Cervical spinal cord injury without fracture-dislocation (CSCIWFD) is referred to as a special type of cervical spinal cord injury characterized by traumatic spinal cord dysfunction and no significant bony structural abnormalities on imagines. Duo to the high risk of missed diagnosis during the initial consultation, CSCIWFD may lead to progressive neurological deterioration or even complete paralysis, severely impacting patients′ prognosis. Currently, there are no established consensuses over the diagnosis and treatment of CSCIWFD, such as the lack of evidence-based standards for indications of non-surgical treatment and risk of secondary neurological injury, as well as debates over the optimal timing for surgical intervention and indications for different surgical approaches. To address these issues, the Spine Trauma Group of the Orthopedic Branch of the Chinese Medical Doctor Association organized experts in the relevant fields to formulate Diagnosis and treatment guideline for acute cervical spinal cord injury without fracture- dislocation in adults ( version 2025) . Based on evidence-based medicine and the principles of scientific rigor and clinical applicability, the guidelines proposed 11 recommendations covering terminology, diagnosis, evaluation treatment, and rehabilitation, etc., aiming to standardize the management of CSCIWFD.

Objective:To investigate the surgical outcomes of congenital cervicothoracic scoliosis (CTS) patients with Klippel-Feil syndrome (KFS) and prognostic characteristics across different subtypes.Methods:A retrospective case series study is conducted. Clinical and radiographic data of 41 CTS patients with KFS who underwent hemivertebra resection with instrumentation at Department of Orthopedic Surgery, Nanjing Drum Tower Hospital from March 2012 to September 2022, with a minimum follow-up of two years, were analyzed. The cohort included 16 males and 25 females, aged (8.6±3.7) years (range: 3 to 15 years). Preoperative, immediate postoperative, and final follow-up cervicothoracic deformity parameters were compared. Patients were classified into three subtypes based on preoperative coronal alignment: shoulder-neck type (type A, 16 cases), trunk-tilt type (type B, 16 cases), and thoracic compensatory curve type (type C, 9 cases). The severity of KFS and the incidence of distal curve progression among subtypes were analyzed. Repeated measurement data were compared by repeated measurement ANOVA, pairwise comparison within groups was performed by Bonferroni method, and categorical variables were compared by Chi-square test or Fisher exact probability method.Results:All patients underwent successful surgery. Twenty-one patients (53.7%) had cervical fusion of ≥3 segments, and 63.1% (82/130) of fused cervical segments were located proximally to the instrumentation. Postoperative cervicothoracic Cobb angle, head tilt, head shift, neck tilt, and clavicle angle significantly improved (all P<0.05). The proportion of patients with cervical fusion of ≥3 segments was higher in types B and C (17/25) than that in type A (5/16) ( χ2=5.299, P=0.021). Four type B (4/16) and 5 type C (5/9) patients underwent long-segment fixation, with stable coronal alignment postoperatively. The remaining patients received short-segment fixation. In the short-segment group, the incidence of distal curve progression was significantly higher in types B and C (8/16) than that in type A (1/16) ( P=0.015). Ultimately, 3 type B patients underwent revision surgery, and 1 type C patient met the criteria for revision (distal compensatory thoracic or lumbar curve>40°). Conclusions:CTS patients with KFS are predisposed to develop significant coronal malalignment involving trunk tilt (type B) or thoracic compensatory curve (type C) before surgery. Following hemivertebra resection with short-segment fixation, such patients have a high risk of distal curve progression and potential need for revision surgery.

