1.Comparative Analysis of Clinical Efficacy of Traditional Chinese Medicine Manipulative Reduction Combined with Small Splint Fixation Versus Surgical Treatment for Type A Distal Radius Fracture
Yang SHAO ; Zihan WANG ; Jianwei WANG ; Guoda DAI ; Hengyan CUI ; Zhen HUA ; Tingchen ZHU ; Shaoshuo LI ; Jun MAO ; Fenghua CHEN ; Shuai TAO ; Mao WU
Journal of Traditional Chinese Medicine 2026;67(10):1078-1085
ObjectiveTo compare the clinical efficacy of traditional Chinese medicine (TCM) manipulative reduction combined with small splint fixation versus surgical treatment for type A distal radius fracture (DRF) and to explore the factors influencing the choice of treatment. MethodsA multi-center retrospective study was conducted, collecting data from 1237 type A DRF patients treated in 11 hospitals in Jiangsu province from September, 2023 to April, 2025. Among them, 851 patients in the TCM group received manipulative reduction combined with small splint fixation, and 386 patients in the surgical group underwent open reduction and internal fixation. Visual analog scale (VAS) scores for pain and radiographic indicators including palmar tilt, ulnar deviation, and radial height were compared before treatment, 5-7 days after treatment, and 4-6 weeks after treatment. The wrist joint function scores including Dienst and Gartland-Werley scores at 12 weeks after treatment were recorded. Subgroup analysis was conducted for the excellent rate of Dienst and Gartland-Werley scores, stratified by age (<50, 50-59, 60-69, ≥70 years old) and AO subtypes (A1, A2, A3). A multivariate logistic regression model was used to identify independent factors influencing treatment choice. ResultsOn 5-7 days after treatment, the surgical group had lower VAS scores than the TCM group, while 4-6 weeks after treatment, the TCM group showed lower VAS scores than the surgical group (P<0.01). In terms of radiographic indicators, except for the palmar tilt before treatment being higher in the surgical group than in the TCM group (P<0.01), there were no significant differences in palmar tilt, ulnar deviation, and radial height at other timepoints (P>0.05). Twelve weeks after treatment, the surgical group had a higher average Gartland-Werley score and the excellent rate than the TCM group (P<0.01). Subgroup analysis showed that in patients with A2 type DRF aged 50-59 and 60-69 years old, the excellent rates of Dienst and Gartland-Werley scores in the TCM group were higher than those in the surgical group (P<0.05). Multivariate logistic regression analysis revealed that age, palmar tilt, ulnar deviation, and the degree of swelling on the affected side were independent factors influencing the choice of treatment (P<0.05). ConclusionBoth TCM manipulative reduction combined with small splint fixation and surgical treatment for type A DRF can achieve good therapeutic effects. TCM manipulative reduction combined with small splint fixation has certain advantages in medium- and long-term pain relief, especially in elderly patients, where wrist joint function recovery is more stable. Age, palmar tilt, ulnar deviation, and swelling degree are the main factors influencing the treatment choice.
