Objective Exploring the performance of a sensitivity recognition model for neoadjuvant therapy based on ensemble learning algorithms for predicting neoadjuvant therapy sensitive patients.Methods In this study,255 rectal cancer patients who underwent standard neoadjuvant therapy and surgery at the Affiliated Cancer Hospital of Harbin Medical University were collected,of which 139 patients were sensitive to neoadjuvant therapy and 116 patients were not.The recursive feature elimination method was used to screen deep learning features and imaging histology features to construct an integrated learning model.The generalization performance of the model was verified using the leave-out method,and the sensitivity,specificity,positive predictive value,negative predictive value,accuracy,G-mean,F-measure,Mathews correlation coefficient(MCC),and area under the receiver operating charactpristic curve(AUC)were used to evaluate and compare the model performance.Results The performance of the integrated model on the external validation set was:an AUC value of 0.916(95％CI:0.899 to 0.935),a sensitivity of 1.000,a specificity of 0.833,a positive predictive value of 0.875,a negative predictive value of 1.000,an accuracy of 0.923,a G-mean of 0.913,an F-measure of 0.933,a MCC was 0.854.Conclusion The integration model of depth features and imaging omics features is superior to the individual depth feature model and imaging omics feature model,and has good practicality and reliability in identifying sensitive patients with neoadjuvant therapy,which can be used as a reference for clinical practice.

Objective To evaluate the clinical efficacy of hip-knee-ankle active and passive exercise therapy in patients with early-to mid-stage knee osteoarthritis(KOA).Methods A total of 180 patients with early to mid-stage knee osteoarthritis(KOA)were recruited from the First Affiliated Hospital of Hebei University of Tradi-tional Chinese Medicine between March 2023 and March 2024.Patients were randomly assigned to one of four groups:active movement group,passive movement group,combined movement group,and control group,with 45 patients in each group.The active movement group received hip-knee-ankle active movement therapy daily until the end of follow-up.The passive movement group underwent hip-knee-ankle passive movement therapy three times per week for two weeks.The combined movement group received both active and passive therapies.The control group was administered oral celecoxib capsules(200 mg once daily for two weeks).Joint function was assessed in all four groups before treatment,at two weeks post-treatment,and at 14 weeks post-treatment.The primary outcome measure was the WOMAC joint function score,while secondary outcomes included the WOMAC pain score,stiffness score,and quality of life score(SF-12).Results A total of 160 patients completed the trial,with 39 in the active group,42 in the passive group,40 in the combined group,and 39 in the control group.There were no significant differences in baseline characteristics among the groups(P>0.05).Compared to baseline,the WOMAC scores for function,pain,and stiffness in the passive,combined,and control groups decreased significantly at both 2 and 14 weeks post-treatment(P<0.05),while the SF-12 scores increased significantly(P<0.05).Between 2 and 14 weeks post-treat-ment,the active and combined groups showed further significant decreases in WOMAC function,pain,and stiffness scores(P<0.05)and increases in SF-12 scores(P<0.05).At 2 weeks post-treatment,compared to the control group,the passive and combined groups exhibited significantly lower WOMAC function scores(P<0.05),with no significant difference between the passive and combined groups(P>0.05).By 14 weeks post-treatment,the active and combined groups demonstrated significantly lower WOMAC function scores(P<0.05),with the combined group showing a significantly lower score than the active group(P<0.05).Conclusion The four therapeutic approaches demonstrate a certain degree of efficacy in improving joint function for patients with early and mid-stage KOA.The passive therapy group exhibits superior short-term outcomes,while the active therapy group shows better long-term benefits.The combined therapy group presents notable advantages in both short-term and long-term effi-cacy,although its short-term effectiveness does not surpass that of the passive therapy group.It is recommended for patients with early and mid-stage KOA who have underlying gastrointestinal and cardiovascular conditions.

