Objective To investigate the predictive value of combined radiomic features derived from chest CT scans with clinical characteristics for epidermal growth factor receptor(EGFR)gene mutations in non-small cell lung cancer(NSCLC).Methods A multi-center case-control study was conducted on the clinical data and CT images of 1 070 NSCLC patients from the radiology departments of the 3 medical institutions between January 2013 and October 2023.The 719 NSCLC patients from the First Affiliated Hospital of Army Medical University were randomly divided into a training set and an internal validation set in a ratio of 7∶3;The 173 patients in the Eastern Theatre General Hospital and the 178 patients in Army Medical Centre of PLA were assigned into the external validation set 1 and 2,respectively.Least absolute shrinkage and selection operator(LASSO)regression was employed to identify the optimal radiomic features,which were subsequently used to construct a radiomics model.Univariate and multivariate logistic regression analyses were applied to identify clinical features associated with EGFR mutation,thereby developing a clinical model.The radiomic and clinical features were subsequently combined to develop a comprehensive model.All the 3 classification models were built using random forest(RF)machine learning.The area under curve(AUC),accuracy,sensitivity and specificity were utilized to evaluate the predictive performance of the models.Calibration curve was plotted to assess the goodness of fit of the comprehensive model,while decision curve analysis was performed to assess the clinical utility of the model.Results The AUC value of the radiomics model was 0.762 4(95%CI:0.692 4～0.825 1),0.745 4(95%CI:0.671 1～0.814 3),and 0.724 7(95%CI:0.639 7～0.801 6),respectively,in the internal validation set,external validation set 1,and external validation set 2;The AUC value of the clinical prediction model was 0.691 7(95%CI:0.627 9～0.757 6),0.652 5(95%CI:0.576 7～0.729 1),and 0.779 2(95%CI:0.712 5～0.847 3),respectively in the above sets in turn;The comprehensive model constructed based on clinical features and radiomic features showed the best predictive efficacy,with an AUC value of 0.818 0(95%CI:0.757 7～0.874 3),0.782 4(95%CI:0.703 1～0.848 2),and 0.796 6(95%CI:0.718 1～0.868 6),respectively in the above sets.Calibration curve analysis indicated that the comprehensive model had a good fit,while decision curve analysis revealed that the model provided a favorable net benefit.Conclusion Our comprehensive model constructed based on chest CT radiomic features and clinical characteristics shows superior predictive performance for EGFR gene mutations in NSCLC across multiple center datasets,which may be helpful for clinical decision-making for treatment strategies.

Objective To evaluate the predictive value of deep learning features from chest CT images combined with clinical and radiomics features for epidermal growth factor receptor(EGFR)mutations in non-small cell lung cancer(NSCLC).Methods This case-control study retrospectively analyzed clinical and imaging data of 1 070 NSCLC patients from radiology departments at three hospitals(January 2013 to October 2023).Patients were divided into:a training set(n=502)and internal validation set(n=217)via 7∶3 randomization of 719 cases from the First Affiliated Hospital of Army Medical University;external validation set 1(n=173)from General Hospital of Eastern Theater Command;external validation set 2(n=178)from Daping Hospital of Army Medical University.Deep learning features were extracted using a 2.5D convolutional neural network(CNN)with ResNet101 backbone,radiomics features were derived from CT images,and clinical risk factors were identified to construct models.An integrated model combined deep learning,clinical,and radiomics features.All four models were developed using random forest(RF)classifiers.Calibration curves assessed goodness-of-fit,and decision curve analysis(DCA)evaluated clinical utility.Results The deep learning model achieved AUCs of 0.833 7(95%CI:0.770 6～0.884 7),0.815 1(0.741 6～0.882 8),and 0.810 1(0.745 2～0.873 6)in the internal and two external validation sets,respectively.Clinical models yielded AUCs of 0.731 0(0.660 2～0.802 1),0.746 0(0.666 4～0.824 9),and 0.813 4(0.743 1～0.883 6);radiomics models showed AUCs of 0.762 4(0.692 4～0.825 1),0.745 4(0.671 1～0.814 3),and 0.724 7(0.639 7～0.801 6).The integrated model demonstrated optimal performance with AUCs of 0.905 5(0.857 0～0.945 4),0.832 7(0.763 3～0.896 4),and 0.889 0(0.834 4～0.934 3).DCA indicated significant net benefit for EGFR prediction at threshold probabilities of 0.15～0.85 using the integrated model.Conclusion Deep learning features from CT images effectively predict EGFR mutation status in NSCLC.The integrated model combining deep learning,clinical,and radiomics features further enhances predictive performance.

Objective This study aims to investigate the role of genes related to fatty acid metabolism in periodon-titis through machine learning and bioinformatics methods.Methods Periodontitis datasets GSE10334 and GSE-16134 were downloaded from the GEO database,and the fatty acid metabolism-related gene sets were obtained from the GeneCards database.Differentially expressed fatty acid metabolism-related genes(DEFAMRGs)in periodontitis were screened using the"limma"R package.Functional enrichment and pathway analyses were conducted.Recursive Feature Elimination,Least Absolute Shrinkage and Selection Operator,and Boruta algorithm were used to determine hub DEFAMRGs and construct diagnostic models with internal and external validation.Subtypes of periodontitis relat-ed to hub DEFAMRGs were constructed using consis-tency clustering analysis.CIBERSORT was used to ana-lyze immune cell infiltration in gingival tissues and ex-plore the correlation between hub DEFAMRGs and im-mune cells.Results A total of 113 periodontitis DE-FAMRGs were screened out as a result.The enrichment analysis results indicate that DEFAMRGs are mainly associat-ed with immune inflammatory responses and immune cell chemotaxis.Finally,8 hub DEFAMRGs(BTG2,CXCL12,FABP4,CLDN10,PPBP,RGS1,LGALSL,and RIF1)were identified and a diagnostic model(AUC=0.967)was con-structed,based on which periodontitis was divided into two subtypes.In addition,there is a significant correlation be-tween hub DEFAMRGs and different immune cell populations,with mast cells and dendritic cells showing higher cor-relation.Conclusion This study provides new insights and ideas for the occurrence and development mechanism of periodontitis and proposes a diagnostic model based on hub DEFAMRGs to provide new directions for diagnosis and treatment.