2.Correlation between serum zinc level and prognosis of patients with sepsis
Xiao-Gang WANG ; Jia-Jun MA ; Rui-Xin ZHU ; Li-Bing ZHOU ; Sai-Hu HUANG ; Shui-Yan WU ; Wen-Si NIU ; Jie HUANG ; Zhen-Jiang BAI
Parenteral & Enteral Nutrition 2025;32(5):278-282
Objective:To investigate the differences in clinical outcomes of septic children with varying serum zinc levels,and to analyze the relationship between reduced serum zinc levels and organ dysfunction as well as 28-day mortality in septic children.Methods:This study conducted a retrospective analysis of clinical data from pediatric patients diagnosed with sepsis or septic shock in the Department of critical care medicine of the children's Hospital of Soochow University between January 2017 and December 2022.Clinical characteristics,organ dysfunction,and prognosis were compared between two groups:children with low serum zinc levels and those with normal zinc levels.Results:The serum zinc level of septic children within 24 hours of admission was 9.60(5.52,13.80)μmol/L,with 50.54%(94/186)of the children exhibiting low serum zinc levels(<10.07 μmol/L).Compared to the normal serum zinc group,the low serum zinc group had a significantly lower Pediatric Critical Illness Score(PCIS)[(78.71±9.35)vs.(85.12±8.51),P=0.005]and higher 28-day mortality(46.80%vs.14.13%,P<0.001).The low serum zinc group also had a higher proportion of invasive mechanical ventilation(64.89%vs.47.82%,P=0.019),renal replacement therapy(15.59%vs.3.26%,P=0.003),and use of vasoactive drugs(56.38%vs.30.43%,P<0.001).The rate of underlying conditions in the low serum zinc group was significantly higher than that in the normal serum zinc group(57.44%vs.36.95%,P=0.005).Additionally,the low serum zinc group had a higher incidence of disseminated intravascular coagulation(DIC),respiratory failure,acute kidney injury,shock,and multiple organ dysfunction syndrome(MODS)compared to the normal serum zinc group(P<0.05).Serum zinc levels had predictive value for 28-day mortality in septic children(AUC=0.813;95%CI:0.725~0.902;P<0.001).A serum zinc level of less than 6.950 μmol/L predicted the death of septic children with a sensitivity of 0.618 and a specificity of 0.902.Conclusion:Sepsis in children is commonly associated with low serum zinc levels,especially in those with underlying conditions such as hematologic and oncologic disorders.Sepsis patients hypozincemia with a higher incidence of DIC,respiratory failure,acute kidney injury,shock,and MODS.A serum zinc level below 6.95 μmol/L serves as a significant predictor of 28-day mortality in children with severe sepsis.
3.Guideline for Adult Weight Management in China
Weiqing WANG ; Qin WAN ; Jianhua MA ; Guang WANG ; Yufan WANG ; Guixia WANG ; Yongquan SHI ; Tingjun YE ; Xiaoguang SHI ; Jian KUANG ; Bo FENG ; Xiuyan FENG ; Guang NING ; Yiming MU ; Hongyu KUANG ; Xiaoping XING ; Chunli PIAO ; Xingbo CHENG ; Zhifeng CHENG ; Yufang BI ; Yan BI ; Wenshan LYU ; Dalong ZHU ; Cuiyan ZHU ; Wei ZHU ; Fei HUA ; Fei XIANG ; Shuang YAN ; Zilin SUN ; Yadong SUN ; Liqin SUN ; Luying SUN ; Li YAN ; Yanbing LI ; Hong LI ; Shu LI ; Ling LI ; Yiming LI ; Chenzhong LI ; Hua YANG ; Jinkui YANG ; Ling YANG ; Ying YANG ; Tao YANG ; Xiao YANG ; Xinhua XIAO ; Dan WU ; Jinsong KUANG ; Lanjie HE ; Wei GU ; Jie SHEN ; Yongfeng SONG ; Qiao ZHANG ; Hong ZHANG ; Yuwei ZHANG ; Junqing ZHANG ; Xianfeng ZHANG ; Miao ZHANG ; Yifei ZHANG ; Yingli LU ; Hong CHEN ; Li CHEN ; Bing CHEN ; Shihong CHEN ; Guiyan CHEN ; Haibing CHEN ; Lei CHEN ; Yanyan CHEN ; Genben CHEN ; Yikun ZHOU ; Xianghai ZHOU ; Qiang ZHOU ; Jiaqiang ZHOU ; Hongting ZHENG ; Zhongyan SHAN ; Jiajun ZHAO ; Dong ZHAO ; Ji HU ; Jiang HU ; Xinguo HOU ; Bimin SHI ; Tianpei HONG ; Mingxia YUAN ; Weibo XIA ; Xuejiang GU ; Yong XU ; Shuguang PANG ; Tianshu GAO ; Zuhua GAO ; Xiaohui GUO ; Hongyi CAO ; Mingfeng CAO ; Xiaopei CAO ; Jing MA ; Bin LU ; Zhen LIANG ; Jun LIANG ; Min LONG ; Yongde PENG ; Jin LU ; Hongyun LU ; Yan LU ; Chunping ZENG ; Binhong WEN ; Xueyong LOU ; Qingbo GUAN ; Lin LIAO ; Xin LIAO ; Ping XIONG ; Yaoming XUE