Objective To evaluate the clinical efficacy of hip-knee-ankle active and passive exercise therapy in patients with early-to mid-stage knee osteoarthritis(KOA).Methods A total of 180 patients with early to mid-stage knee osteoarthritis(KOA)were recruited from the First Affiliated Hospital of Hebei University of Tradi-tional Chinese Medicine between March 2023 and March 2024.Patients were randomly assigned to one of four groups:active movement group,passive movement group,combined movement group,and control group,with 45 patients in each group.The active movement group received hip-knee-ankle active movement therapy daily until the end of follow-up.The passive movement group underwent hip-knee-ankle passive movement therapy three times per week for two weeks.The combined movement group received both active and passive therapies.The control group was administered oral celecoxib capsules(200 mg once daily for two weeks).Joint function was assessed in all four groups before treatment,at two weeks post-treatment,and at 14 weeks post-treatment.The primary outcome measure was the WOMAC joint function score,while secondary outcomes included the WOMAC pain score,stiffness score,and quality of life score(SF-12).Results A total of 160 patients completed the trial,with 39 in the active group,42 in the passive group,40 in the combined group,and 39 in the control group.There were no significant differences in baseline characteristics among the groups(P>0.05).Compared to baseline,the WOMAC scores for function,pain,and stiffness in the passive,combined,and control groups decreased significantly at both 2 and 14 weeks post-treatment(P<0.05),while the SF-12 scores increased significantly(P<0.05).Between 2 and 14 weeks post-treat-ment,the active and combined groups showed further significant decreases in WOMAC function,pain,and stiffness scores(P<0.05)and increases in SF-12 scores(P<0.05).At 2 weeks post-treatment,compared to the control group,the passive and combined groups exhibited significantly lower WOMAC function scores(P<0.05),with no significant difference between the passive and combined groups(P>0.05).By 14 weeks post-treatment,the active and combined groups demonstrated significantly lower WOMAC function scores(P<0.05),with the combined group showing a significantly lower score than the active group(P<0.05).Conclusion The four therapeutic approaches demonstrate a certain degree of efficacy in improving joint function for patients with early and mid-stage KOA.The passive therapy group exhibits superior short-term outcomes,while the active therapy group shows better long-term benefits.The combined therapy group presents notable advantages in both short-term and long-term effi-cacy,although its short-term effectiveness does not surpass that of the passive therapy group.It is recommended for patients with early and mid-stage KOA who have underlying gastrointestinal and cardiovascular conditions.

Cardiovascular diseases and psychological disorders represent two major threats to human physical and mental health. Research on electrocardiogram (ECG) signals offers valuable opportunities to address these issues. However, existing methods are constrained by limitations in understanding ECG features and transferring knowledge across tasks. To address these challenges, this study developed a multi-resolution feature encoding network based on residual networks, which effectively extracted local morphological features and global rhythm features of ECG signals, thereby enhancing feature representation. Furthermore, a model compression-based continual learning method was proposed, enabling the structured transfer of knowledge from simpler tasks to more complex ones, resulting in improved performance in downstream tasks. The multi-resolution learning model demonstrated superior or comparable performance to state-of-the-art algorithms across five datasets, including tasks such as ECG QRS complex detection, arrhythmia classification, and emotion classification. The continual learning method achieved significant improvements over conventional training approaches in cross-domain, cross-task, and incremental data scenarios. These results highlight the potential of the proposed method for effective cross-task knowledge transfer in ECG analysis and offer a new perspective for multi-task learning using ECG signals.
Humans ; Electrocardiography/methods* ; Mental Health ; Algorithms ; Signal Processing, Computer-Assisted ; Machine Learning ; Arrhythmias, Cardiac/diagnosis* ; Cardiovascular Diseases ; Neural Networks, Computer ; Mental Disorders

Objective Exploring the performance of a sensitivity recognition model for neoadjuvant therapy based on ensemble learning algorithms for predicting neoadjuvant therapy sensitive patients.Methods In this study,255 rectal cancer patients who underwent standard neoadjuvant therapy and surgery at the Affiliated Cancer Hospital of Harbin Medical University were collected,of which 139 patients were sensitive to neoadjuvant therapy and 116 patients were not.The recursive feature elimination method was used to screen deep learning features and imaging histology features to construct an integrated learning model.The generalization performance of the model was verified using the leave-out method,and the sensitivity,specificity,positive predictive value,negative predictive value,accuracy,G-mean,F-measure,Mathews correlation coefficient(MCC),and area under the receiver operating charactpristic curve(AUC)were used to evaluate and compare the model performance.Results The performance of the integrated model on the external validation set was:an AUC value of 0.916(95％CI:0.899 to 0.935),a sensitivity of 1.000,a specificity of 0.833,a positive predictive value of 0.875,a negative predictive value of 1.000,an accuracy of 0.923,a G-mean of 0.913,an F-measure of 0.933,a MCC was 0.854.Conclusion The integration model of depth features and imaging omics features is superior to the individual depth feature model and imaging omics feature model,and has good practicality and reliability in identifying sensitive patients with neoadjuvant therapy,which can be used as a reference for clinical practice.

