Objective:To construct a predictive model for urinary tract infection in patients with cervical spine fracture based on the random forest (RF) algorithm and evaluate its predictive performance.Methods:A retrospective cohort study was conducted to analyze the clinical data of 400 patients with cervical spine fracture admitted to West China Hospital of Sichuan University from October 2020 to February 2025, including 311 males and 89 females, aged 12-87 years [(48.5±14.8)years]. According to the occurrence of urinary tract infection during hospital stay, the patients were divided into urinary tract infection group ( n=57) and non-urinary tract infection group ( n=343). General information, disease-related data, and serological laboratory indicators during hospital stay were recorded in both groups. Viriables for urinary tract infection in patients with cervical spine fracture were analyzed and identified through univariate analysis and Lasso regression analysis. Using the bootstrap method with 500 resamples, the data were randomly allocated into the training set ( n=281) and test set ( n=119) at a ratio of 7∶3. An RF prediction model for urinary tract infection in patients with cervical spine fracture was constructed in the training set and the variable importance for the model was calculated. The constructed RF prediction model was validated in the test set, with the predictive accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC) calculated to evaluate its predictive performance. Results:Univariate analysis showed that age, body mass index (BMI), length of hospital stay, concurrent hepatic impairment, concurrent benign prostatic hyperplasia, indwelling catheterization, duration of indwelling catheterization, immunosuppressant use, fracture site, cervical spinal cord injury, Frankel grade, time from injury to surgery, red blood cell count (RBC), hemoglobin (Hb), white blood cell count (WBC), albumin (Alb), globulin (GLO), blood urea nitrogen (BUN), and C-reactive protein (CRP) were significantly associated with urinary tract infection in patients with cervical spine fracture ( P<0.05). Among them, 9 viriables screened through Lasso regression analysis were age, length of hospital stay, concurrent hepatic impairment, concurrent benign prostatic hyperplasia, indwelling catheterization, duration of indwelling catheterization, Frankel grade, time from injury to surgery, and RBC. Based on the 9 viriables, a predictive model for urinary tract infection in patients with cervical spine fracture was constructed using the RF algorithm. Based on the mean decrease in Gini coefficient in the RF model, the top 6 important variables were duration of indwelling catheterization, length of hospital stay, RBC, age, time from injury to surgery, and Frankel grade in sequence. In the test set, the model achieved a prediction accuracy of 87.4%, sensitivity of 88.2%, specificity of 82.4%, and AUC of 0.89 (95% CI 0.80, 0.93). Conclusion:The RF prediction model for urinary tract infection in patients with cervical spine fracture is constructed based on 9 predictors including duration of indwelling catheterization, length of hospital stay, RBC, age, time from injury to surgery, Frankel grade, concurrent hepatic impairment, concurrent benign prostatic hyperplasia, and indwelling catheterization, with the first 6 viriables ranked as the most important factors, and demonstrates favorable predictive performance.

Objective:To construct a predictive model for urinary tract infection in patients with cervical spine fracture based on the random forest (RF) algorithm and evaluate its predictive performance.Methods:A retrospective cohort study was conducted to analyze the clinical data of 400 patients with cervical spine fracture admitted to West China Hospital of Sichuan University from October 2020 to February 2025, including 311 males and 89 females, aged 12-87 years [(48.5±14.8)years]. According to the occurrence of urinary tract infection during hospital stay, the patients were divided into urinary tract infection group ( n=57) and non-urinary tract infection group ( n=343). General information, disease-related data, and serological laboratory indicators during hospital stay were recorded in both groups. Viriables for urinary tract infection in patients with cervical spine fracture were analyzed and identified through univariate analysis and Lasso regression analysis. Using the bootstrap method with 500 resamples, the data were randomly allocated into the training set ( n=281) and test set ( n=119) at a ratio of 7∶3. An RF prediction model for urinary tract infection in patients with cervical spine fracture was constructed in the training set and the variable importance for the model was calculated. The constructed RF prediction model was validated in the test set, with the predictive accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC) calculated to evaluate its predictive performance. Results:Univariate analysis showed that age, body mass index (BMI), length of hospital stay, concurrent hepatic impairment, concurrent benign prostatic hyperplasia, indwelling catheterization, duration of indwelling catheterization, immunosuppressant use, fracture site, cervical spinal cord injury, Frankel grade, time from injury to surgery, red blood cell count (RBC), hemoglobin (Hb), white blood cell count (WBC), albumin (Alb), globulin (GLO), blood urea nitrogen (BUN), and C-reactive protein (CRP) were significantly associated with urinary tract infection in patients with cervical spine fracture ( P<0.05). Among them, 9 viriables screened through Lasso regression analysis were age, length of hospital stay, concurrent hepatic impairment, concurrent benign prostatic hyperplasia, indwelling catheterization, duration of indwelling catheterization, Frankel grade, time from injury to surgery, and RBC. Based on the 9 viriables, a predictive model for urinary tract infection in patients with cervical spine fracture was constructed using the RF algorithm. Based on the mean decrease in Gini coefficient in the RF model, the top 6 important variables were duration of indwelling catheterization, length of hospital stay, RBC, age, time from injury to surgery, and Frankel grade in sequence. In the test set, the model achieved a prediction accuracy of 87.4%, sensitivity of 88.2%, specificity of 82.4%, and AUC of 0.89 (95% CI 0.80, 0.93). Conclusion:The RF prediction model for urinary tract infection in patients with cervical spine fracture is constructed based on 9 predictors including duration of indwelling catheterization, length of hospital stay, RBC, age, time from injury to surgery, Frankel grade, concurrent hepatic impairment, concurrent benign prostatic hyperplasia, and indwelling catheterization, with the first 6 viriables ranked as the most important factors, and demonstrates favorable predictive performance.