Chinese Journal of Endocrinology and Metabolism 2025;41(11):891-907
Body weight abnormalities, including overweight, obesity, and underweight, have become a dual public health challenge in Chinese adults: overweight and obesity lead to a variety of chronic complications, while underweight increases the risks of malnutrition, sarcopenia, and organ dysfunction. To systematically address these issues, multidisciplinary experts in endocrinology, sports science, nutrition, and psychiatry from various regions have held multiple weight management seminars. Based on the latest epidemiological data and clinical evidence, they expanded the guideline to include assessment and intervention strategies for underweight, in addition to the core content of obesity management. This guideline outlines the etiological mechanisms, evaluation methods, and multidimensional management strategies for overweight and obesity, covering key areas such as diagnosis and assessment, medical nutrition therapy, exercise prescription, pharmacological intervention, and psychological support. It is intended to provide a scientific and standardized approach to weight management across the adult population, aiming to curb the rising prevalence of obesity, mitigate complications associated with abnormal body weight, and improve nutritional status and overall quality of life.
4.Treatment of neck-type cervical spondylosis by Baduanjin combined with acupuncture:a randomized controlled study
Jun DONG ; Zhen YANG ; Jiong ZHU ; Shi-min ZHU
Fudan University Journal of Medical Sciences 2025;52(4):532-537,580
Objective To observe the efficacy and safety of Baduanjin combined with acupuncture in treating neck-type cervical spondylopathy(NTCS)patients.Methods Eighty patients were randomly divided into an intervention group and a control group in a 1∶1 ratio.The intervention group was treated with a combination of Baduanjin and acupuncture.Patients underwent Baduanjin exercise daily and acupuncture treatment twice a week for a total of 8 consecutive weeks.The control group received routine acupuncture twice a week for a total of 8 consecutive weeks.After the end of the treatment course,the effective rates of the two groups,as well as the visual analogue scale(VAS),neck disability index(NDI),self-rating anxiety scale(SAS),self-rating depression scale(SDS),and general comfort questionnaire(GCQ)assessment before and after treatment were compared,then safety evaluations was assessed.Results After intervention,the total effective rates of the intervention group and the control group were 91.4%and 76.31%,respectively,with a statistically significant difference(P<0.05);Compared within the group,the VAS,NDI,SAS,SDS scores of both groups were significantly lower than before treatment(all P<0.01),and the GCQ scores were higher than before treatment(both P<0.01);After intervention,inter-group comparison showed that the improvement of VAS,NDI,SAS,SDS,and GCQ scores in the intervention group was more significant than that in the control group(all P<0.05).Conclusion The combination of Baduanjin and acupuncture treatment can improve the clinical efficacy of NTCS patients and has good safety,which is worthy of clinical promotion and application.