Objective:To analyze the genetic landscape of multiple fusion genes in patients with de novo acute myeloid leukemia (AML) and investigate the characteristics of immunophenotypes and mutations.Methods:The results of multiple fusion genes from 4192 patients with de novo AML were retrospectively analyzed from 2016 to 2020. In addition, the immunophenotypical data and the mutational results from high-through put method were statistically investigated and correlated as well.Results:①Among the 52 targets, 29 different types of fusion genes were detected in 1948 patients (46.47%) with AML, which demonstrated an "exponential distribution" . ② As the age increased, the number of patients with fusion gene increased first and then decreased gradually. The total incidence rate of fusion genes and MLL rearrangment in children were significantly higher than those in adults (69.18% vs 44.76%, 15.35% vs 8.36%) . ③The mutations involving FLT3 and RAS signaling pathway contributed most in patients with MLL rearrangment. ④No specific immunophenotypic characteristics were found in AML patients with MLL or NUP98 rearrangements. Conclusion:Nearly half of AML patients were accompanied by specific fusion gene expression, the proportions of different fusion genes in pediatric and adults patients were different by multiple PCR. The gene mutations and immunophenotype of these AML patients have certain rules.

Objective:To evaluate the promoting surgery incision healing effect of recombinant human acidic fibroblast growth fac-tor ( rh-aFGF) in the treatment of children with open fractures. Methods:A multicenter, randomized and controlled clinical trial was conducted to study the efficacy of rh-aFGF. Totally 120 cases of injured children (age<14y) were randomly divided into two groups, the treatment group (n=60) was given rh-aFGF washing during the operation and spraying after the operation, and the control group ( n=60) was treated with normal saline. Both groups were given traction, screw or Kirschner wire fixation. The healing time, healing status and delayed healing were observed and compared in the two groups. Results:Stage I healing rate, the complete healing time and delayed healing rate in the treatment group was 86. 6%, (20. 3 ± 5. 6)d and 3. 3%, respectively, while that in the control group was 56.7%, (23.4 ±6.2)d and 15.0%, respectively. The differences between the two groups were significant (P<0.05 or 0.01). Conclusion:Rh-aFGF can effectively promote wound healing and shorten the healing time. For all these positive aspects,rh-aFGF de-serves wider clinical application in postoperative rehabilitation after open fractures.

Objective To investigate characteristics of memory-guided saccade in Parkinson' s disease (PD),and to evaluate the application of memory-guided saccade in diagnosing PD.Methods Fiftythree subjects with early- or mid- stage PD were chosen as PD group,meanwhile,36 age-matched healthy subjects were chosen as control group.Memory-guided saccade test and event-related potential P300 were performed in all subjects,and results of the two groups were compared; furthermore,results of subgroups comprised of 29 patients with early-stage PD were analyzed.Results In comparison with control group,memory-guided saccade in PD group showed decreased velocity and primary gain,prolonged latency,extremely increased incidence of unwanted saccade and multi-step saccade ( U =124.000,37.000;both P ＜0.01 ),such abnormalities has already stood out even in subgroup comprised of early-stage PD patients.Meanwhile,latency of event-related potential P300 in PD group was prolonged compared with control group ((384.76 ± 34.48) ms vs (352.42 ± 24.99) ms,t =- 4.791,P ＜ 0.01 ).Multi-step saccade measurement demonstrated excellent sensitivity (96.2％ ) and specificity (94.4％) in the ability to discriminate PD patients from controls.Conclusion Memory-guided saccade in PD patients shows highly abnormal which may reflect the impairment of pontine saccade pathway and the dysfunction of frontal lobe.Memory-guided saccade test may be a useful examination in assisting the diagnosis of PD.

Objective To investigate the systemic effects of Helicobacter pylori (Hp) infection by comparing differential counts of leukocytes in peripheral blood and C-reactive protein (CRP) levels before and after eradication of Hp. Method A total of 158 Hp-positive patients underwent eradication by standard one-week triple therapy were divided into Hp eradicated group(n = 108) and Hp non-eradicated group(n = 50),the populations of peripheral blood leukocytes and CRP levels before and 0 (just after therapy),1 and 12 months after eradication were retrospectively analysed. Results In the eradicated group,blood leukecytes,neutrophils and monocytes decreased significantly after eradication,and the CRP levels were significantly lower than the levels before treatment (P < 0.05 ),but there was no significant change in eosinophils,basophils and lymphecytes (P > 0.05).In the non-eradicated group,there was no significant change in any studied pa-rameter (P > 0.05). Conclusion These findings suggest that Hp infection increase blood leukocytes,neu-trophil and monocyte counts in the peripheral blood and CRP levels,which indicates a significant role of Hp infection in systemic disorders.