1.Comparison of different prediction models based on machine learning algorithms for the risk of poor postoperative wound healing in patients with spinal tuberculosis
Jinglian WEN ; Wei TANG ; Chengli WU ; Run LI ; Qing YE ; Guoxuan PENG
Chongqing Medicine 2025;54(11):2552-2558
Objective To analyze risk factors for poor postoperative wound healing in spinal tuberculo-sis patients and construct prediction models along with a risk scoring table using machine learning algorithms,providing references for early prevention and management.Methods Clinical data from 420 spinal tuberculo-sis patients treated at four tertiary hospitals in Guizhou Province between January 2017 and February 2024 were retrospectively analyzed.Risk factors were identified through univariate and multivariate analyses.Logis-tic regression,random forest,and support vector machine prediction models were constructed.Model perform-ance was evaluated using receiver operating characteristic(ROC)curves,precision,recall,accuracy,and F1-score.A risk prediction scoring table for poor postoperative wound healing was subsequently developed.Re-sults Among the 420 patients with spinal tuberculosis,132 experienced poor postoperative wound healing,with an incidence rate of 31.43%.Logistic regression analysis showed that BMI≤18.5 kg/m2,preoperative albumin≤30 g/L,combined surgical procedure,intraoperative blood loss>1 000 mL,direct bilirubin>8 μmol/L within 3 days after surgery,neutrophil count≤75×109/L within 3 days after surgery,and postopera-tive drainage volume>500 mL were risk factors for poor postoperative wound healing(P<0.05).In the comparison among the three risk prediction models constructed based on machine learning algorithms,the ran-dom forest model demonstrated the best predictive performance.A risk prediction scoring table was construc-ted based on the partial regression coefficients from the multivariate analysis,with a total score range from 0 to 11 points.A score>6 points indicated an increased risk of poor postoperative wound healing.The area un-der the ROC curve(AUC)for this risk prediction scoring table was 0.846(95%CI:0.769 to 0.923),indica-ting good predictive performance.Conclusion The random forest model based on machine learning algorithms and the risk prediction scoring table have certain predictive value for assessing the risk of poor postoperative wound healing in patients with spinal tuberculosis;they can assist healthcare professionals in early identifica-tion of high-risk patients.
2.Summary of best evidence for management of neurogenic bowel dysfunction in patients with spinal cord injury
Jinglian WEN ; Wei TANG ; Yuhong LUO ; Fan TANG ; Guanglin CHEN ; Xumei YANG ; Yuxin ZHONG
Chinese Journal of Modern Nursing 2024;30(7):919-925
Objective:To retrieve, evaluate, and integrate the best evidence for the management of neurogenic bowel dysfunction (NBD) in spinal cord injury patients both domestically and internationally, providing a basis for relevant evidence-based practices.Methods:The guidelines, expert consensus, clinical decision-making, and systematic review of NBD management for spinal cord injury patients were electronically searched in various databases and professional association websites at home and abroad. The search period was from database establishment to March 31, 2023.Results:A total of 13 articles were included, including five guidelines, five evidence summaries, two expert consensus, and one clinical decision-making. A total of 33 recommendations for NBD management in spinal cord injury patients were summarized from five aspects of medical history assessment, medication management, physical therapy, diet and exercise, and health education.Conclusions:The best evidence for NBD management in spinal cord injury patients summarized is scientific and practical. Medical and nursing staff should selectively apply the best evidence based on clinical practice.
3.Meta-integration of qualitative studies on caregiving experiences of caregivers of children with liver transplantation
Yuxin ZHONG ; Li ZHANG ; Jinglian WEN ; Jing CHEN
Chinese Journal of Modern Nursing 2024;30(19):2565-2572
Objective:To systematically review and integrate the real feelings and needs of caregivers of children with liver transplantation.Methods:The computer search was conducted on China National Knowledge Infrastructure, China Biology Medicine disc, VIP, Wanfang Data, PubMed, Scopus, Web of Science, SDS, PsycINFO, CINAHL and Embase to collect qualitative studies on the real experiences of caregivers of children with liver transplantation. The search period was from establishment of the databases to July 31, 2023. The quality of the included literature was evaluated using the qualitative research appraisal tool of Australia Joanna Briggs Institute Evidence-based Health Care Center, and the results were analyzed using the Meta-integration method.Results:A total of eight articles were included, and 35 research results were extracted, which were summarized into 10 new categories and integrated into four results, namely, the dilemma of multiple challenges, complex emotional experience, multi-dimensional care needs and positive coping strategies.Conclusions:The caregivers of children with liver transplantation are faced with great pressure and difficulties in the process of care, and they are eager for multifaceted support. Medical staff should pay attention to the inner experience and needs of caregivers and construct supportive intervention programs to reduce their physical and mental burden and improve the quality of care for children with liver transplantation.

Result Analysis
Print
Save
E-mail