5.Comparative analysis of Exoview and Mimics three-dimensional reconstruction in thoracoscopic pulmonary segmentectomy
Jun-ping ZHU ; Meng-meng GUO ; Jia-xing SHI ; Zhi-gang GUO ; Sheng-hui YANG ; Zhen QIAO
Journal of Regional Anatomy and Operative Surgery 2025;34(11):998-1003
Objective To compare the effects of sequential Exoview and Mimics three-dimensional reconstruction with fluorescence method in thoracoscopic pulmonary segmentectomy.Methods The clinical data of 160 patients with lung cancer admitted to our hospital from January 2020 to June 2023 were retrospectively analyzed.Among them,79 patients who underwent thoracoscopic pulmonary segmentectomy with the sequential Exoview three-dimensional reconstruction and fluorescence method before the operation were classified as the Exoview group,and 81 patients who underwent thoracoscopic pulmonary segmentectomy with the sequential Mimics three-dimensional reconstruction and fluorescence method before the operation were classified as the Mimics group.The surgical completion status,the coincidence rate between the number of left and right pulmonary artery branches evaluated before operation and intraoperative findings,reconstruction time,segment display effect,general indicators of operation(operation time,intraoperative blood loss,number of lymph node dissection,thoracic tube placement time,postoperative hospital stay),pulmonary function[forced expiratory volume in one second(FEV1),percentage of forced expiratory volume in one second(FEV1%)]and complications were compared between the two groups.Results All patients in the two groups successfully completed thoracoscopic pulmonary segmentectomy,and indocyanine green was injected once in each group.The operation process was roughly consistent with the preoperative simulation,and no thoracotomy was performed.There was no statistically significant difference in the resection of lung segment between the two groups of patients(P>0.05).The coincidence rate between the number of left and right pulmonary artery branches evaluated before operation and intraoperative findings in the Exoview group was higher than that in the Mimics group(P<0.05).There was no significant difference in the segment display effect between the Exoview group and the Mimics group(P>0.05).The operation time and the reconstruction time in the Exoview group were shorter those that in the Mimics group,and the intraoperative blood loss was less than that in the Mimics group(P<0.05).There was no significant difference in the number of lymph node dissection,the thoracic tube placement time,or the postoperative hospital stay between the two groups(P>0.05).There was no statistically significant difference in FEV1 or FEV1%7 days after surgery compared with those before surgery(P>0.05).The FEV1 and FEV1%of patients in the Mimics group 7 days after surgery were lower than those beforesurgery(P<0.05).There was no statistically significant difference in FEV1 or FEV1%between the Exoview group and the Mimics group before and 7 days after surgery(P>0.05).The total incidence of complications in the Exoview group was 1.27%,compared with 4.94%in the Mimics group,the difference was not statistically significant(P>0.05).Conclusion Both sequential Exoview and Mimics three-dimensional reconstruction with fluorescence method are safe and effective for thoracoscopic pulmonary segmentectomy,while Exoview has more advantages in preoperative assessment of the number of pulmonary artery branches,and it has shorter reconstruction time and operation time,with less impact on lung function.
6.Surgical efficacy evaluation of NF1-related dystrophic lumbosacral deformity: comparative analysis between pelvic and non-pelvic fixation
Song LI ; Zezhang ZHU ; Jie ZHOU ; Saihu MAO ; Shuqi SUN ; Zhen LIU ; Benlong SHI ; Xu SUN ; Jun QIAO ; Yong QIU
Chinese Journal of Orthopaedics 2025;45(9):604-612