Objective:To compare the clinical efficacy of Minimally Invasive Surgery (MIS) and traditional Posterior Spinal Fusion (PSF) in treating children with paralytic scoliosis with pelvic obliquity (PSPO) following spinal cord injury.Methods:A retrospective analysis was conducted on the data of 25 patients with PSPO who underwent surgical treatment at the Drum Tower Hospital affiliated with Nanjing University Medical School from January 2017 to June 2023. The cohort included 4 males and 21 females, aged 12.3±2.8 years (range 9-14 years). Patients were divided into the MIS group (12 cases) and the PSF group (13 cases). Radiological parameters were measured preoperatively, postoperatively, and at the last follow-up. Surgical time, intraoperative blood loss, intraoperative blood transfusion volume, length of hospital stay, total hospitalization costs, and complications were recorded. The Scoliosis Research Society questionnaires-22 (SRS-22) Chinese version were used to assess patient satisfaction and efficacy.Results:There were no statistically significant differences between the MIS and PSF groups in age, gender, Risser sign, preoperative Cobb angle for scoliosis, pelvic tilt angle, or local kyphosis angle ( P>0.05). The MIS group demonstrated surgical time of 176±30 minutes, intraoperative blood loss of 300±70 ml, blood transfusion volume of 280±175 ml, and total hospitalization costs of 87'800± 13'300 yuan, all of which were lower than PSF group, with values of 280±91 minutes, 1'433±116 ml, 1'351±996 ml, and 14'8400±26'100 yuan, respectively. These differences were statistically significant ( t=3.789, P=0.001; t=29.328, P<0.001; t=3.667, P=0.001; t=7.271, P<0.001). In the MIS group, preoperative, postoperative, and last follow-up Cobb angles were 79.11°±6.74°, 35.86°±4.98°, and 36.27°±4.84° respectively; pelvic tilt angles were 24.79°±5.58°, 9.18°±3.32°, and 8.79°±2.94°; local kyphosis angles were 38.84°±4.18°, 12.96°±4.87°, and 11.43°±6.08°, respectively. Postoperative and last follow-up angles were significantly reduced compared to preoperative values, with statistically significant differences ( P<0.05). In the PSF group, preoperative, postoperative, and last follow-up Cobb angles were 82.06°±9.26°, 34.75°±5.14°, and 35.15°±5.04° respectively; pelvic tilt angles were 26.60°±6.21°, 10.12°±3.21°, and 9.91°±2.97°; local kyphosis angles were 40.92°±7.04°, 10.92°±7.26°, and 14.02°±5.58°, respectively. Differences from preoperative to postoperative measurements were statistically significant ( P<0.05). At the last follow-up, both groups showed no significant loss of scoliosis correction, and there were no statistically significant differences between the groups postoperatively or at the last follow-up ( P>0.05). In the MIS group, one case of superficial surgical site infection and one case of postoperative atelectasis occurred. In the PSF group, two cases of deep surgical site infection, one case of poor screw placement, and two cases were transferred to the ICU postoperatively due to excessive intraoperative bleeding. Preoperative SRS-22 total scores were 2.0±0.6 for PSF and 2.1±0.4 for MIS. Postoperative SRS-22 total scores (excluding satisfaction) were 3.0±0.5 for PSF and 2.9±0.3 for MIS. The within-group differences from preoperative to postoperative were statistically significant ( P<0.05), while the between-group differences from preoperative to postoperative were not statistically significant ( P>0.05). Conclusion:Compared to the PSF technique, MIS can shorten surgery time, reduce intraoperative blood loss and perioperative complications, and decrease hospitalization costs. MIS can achieve similar early clinical efficacy.

Objective:To explore a selective resection strategy for combined lumbosacral hemivertebra (LSHV) and thoracolumbar hemivertebra/lumbar hemivertebra (TLHV/LHV) double-balanced hemivertebra deformities.Methods:A retrospective analysis was conducted on 21 patients aged over 10 years with lumbosacral and thoracolumbar or lumbar combined hemimetameric segmental shift (HMMS) deformities who underwent surgery at Nanjing Drum Tower Hospital between May 2009 and October 2022. The cohort included 7 males and 14 females, with a mean surgical age of 21.5±10.9 years (range: 12-55 years) and a mean follow-up duration of 32.8±15.9 months (range: 24-74 months). Patients were divided into two groups based on preoperative coronal balance: the balanced group (Type A) and the unbalanced group (Type C). Radiographic parameters, including the major Cobb angle, lumbosacral take-off angle, kyphotic angle, coronal balance distance (CBD), and the deviation of the upper instrumented vertebra (UIV), were measured preoperatively, postoperatively, and at the final follow-up. Surgical complications were also recorded.Results:Of the 21 patients, 11 were classified as preoperatively balanced, and 10 as unbalanced. The deformity angular ratio of thoracolumbar to lumbosacral curves was significantly higher in the balanced group than in the unbalanced group (0.9±0.3 vs. 0.6±0.2; t=2.143, P=0.045). The preoperative main curve Cobb angles in the balanced and imbalanced groups were 71.3°±22.3° and 58.6°±8.2°, respectively. One week postoperatively, these angles were reduced to 38.4°±17.6° and 31.3°±5.6°, and were maintained at 40.0°±18.1° and 32.6°±5.6° at the final follow-up, all differences were statistically significant ( P<0.05). The preoperative lumbosacral take-off angles were 37.5°±9.1° in the balanced group and 36.7°±7.7° in the imbalanced group, which decreased to 18.4°±9.4° and 19.2°±5.5° at 1 week postoperatively, and remained at 19.4°±10.1° and 19.6°±5.8° at the final follow-up. These changes were also statistically significant ( P<0.05). In the balanced group, the UIV tilt angle, the CBD and the deviation of the UIV, were all significantly reduced compared to preoperative values ( P<0.05). Among the 21 patients, LSHV resection was performed in 15 cases, and TLHV/LHV resection was performed in 7 cases. Among the 15 patients with kyphosis, TLHV/LHV resection was performed in 6 cases. In the balanced group, 9 patients maintained type A postoperatively, including 4 patients with LSHV resection, 2 with TLHV/LHV resection, 2 with both LSHV and TLHV/LHV resection, 1 without resection of both hemivertebra. Two patients in the balanced group who underwent TLHV/LHV resection experienced postoperative deterioration to type C. In the unbalanced group, 8 cases with LSHV resection improved to type A, while 1 case with LSHV resection and 1 case with neither resection maintained C-type. In the LSHV resection group, CBD improved from 29.8±15.2 mm to 13.9±5.7 mm postoperatively and remained stable at 14.6±8.6 mm at final follow-up. Only 1 patient in this group experienced worsened coronal imbalance. In contrast, in the non-LSHV resection group, CBD worsened from 17.2 ± 8.7 mm to 19.7±12.1 mm postoperatively, progressing further to 20.5±13.0 mm at follow-up. Three patients in this group had worsening coronal imbalance, and 2 required revision surgery. Reported complications included 3 cases of internal fixation fracture, 1 case of proximal junctional kyphosis, and 1 case of acute incision infection. Conclusions:Effective resection of lumbosacral hemivertebrae is the preferred selective strategy, particularly for patients with preoperative coronal imbalance, as it significantly reduces the risk of worsening coronal imbalance and internal fixation-related complications. However, selective resection involving only TLHV or LHV without addressing LSHV in preoperatively balanced patients may increase the risk of postoperative coronal imbalance.