Objective To explore the value of deep learning models in predicting axillary lymph node(ALN)metastasis of breast cancer based on intratumoral and peritumoral dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI).Methods A retrospective analysis was conducted on cases from Tianjin Medical University Cancer Hospital and Laoshan Branch of Affiliated Hospital of Qingdao University,involving a total of 850 lesions in 850 patients.The region of interest within the tumor was delineated at the largest area of the lesion on the first enhancement images and automatically expanded by 3 mm and 6 mm in a conformal fashion.Deep learning prediction models based on ResNet50 were developed via intratumoral,peritumoral,and intratumoral combined peritumoral models,respectively,and a comprehensive prediction model was developed by integrating semantic features of imaging reports.Cases from Tianjin Medical University Cancer Hospital were randomly divided into training and test cohorts in a 7∶3 ratio,while cases from Laoshan Branch of Affiliated Hospital of Qingdao University served as the external validation cohort.The area under the curve(AUC),accuracy,sensitivity,specificity,F1-score,and Brier-score were calculated,respectively.Results The model incorporating intratumoral,peritumoral(3 mm),and semantic features demonstrated the highest performance,with AUC of 0.801[95％confidence interval(CI)0.765-0.845],0.781(95％CI 0.745-0.817),and 0.752(95％CI 0.700-0.793)in the training cohort,test cohort,and external validation cohort,respectively,and there was no significant difference in AUC between combined model and intratumoral/peritumoral model,respectively,but it demonstrated the higher sensitivity and F1-score,and the lower Brier-score.Conclusion Incorporating peritumoral images into the conventional model based on intratumoral images enhanced the predictive ability of ALN metastasis in breast cancer.

Objective:To summarize the best evidence of thirst management in peripheral surgical patients in China, and to provide theoretical basis for clinical thirst management.Methods:According to the PIPOST model, research questions were raised. According to the "6S" model, literature published by various guide websites, evidence-based databases, original research databases and professional association websites at home and abroad from database establishment to January 30, 2022 were systematically retrieved. Two researchers independently evaluated the quality of the literature and extracted and integrated the evidence of the literature that met the quality standards. The research team graded the evidence and determined the recommendation level.Results:A total of 15 literatures were selected, including 2 systematic reviews, 3 clinical decisions and 10 randomized controlled trials (RCTS) . A total of 23 evidences were sorted out, including 8 aspects such as drug factors affecting thirst, thirst assessment tools, preoperative thirst intervention strategy, postoperative safe drinking water assessment, postoperative thirst intervention strategy, nursing observation, health education and precautions.Conclusions:In the absence of uniform standards for perioperative thirst management, the evidence summarized in this study can provide evidence-based evidence for clinical nursing work.

Objective:To retrieve and summarize the best evidence on non-pharmacological interventions for pain management in knee osteoarthritis.Methods:The literatures related to non-pharmacological intervention in pain management for knee osteoarthritis were searched on UpToDate, BMJ Best Practice, Australia Joanna Briggs Institute evidence-based healthcare center database, Cochrane Library, National Institute for Health and Clinical Excellence, Guidelines International Network, Medlive, Medline, PubMed, Wanfang database and China National Knowledge Infrasructure. The evidences were extracted after quality evaluation of the included literature.Results:A total of 11 references were included, including 6 guidelines, 2 expert consensuses, 2 systematic evaluations and 1 randomized controlled trial. Finally, 22 pieces of best evidences were summarized from 6 aspects, including health education, pain assessment, referral, psychological intervention, exercise intervention and physical therapy.Conclusions:Summary of the best evidence for non-pharmacological intervention in pain management for patients with knee osteoarthritis can provide evidence-based evidence for clinical healthcare professionals and knee osteoarthritis patients to undergo non-pharmacological pain intervention.