Objective:To analyze the selection of internal fixation methods, surgical outcomes, and complications in patients with Neurofibromatosis Type 1 (NF1) accompanied by dystrophic lumbosacral deformities, and to evaluate the indications for pelvic fixation.Methods:A retrospective analysis was conducted on 21 patients with NF1 and associated dystrophic lumbosacral malformations (L 4 to sacrum) who underwent spinal deformity correction surgery at Nanjing Drum Tower Hospital from January 2009 to November 2022. The cohort included 11 males and 10 females, with a mean surgical age of 15.4±4.7 years (range, 7-24 years). Patients were divided into two groups based on whether pelvic fixation was performed: 10 patients in the non-pelvic fixation group (NP group) and 11 in the pelvic fixation group (P group), where fixation involved second sacral alar-iliac (S 2AI) screws or iliac screws. Radiographic parameters, including the Cobb angle of the lumbosacral fractional curve, main curve, and focal kyphosis, were compared preoperatively, postoperatively, and at the last follow-up. Results:The NP group had a significantly lower mean age (13.2±4.9 years) compared to the P group (17.5±3.5 years; t=2.287, P=0.034). Spinal instability (rotational subluxation or spondylolisthesis) due to dystrophic changes was observed in 2 patients in the NP group and 8 in the P group, a statistically significant difference (χ 2=5.838, P=0.030). In the P group, five patients underwent unilateral fixation and six underwent bilateral fixation. Implant types included 2 cases with iliac screws, 1 case with iliac screws plus S 2AI, and 8 cases with S 2AI screws alone. The utilization rate of hooks was significantly higher in the NP group (12.6%±11.5%) compared to the P group (3.5%±6.9%; t=2.230, P=0.038). The preoperative Cobb angle of the lumbosacral fractional curve was significantly smaller in the NP group (13.8°±9.0°) than in the P group (25.5°±13.9°; t=2.228, P=0.039). Postoperatively, the angles were corrected to 6.3°±6.1° and 6.4°±5.3°, respectively ( t=0.901, P=0.969), with correction rates of 57.3%±13.6% and 74.1%±17.8% ( t=2.369, P=0.029). At final follow-up, the angles remained stable (6.6°±6.6° vs. 6.3°±4.8°; t=0.116, P=0.909). For the main curve, preoperative Cobb angles were 52.5°±15.1° (NP) and 61.1°±16.9° (P; t=1.200, P=0.246), corrected to 31.3°±13.8° and 28.0°±8.4°, respectively ( t=0.646, P=0.526). Correction rates were 41.3%±13.0% in the NP group and 53.2%±11.6% in the P group ( t=2.206, P=0.037). At the final follow-up, these values were 32.4°±14.2° and 31.7°±10.3° ( t=0.133, P=0.896). Focal kyphosis, seen in 9 patients, was corrected from 19.7°±10.9° preoperatively to -13.6°±9.5° postoperatively, and remained at -14.1°±9.6° at the final follow-up ( F=33.547, P<0.001). Multi-rod systems were used in 6 cases (NP group) and 7 cases (P group), with no significant difference (χ 2=0.153, P=0.926). Two patients in the NP group developed coronal decompensation three years postoperatively, and one required revision surgery. In the P group, rod breakage occurred in 3 patients, two of whom underwent revision. Conclusions:Dystrophic rotational subluxation or spondylolisthesis of the lumbosacral spine is a primary indication for pelvic fixation in patients with NF1-associated deformities. However, complications related to internal fixation remain common. The combined use of a multi-rod screw-hook hybrid system, particularly when extending across the lumbosacral region, may reduce the risk of instrumentation failure.
7.Development of a visualizable machine learning model for mechanical complication risk in adult spinal deformity surgery
Jie LI ; Zhen TIAN ; Zhong HE ; Xiaodong QIN ; Jun QIAO ; Saihu MAO ; Benlong SHI ; Yong QIU ; Zezhang ZHU ; Zhen LIU
Chinese Journal of Orthopaedics 2025;45(17):1137-1146