Colorectal cancer is one of the most common malignant tumors, which is a great threat to human life and health. The change of bile acid homeostasis can activate their corresponding receptors to regulate the immune functions, which is closely related to the occurrence of colorectal cancer. In addition, some bile acids can directly induce colorectal cancer and play an important role in the development of colorectal cancer. In this paper, the metabolic process of bile acids in vivo and the immunomodulatory role of bile acid receptors were reviewed, and the evidence of associations between bile acids and colorectal cancer were summarized, which showed the rebalancing the bile acid levels might play a role in the prevention or treatment of colorectal cancer.

Objective To summarize the clinical characteristics of delayed diagnosis of tuberculosis in children,analyze the risk factors of delayed diagnosis,and support early diagnosis of tuberculosis in children.Methods This is a retrospective analysis based on the clinical data of tuberculosis patients admitted to the Children's Hospital Affiliated to Zhengzhou University from January 2015 to February 2023.The clinical characteristics of children were analyzed in terms of age group.According to the definition of diagnosis delay,the patients were assigned to delayed group and non-delayed group.Univariate analysis and multivariate logistic regression were used to analyze the risk factors for diagnosis delay.Results A total of 82 children with tuberculosis were included(46 cases in delayed diagnosis group and 36 cases in non-delayed diagnosis group).The rate of diagnosis delay was 56.1％.The incidence of acute miliary pulmonary tuberculosis and tuberculous meningitis was significantly higher in children ≤5 years old than that in children＞5 years old(P＜0.05).Diagnosis delay was associated with significantly higher prevalence of chronic fever,cough＞2 weeks,growth retardation and significantly longer duration of empirical antibiotic use compared to the children without diagnosis delay(P＜0.05).Univariate analysis showed that patient origin,contact history,mixed infection,tuberculosis type,molecular biological assay and severe disease were related to the delay of TB diagnosis(P＜0.05).Multivariate logistic regression analysis showed that patient origin[≥3 clinic visits(OR=7.064,95％CI:1.677-29.754)],mixed infection(OR=3.812,95％CI:1.185-12.260),severe disease(OR=3.697,95％CI:1.081-12.646)]were risk factors for diagnosis delay in children.Molecular biological assay(OR=4.642,95％CI:1.318-16.345)was a protective factor.Conclusions The clinical symptoms of tuberculosis in children are atypical.Delayed diagnosis of tuberculosis is common.Multiple clinic visits,mixed infection,and severe disease are the risk factors for diagnosis delay.Tuberculosis should be taken into account for the children with chronic fever,cough and growth retardation who have failed to respond to adequate therapy with third-generation cephalosporin and carbapenems.Molecular biological assay is helpful for early diagnosis of tuberculosis in children with negative sputum smear.

Objective To summarize the clinical characteristics of delayed diagnosis of tuberculosis in children,analyze the risk factors of delayed diagnosis,and support early diagnosis of tuberculosis in children.Methods This is a retrospective analysis based on the clinical data of tuberculosis patients admitted to the Children's Hospital Affiliated to Zhengzhou University from January 2015 to February 2023.The clinical characteristics of children were analyzed in terms of age group.According to the definition of diagnosis delay,the patients were assigned to delayed group and non-delayed group.Univariate analysis and multivariate logistic regression were used to analyze the risk factors for diagnosis delay.Results A total of 82 children with tuberculosis were included(46 cases in delayed diagnosis group and 36 cases in non-delayed diagnosis group).The rate of diagnosis delay was 56.1％.The incidence of acute miliary pulmonary tuberculosis and tuberculous meningitis was significantly higher in children ≤5 years old than that in children＞5 years old(P＜0.05).Diagnosis delay was associated with significantly higher prevalence of chronic fever,cough＞2 weeks,growth retardation and significantly longer duration of empirical antibiotic use compared to the children without diagnosis delay(P＜0.05).Univariate analysis showed that patient origin,contact history,mixed infection,tuberculosis type,molecular biological assay and severe disease were related to the delay of TB diagnosis(P＜0.05).Multivariate logistic regression analysis showed that patient origin[≥3 clinic visits(OR=7.064,95％CI:1.677-29.754)],mixed infection(OR=3.812,95％CI:1.185-12.260),severe disease(OR=3.697,95％CI:1.081-12.646)]were risk factors for diagnosis delay in children.Molecular biological assay(OR=4.642,95％CI:1.318-16.345)was a protective factor.Conclusions The clinical symptoms of tuberculosis in children are atypical.Delayed diagnosis of tuberculosis is common.Multiple clinic visits,mixed infection,and severe disease are the risk factors for diagnosis delay.Tuberculosis should be taken into account for the children with chronic fever,cough and growth retardation who have failed to respond to adequate therapy with third-generation cephalosporin and carbapenems.Molecular biological assay is helpful for early diagnosis of tuberculosis in children with negative sputum smear.