Objective:To compile Pressure Injury Prevention Behavior Assessment Scale (Patient Version) and conduct reliability and validity test.Methods:Guided by the theory of "patient participation in patient safety" , an item pool was initially constructed through literature review and patient interview, and Delphi expert consultation method was used to evaluate and screen items. From October to November 2021, the convenient sampling method was adopted to select 160 inpatients of Orthopedics Department of West China Hospital of Sichuan University as research objects for questionnaire survey, project analysis, reliability and validity test.Results:The formed Pressure Injury Prevention Behavior Assessment Scale (Patient Version) contained 21 items in 3 dimensions. The Cronbach 's α coefficient was 0.947, and the broken half reliability coefficient was 0.873. The content validity index at scale level was 0.958, and the content validity index at item level was 0.909-1.000. Exploratory factor analysis showed that the cumulative variance contribution rate of the three common factors was 61.931%. Conclusions:It is preliminarily verified that Pressure Injury Prevention Behavior Assessment Scale (Patient Version) has good reliability and validity, which can be used to evaluate the current situation of orthopaedic patients participating in the prevention of stress injury behavior and provide a basis for the corresponding intervention measures.

Objective:To establish an animal model of acute systemic cold injury in mice.Methods:There were 98 C57BL/6 mice, half male and half female, with body weight of 22-27 g and age of 10 weeks. The mice were randomly divided into 7 groups ( n=14) according to the changes of anal temperature in cold environment, namely, group A (38.5 ± 1) ℃, group B (35 ± 1) ℃, group C (30 ± 1) ℃, group D (25 ± 1) ℃, group E (20 ± 1) ℃, group F (15 ± 1) ℃, and group G (10 ± 1) ℃, among which, group A was the blank control group, and the rest groups were the experimental group. The mice in the blank control group were placed in the normal environment (20 ± 5) ℃, and the mice in the experimental group were placed in the low temperature artificial climate box at - 20℃. The anal temperature of the mice was measured intermittently (as the core temperature), and the time required for the core temperature of the mice to drop to groups B, C, D, E, F and G was recorded. The righting reflex was used to evaluate the consciousness state, the action ability and the general state of each organ of mice were observed, and the blood routine and HE staining of each organ were detected. Results:The lower the core temperature of the experimental group, the longer the time required. The consciousness state, action ability, general state of organs, blood routine, and HE staining of organs in groups B, C, and D were basically the same as those in group A, and there was no acute systemic cold injury. Therefore, the blood routine, general observation of organs, and HE staining of organs in groups B, C, and D were no longer displayed compared with those in group A. Compared with group A, mice in group E began to suffer from disturbance of consciousness and action ability. With the decrease of core body temperature, the damage was aggravated, and mice in group G died. Compared with group A, the indices of blood routine test (WBC, RBC, HGB, PLT) of mice in group E began to decrease, and the univariate variance calculation showed that only WBC changes had statistical significance ( P<0.05). Compared with groups A and E, the indices of blood routine test (WBC, RBC, HGB, PLT) of mice in group F were further reduced, and the changes of each index in univariate variance calculation were statistically significant ( P<0.05). The general observation results showed that compared with group A, the lung, liver and spleen surfaces of mice in group E began to darken, and compared with groups A and E, the lung, liver, spleen, kidney and heart of mice in group F were further deepened and darkened, with irregular edges. HE staining results of various organs showed that compared with group A, the mice in group E began to have partial alveolar structure destruction and a small amount of inflammatory cell infiltration, the central vein of the liver was slightly congested, and the red and white pulp of the spleen were indistinct. Compared with groups A and E, the pathological structure damage of the lung, liver, spleen, kidney, heart and brain tissues of the mice in group F was further aggravated. Conclusions:Detection of consciousness state, action ability, general state of organs, blood routine and HE staining indices of organs in mice under low temperature can simulate the progress of clinical acute cold injury, and the animal model of acute systemic cold injury was successfully prepared.