Objective:To predict mechanical complications (MC) following spinal deformity surgery for adult spine deformity (ASD) using machine learning models, identify key risk factors, and develop a visualizable tool for individualized risk assessment.Methods:Clinical and radiological data from 525 patients with ASD who underwent surgery in our hospital between January 2017 and December 2021 were collected. Patients were randomly assigned to a training set (70%) and a test set (30%) for model development. The cohort included 88 males and 437 females, with a mean age of 42.2±18.1 years. Variables included demographic data, comorbidities, local and systemic radiological parameters, paraspinal muscle fat infiltration (FI), and vertebral bone quality (VBQ) scores. Multiple machine learning algorithms: Random Forest (RF), Gaussian Naive Bayes (GNB), Light GBM, Support Vector Machine (SVM), XGBoost (XGB), and Logistic Regression (LR) were trained and evaluated. Model performance was compared using the receiver operating characteristic curve (ROC) and precision-recall curve (PRC). SHAP (Shapley Additive Explanations) was used to rank risk factors, while LIME (Local Interpretable Model-Agnostic Explanations) was applied to visualize MC risk in individual cases.Results:Of the 525 patients, 135 (25.7%) developed postoperative MC. Among these, 80 (59.3%) experienced proximal junction kyphosis or failure (PJK/PJF), 7 (5.2%) had distal junction kyphosis or failure (DJK/DJF), 28 (20.7%) sustained rod fractures, and 29 (21.5%) showed significant loss of correction. In the validation cohort, the RF model achieved the highest area under the curve (AUC=0.80), followed by GNB (0.77), XGB (0.76), LR (0.74), LightGBM (0.73), and SVM (0.66). The RF model also demonstrated the best PRC value (0.58), highest sensitivity (0.65), and lowest Brier score (0.20). GNB, Light GBM, and LR models achieved the highest accuracy (0.78 each), while LightGBM exhibited the highest specificity (0.93). SHAP analysis identified higher preoperative VBQ scores, larger T 1 pelvic angle (TPA), and higher paraspinal muscle FI as the main risk factors for MC. Based on the RF model, a LIME-based tool was successfully constructed for individualized MC risk estimation. Conclusion:The RF model demonstrated the best overall predictive performance for MC. A machine learning-based prediction model has the potential to provide valuable guidance for surgical decision-making in ASD patients.
8.Establishment and application of ultra-fast real-time PCR for Brucella detection
Zhen-na XU ; Zhi-peng WU ; Wei-bin HONG ; Zhi-shen GUAN ; Qi-ming LIN ; Zuan-lan MO ; Yi-fei YE ; Hai-yan XIE ; Min LI ; Yan-qiu ZHU ; Xiao-jun LI ; Xian-peng ZHANG
Chinese Journal of Zoonoses 2025;41(3):278-283
This study was aimed at establishing a method of ultra-fast quantitative PCR for Brucella detection.We used an exogenous recombinant plasmid as the internal reference and targeted the T4SS secretion system,an important Brucella viru-lence factor,to design specific primers and probes.The sensitivity,specificity,and repeatability of this method were evaluated,and a standard curve was constructed.The coincidence rate of detection findings with this method versus quantitative PCR was determined.This method markedly decreased the detection time to only 10 minutes.The standard curve demonstrated a good linear relationship(Y=-3.410 7x+38.357,R2=0.998 5)with a low minimum detection limit of 10 copies/μL.The method exhibited good specificity and did not specifically amplify several common clinical bacteria other than Brucella.The de-tection of three concentrations of positive plasmids yielded coefficients of variation(CVs)of 0.20%to 0.91%,thus demonstra-ting the method's excellent repeatability.Furthermore,140 clinical samples were analyzed concurrently with the fluorescence PCR method,which yielded a 100%compliance rate and consistent results.Our findings indicated that the Brucella ultra-fast quantitative PCR was ultrafast;had high sensitivity,high specificity,and good specificity;and can be used for the clinical de-tection of Brucella and emergency investigation of epidemics.Therefore,this method is valuable for the early diagnosis of Bru-cella.
