,PEF index in the observation group were better than the control group,which difference was statistically significant(P<0.05).The complication rate of observation group was lower than the control group,which difference was statistically significant(P < 0.05). Conclusion Drug injection under bronchoscopy can significantly improve the clinical efficacy and lung function and promote clinical symptoms in patients with retreated smear positive pulmonary tuberculosis.It is worthy of popu-larization and application.