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.

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.

Objective:To compare the clinical efficacy of Minimally Invasive Surgery (MIS) and traditional Posterior Spinal Fusion (PSF) in treating children with paralytic scoliosis with pelvic obliquity (PSPO) following spinal cord injury.Methods:A retrospective analysis was conducted on the data of 25 patients with PSPO who underwent surgical treatment at the Drum Tower Hospital affiliated with Nanjing University Medical School from January 2017 to June 2023. The cohort included 4 males and 21 females, aged 12.3±2.8 years (range 9-14 years). Patients were divided into the MIS group (12 cases) and the PSF group (13 cases). Radiological parameters were measured preoperatively, postoperatively, and at the last follow-up. Surgical time, intraoperative blood loss, intraoperative blood transfusion volume, length of hospital stay, total hospitalization costs, and complications were recorded. The Scoliosis Research Society questionnaires-22 (SRS-22) Chinese version were used to assess patient satisfaction and efficacy.Results:There were no statistically significant differences between the MIS and PSF groups in age, gender, Risser sign, preoperative Cobb angle for scoliosis, pelvic tilt angle, or local kyphosis angle ( P>0.05). The MIS group demonstrated surgical time of 176±30 minutes, intraoperative blood loss of 300±70 ml, blood transfusion volume of 280±175 ml, and total hospitalization costs of 87'800± 13'300 yuan, all of which were lower than PSF group, with values of 280±91 minutes, 1'433±116 ml, 1'351±996 ml, and 14'8400±26'100 yuan, respectively. These differences were statistically significant ( t=3.789, P=0.001; t=29.328, P<0.001; t=3.667, P=0.001; t=7.271, P<0.001). In the MIS group, preoperative, postoperative, and last follow-up Cobb angles were 79.11°±6.74°, 35.86°±4.98°, and 36.27°±4.84° respectively; pelvic tilt angles were 24.79°±5.58°, 9.18°±3.32°, and 8.79°±2.94°; local kyphosis angles were 38.84°±4.18°, 12.96°±4.87°, and 11.43°±6.08°, respectively. Postoperative and last follow-up angles were significantly reduced compared to preoperative values, with statistically significant differences ( P<0.05). In the PSF group, preoperative, postoperative, and last follow-up Cobb angles were 82.06°±9.26°, 34.75°±5.14°, and 35.15°±5.04° respectively; pelvic tilt angles were 26.60°±6.21°, 10.12°±3.21°, and 9.91°±2.97°; local kyphosis angles were 40.92°±7.04°, 10.92°±7.26°, and 14.02°±5.58°, respectively. Differences from preoperative to postoperative measurements were statistically significant ( P<0.05). At the last follow-up, both groups showed no significant loss of scoliosis correction, and there were no statistically significant differences between the groups postoperatively or at the last follow-up ( P>0.05). In the MIS group, one case of superficial surgical site infection and one case of postoperative atelectasis occurred. In the PSF group, two cases of deep surgical site infection, one case of poor screw placement, and two cases were transferred to the ICU postoperatively due to excessive intraoperative bleeding. Preoperative SRS-22 total scores were 2.0±0.6 for PSF and 2.1±0.4 for MIS. Postoperative SRS-22 total scores (excluding satisfaction) were 3.0±0.5 for PSF and 2.9±0.3 for MIS. The within-group differences from preoperative to postoperative were statistically significant ( P<0.05), while the between-group differences from preoperative to postoperative were not statistically significant ( P>0.05). Conclusion:Compared to the PSF technique, MIS can shorten surgery time, reduce intraoperative blood loss and perioperative complications, and decrease hospitalization costs. MIS can achieve similar early clinical efficacy.