Objective:To evaluate the long-term safety, tolerability and efficacy of Lacosamide add-on therapy in Chinese children with partial-onset seizures.Methods:SP848 was a global multicenter single-arm study involving 60 Chinese children with partial-onset seizures with the age of 4-17 years who were managed by Lacosamide add-on therapy at seven hospitals across China from April 2018 to May 2019.After treatment with at least two kinds of anti-seizure medications simultaneously or sequentially, partial seizures were still poorly controlled and Lacosamide oral solution (syrup) or tablets were added.The minimum initial oral dose was 2 mg/(kg·d), and the maximum allowable dose was 12 mg/(kg·d)or 600 mg/d during the study period.The dose was adjusted according to the tolerance and seizure control level of partial-onset seizures children.Seizure frequency and the median percentage change in partial-onset seizures per 28 days from baseline to the final visit were recorded, including 50% responder rate and 75% responder rate.Results:A total of 60 Chinese children with the mean age of 9.18 (4.00-15.40) years were included in this interim analysis, involving 39 males and 21 females.The mean course of epilepsy was 5.04 (0.50-15.20) years.A total of 43 patients (71.7%) still have been treated.One patient (1.7%) has completed the 6-12 months of follow-up, and 14 patients (23.3%) have completed the follow-up for less than 6 months.The median change in the frequency of partial seizures every 28 days from baseline to the last visit was -2.91, with its median percentage as -25.46%, and the proportions of ≥50%, while ≥75% responder rate were 40.0% and 28.3%, respectively.A total of 52 patients (86.7%) had 265 treatment emergent adverse events (TEAE), 11 patients (18.3%) had 19 serious TEAE, 37 patients (61.7%) had 127 drug-related TEAE, and 11 patients (18.3%) had 16 TEAE leading to the discontinuation of the trial.The most common TEAE were upper respiratory tract infections (20 cases, 33.3%), followed by drowsiness (16 cases, 26.7%), dizziness (15 cases, 25.0%) and vomiting (13 cases, 21.7%). There were no abnormal changes in the electrocardiographic findings during the treatment.Conclusions:For Chinese patients with partial seizures who are older than the age of 4 years and poorly controlled by other drugs, Lacosamide is effective and well tolerated as an add-on therapy drug.The safety characteristics are consistent with those reported in children and adults.No new safety concerns are identified.

Background Dentists are a high-risk population of work-related musculoskeletal disorders (WMSDs), where the body part with the highest prevalence is the neck. Objective To analyze potential influencing factors of neck pain among dentists, and explore a prediction model of neck pain in dentists. Methods Dentists from different hospitals in Fuzhou were selected as study subjects by stratified cluster sampling according to hospital characteristics (dental hospitals, general hospitals, and dental clinics). The basic information, presentation of WMSDs, and its influencing factors were investigated by using the Chinese version of Musculoskeletal Disorders Questionnaire and the Subjective Workload Assessment Technique. A total of 655 questionnaires were collected, of which 603 were valid, with an effective rate of 92.1%. Multiple logistic regression was used to analyze potential influencing factors of neck pain in dentists. A prediction model of neck pain of dentists was constructed by using neural network model, and the prediction efficiency of the model was evaluated. Results The neck was the body part with the highest prevalence (43.8%, 264/603) of WMSDs among dentists. The results of multiple logistic regression analysis showed that female (OR=2.709, 95%CI: 1.852-3.962, P <0.001), working age of 10-<20 years (versus <10 years, OR=3.836, 95%CI: 2.471-5.957, P<0.001), keeping head up or down for a long time (OR=8.492, 95%CI: 2.203-32.731, P=0.002), holding head sideways for a long time (OR=2.210, 95%CI: 1.376-3.550, P<0.001), maintaining the same sitting spot for a long time (OR=4.336, 95%CI: 2.192-8.579, P<0.001), and psychological load value ≥70 (versus <40, OR=1.901, 95%CI: 1.038-3.480, P=0.037) increased the risk of neck pain in dentists. Sufficient operating space (OR=0.507, 95%CI: 0.302-0.850, P=0.010) and doing some exercise during work break (OR=0.670, 95%CI: 0.453-0.991, P=0.045) reduced the risk of reporting neck pain among dentists. A neural network prediction model of dentists' neck pain was constructed with 1 hidden layer and 6 hidden layer neurons. The percentage of correct prediction of training set was 89.6%, and the percentage of correct prediction of test set was 83.9%. The order of importance of the independent variables included in the model were working age, holding head sideways for a long time, psychological load, etc. The result of neural network model of neck pain among dentists showed that the area under the curve of receiver operator characteristic (ROC) was 0.940 (95%CI: 0.922-0.958, P<0.001). When the maximum diagnostic value was determined by the ROC curve, the sensitivity was 84.8%, the specificity was 91.2%, and the Youden Index was 0.760. Conclusion Neck pain of dentists is affected by many factors, such as individual factors (gender and working age), ergonomic factors (keeping various postures and operations for a long time, operating space, etc.), psychological factors (different levels of psychological load) and so on. The neural network model can be used as a prediction tool to explore the risk of reporting neck pain among dentists.

Wound healing is a complex pathophysiological process that is affected by many systemic and local factors. Undisturbed wound healing (UWH) is a new concept whereby the disturbance to the wound healing process is reduced and the wound healing outcome is improved mainly through the selection of wound dressings with appropriate performance and reducing the frequency of dressing changes. This paper summarizes the development, intervention measures, and advantages of the concept of UWH, aiming to provide new ideas and directions for wound diagnosis and treatment.