Objective To summarize the clinical characteristics of delayed diagnosis of tuberculosis in children,analyze the risk factors of delayed diagnosis,and support early diagnosis of tuberculosis in children.Methods This is a retrospective analysis based on the clinical data of tuberculosis patients admitted to the Children's Hospital Affiliated to Zhengzhou University from January 2015 to February 2023.The clinical characteristics of children were analyzed in terms of age group.According to the definition of diagnosis delay,the patients were assigned to delayed group and non-delayed group.Univariate analysis and multivariate logistic regression were used to analyze the risk factors for diagnosis delay.Results A total of 82 children with tuberculosis were included(46 cases in delayed diagnosis group and 36 cases in non-delayed diagnosis group).The rate of diagnosis delay was 56.1％.The incidence of acute miliary pulmonary tuberculosis and tuberculous meningitis was significantly higher in children ≤5 years old than that in children＞5 years old(P＜0.05).Diagnosis delay was associated with significantly higher prevalence of chronic fever,cough＞2 weeks,growth retardation and significantly longer duration of empirical antibiotic use compared to the children without diagnosis delay(P＜0.05).Univariate analysis showed that patient origin,contact history,mixed infection,tuberculosis type,molecular biological assay and severe disease were related to the delay of TB diagnosis(P＜0.05).Multivariate logistic regression analysis showed that patient origin[≥3 clinic visits(OR=7.064,95％CI:1.677-29.754)],mixed infection(OR=3.812,95％CI:1.185-12.260),severe disease(OR=3.697,95％CI:1.081-12.646)]were risk factors for diagnosis delay in children.Molecular biological assay(OR=4.642,95％CI:1.318-16.345)was a protective factor.Conclusions The clinical symptoms of tuberculosis in children are atypical.Delayed diagnosis of tuberculosis is common.Multiple clinic visits,mixed infection,and severe disease are the risk factors for diagnosis delay.Tuberculosis should be taken into account for the children with chronic fever,cough and growth retardation who have failed to respond to adequate therapy with third-generation cephalosporin and carbapenems.Molecular biological assay is helpful for early diagnosis of tuberculosis in children with negative sputum smear.

Objective To summarize the clinical characteristics of delayed diagnosis of tuberculosis in children,analyze the risk factors of delayed diagnosis,and support early diagnosis of tuberculosis in children.Methods This is a retrospective analysis based on the clinical data of tuberculosis patients admitted to the Children's Hospital Affiliated to Zhengzhou University from January 2015 to February 2023.The clinical characteristics of children were analyzed in terms of age group.According to the definition of diagnosis delay,the patients were assigned to delayed group and non-delayed group.Univariate analysis and multivariate logistic regression were used to analyze the risk factors for diagnosis delay.Results A total of 82 children with tuberculosis were included(46 cases in delayed diagnosis group and 36 cases in non-delayed diagnosis group).The rate of diagnosis delay was 56.1％.The incidence of acute miliary pulmonary tuberculosis and tuberculous meningitis was significantly higher in children ≤5 years old than that in children＞5 years old(P＜0.05).Diagnosis delay was associated with significantly higher prevalence of chronic fever,cough＞2 weeks,growth retardation and significantly longer duration of empirical antibiotic use compared to the children without diagnosis delay(P＜0.05).Univariate analysis showed that patient origin,contact history,mixed infection,tuberculosis type,molecular biological assay and severe disease were related to the delay of TB diagnosis(P＜0.05).Multivariate logistic regression analysis showed that patient origin[≥3 clinic visits(OR=7.064,95％CI:1.677-29.754)],mixed infection(OR=3.812,95％CI:1.185-12.260),severe disease(OR=3.697,95％CI:1.081-12.646)]were risk factors for diagnosis delay in children.Molecular biological assay(OR=4.642,95％CI:1.318-16.345)was a protective factor.Conclusions The clinical symptoms of tuberculosis in children are atypical.Delayed diagnosis of tuberculosis is common.Multiple clinic visits,mixed infection,and severe disease are the risk factors for diagnosis delay.Tuberculosis should be taken into account for the children with chronic fever,cough and growth retardation who have failed to respond to adequate therapy with third-generation cephalosporin and carbapenems.Molecular biological assay is helpful for early diagnosis of tuberculosis in children with negative sputum smear.