Objective:To explore a selective resection strategy for combined lumbosacral hemivertebra (LSHV) and thoracolumbar hemivertebra/lumbar hemivertebra (TLHV/LHV) double-balanced hemivertebra deformities.Methods:A retrospective analysis was conducted on 21 patients aged over 10 years with lumbosacral and thoracolumbar or lumbar combined hemimetameric segmental shift (HMMS) deformities who underwent surgery at Nanjing Drum Tower Hospital between May 2009 and October 2022. The cohort included 7 males and 14 females, with a mean surgical age of 21.5±10.9 years (range: 12-55 years) and a mean follow-up duration of 32.8±15.9 months (range: 24-74 months). Patients were divided into two groups based on preoperative coronal balance: the balanced group (Type A) and the unbalanced group (Type C). Radiographic parameters, including the major Cobb angle, lumbosacral take-off angle, kyphotic angle, coronal balance distance (CBD), and the deviation of the upper instrumented vertebra (UIV), were measured preoperatively, postoperatively, and at the final follow-up. Surgical complications were also recorded.Results:Of the 21 patients, 11 were classified as preoperatively balanced, and 10 as unbalanced. The deformity angular ratio of thoracolumbar to lumbosacral curves was significantly higher in the balanced group than in the unbalanced group (0.9±0.3 vs. 0.6±0.2; t=2.143, P=0.045). The preoperative main curve Cobb angles in the balanced and imbalanced groups were 71.3°±22.3° and 58.6°±8.2°, respectively. One week postoperatively, these angles were reduced to 38.4°±17.6° and 31.3°±5.6°, and were maintained at 40.0°±18.1° and 32.6°±5.6° at the final follow-up, all differences were statistically significant ( P<0.05). The preoperative lumbosacral take-off angles were 37.5°±9.1° in the balanced group and 36.7°±7.7° in the imbalanced group, which decreased to 18.4°±9.4° and 19.2°±5.5° at 1 week postoperatively, and remained at 19.4°±10.1° and 19.6°±5.8° at the final follow-up. These changes were also statistically significant ( P<0.05). In the balanced group, the UIV tilt angle, the CBD and the deviation of the UIV, were all significantly reduced compared to preoperative values ( P<0.05). Among the 21 patients, LSHV resection was performed in 15 cases, and TLHV/LHV resection was performed in 7 cases. Among the 15 patients with kyphosis, TLHV/LHV resection was performed in 6 cases. In the balanced group, 9 patients maintained type A postoperatively, including 4 patients with LSHV resection, 2 with TLHV/LHV resection, 2 with both LSHV and TLHV/LHV resection, 1 without resection of both hemivertebra. Two patients in the balanced group who underwent TLHV/LHV resection experienced postoperative deterioration to type C. In the unbalanced group, 8 cases with LSHV resection improved to type A, while 1 case with LSHV resection and 1 case with neither resection maintained C-type. In the LSHV resection group, CBD improved from 29.8±15.2 mm to 13.9±5.7 mm postoperatively and remained stable at 14.6±8.6 mm at final follow-up. Only 1 patient in this group experienced worsened coronal imbalance. In contrast, in the non-LSHV resection group, CBD worsened from 17.2 ± 8.7 mm to 19.7±12.1 mm postoperatively, progressing further to 20.5±13.0 mm at follow-up. Three patients in this group had worsening coronal imbalance, and 2 required revision surgery. Reported complications included 3 cases of internal fixation fracture, 1 case of proximal junctional kyphosis, and 1 case of acute incision infection. Conclusions:Effective resection of lumbosacral hemivertebrae is the preferred selective strategy, particularly for patients with preoperative coronal imbalance, as it significantly reduces the risk of worsening coronal imbalance and internal fixation-related complications. However, selective resection involving only TLHV or LHV without addressing LSHV in preoperatively balanced patients may increase the risk of postoperative coronal imbalance.

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.

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.