9.Validation and Forensic Application of a Domestic Human DNA Quantitative De-tection Kit
Jing CHEN ; Ya-Ping WANG ; Yun-Peng FENG ; Xiao-Xin HU ; Zhen-Jun JIA ; Hong-Di LIU ; An-Xin YAN ; Yong-Jiu LI ; Zhu PENG ; Zhi-Fang LIU ; Jian-Gang CHEN
Journal of Forensic Medicine 2025;41(3):252-259
Objective To verify the efficacy of a domestic human DNA quantification kit based on real-time fluorescence quantitative PCR in detecting the total human DNA concentration,male DNA concen-tration in mixed male/female DNA samples,the degree of DNA degradation and inhibitor tolerance.Methods Samples with different concentrations,different male/female ratios,different concentrations of inhibitors,and different degradation degrees were tested using the domestic human DNA quantification kit based on real-time fluorescence quantitative PCR.This kit was compared with a similar product on the market and was applied to the detection of DNA from real cases.Results This human DNA quan-tification kit can effectively detect human DNA as low as 0.001 65 ng/μL,and 6.25 pg/μL of male DNA in mixed samples with a male-to-female ratio of 1∶15 000.Even when the sample contains as high as 400 ng/μL of humic acid or 1 000 μmol/L of hemin alone,the DNA concentration can still be accurately detected.The degradation index can effectively characterize the degradation degree of the sample.This kit has been successfully applied in forensic practice.Conclusion This human DNA quan-tification kit is accurate and reliable in detection.It can accurately reflect the degradation of DNA and inhibitor tolerance.It has good performance in quantitative accuracy,determination of the male/female ratio in mixed samples,and inhibitor tolerance.It has application potential in forensic case examination.
10.Development of a visualizable machine learning model for mechanical complication risk in adult spinal deformity surgery
Jie LI ; Zhen TIAN ; Zhong HE ; Xiaodong QIN ; Jun QIAO ; Saihu MAO ; Benlong SHI ; Yong QIU ; Zezhang ZHU ; Zhen LIU
Chinese Journal of Orthopaedics 2025;45(17):1137-1146
Objective:To predict mechanical complications (MC) following spinal deformity surgery for adult spine deformity (ASD) using machine learning models, identify key risk factors, and develop a visualizable tool for individualized risk assessment.Methods:Clinical and radiological data from 525 patients with ASD who underwent surgery in our hospital between January 2017 and December 2021 were collected. Patients were randomly assigned to a training set (70%) and a test set (30%) for model development. The cohort included 88 males and 437 females, with a mean age of 42.2±18.1 years. Variables included demographic data, comorbidities, local and systemic radiological parameters, paraspinal muscle fat infiltration (FI), and vertebral bone quality (VBQ) scores. Multiple machine learning algorithms: Random Forest (RF), Gaussian Naive Bayes (GNB), Light GBM, Support Vector Machine (SVM), XGBoost (XGB), and Logistic Regression (LR) were trained and evaluated. Model performance was compared using the receiver operating characteristic curve (ROC) and precision-recall curve (PRC). SHAP (Shapley Additive Explanations) was used to rank risk factors, while LIME (Local Interpretable Model-Agnostic Explanations) was applied to visualize MC risk in individual cases.Results:Of the 525 patients, 135 (25.7%) developed postoperative MC. Among these, 80 (59.3%) experienced proximal junction kyphosis or failure (PJK/PJF), 7 (5.2%) had distal junction kyphosis or failure (DJK/DJF), 28 (20.7%) sustained rod fractures, and 29 (21.5%) showed significant loss of correction. In the validation cohort, the RF model achieved the highest area under the curve (AUC=0.80), followed by GNB (0.77), XGB (0.76), LR (0.74), LightGBM (0.73), and SVM (0.66). The RF model also demonstrated the best PRC value (0.58), highest sensitivity (0.65), and lowest Brier score (0.20). GNB, Light GBM, and LR models achieved the highest accuracy (0.78 each), while LightGBM exhibited the highest specificity (0.93). SHAP analysis identified higher preoperative VBQ scores, larger T 1 pelvic angle (TPA), and higher paraspinal muscle FI as the main risk factors for MC. Based on the RF model, a LIME-based tool was successfully constructed for individualized MC risk estimation. Conclusion:The RF model demonstrated the best overall predictive performance for MC. A machine learning-based prediction model has the potential to provide valuable guidance for surgical decision-making in ASD patients.

Result Analysis
Print
Save
E-mail