Dongfan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dongfan Wang has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Shibao Lu
Department of Orthopedics, Xuanwu Hospital, Capital Medical University, National Clinical Research Center for Geriatric Diseases, Beijing, China
17 shared publications - Xiaolong Chen
Department of Orthopedics, Xuanwu Hospital, Capital Medical University, National Clinical Research Center for Geriatric Diseases, Beijing, China
15 shared publications Wei Wang
Department of Orthopedics & Elderly Spinal Surgery, Xuanwu Hospital of Capital Medical University, National Clinical Research Center for Geriatric Diseases, Beijing, China
7 shared publications- Wei Wang
Nuclear Medicine Department, Beijing Friendship Hospital, Capital Medical University, Beijing, China
7 shared publications Chao Kong
Department of Orthopedics & Elderly Spinal Surgery, Xuanwu Hospital of Capital Medical University, National Clinical Research Center for Geriatric Diseases, Beijing, China
6 shared publicationsDi Han
Department of Orthopedics, Xuanwu Hospital, Capital Medical University, No.45 Changchun Street, Xicheng District, Beijing 100053, China
5 shared publications
Latest Publications
- Open Access
- 3 August 2026
- Published by Wolters Kluwer Health in Spine
Explainable Machine Learning for Perioperative Risk Stratification of Radiographic Adjacent Segment Degeneration After Short-Segment Lumbar Fusion
Study Design.: Retrospective Cohort Study. Objectives.: To develop and externally validate an explainable machine-learning framework for perioperative risk stratification of radiographic adjacent segment degeneration (ASDeg) after short-segment lumbar fusion. Summary of Background Data.: Radiographic ASDeg is frequently observed after lumbar fusion and may represent an early structural phenotype preceding symptomatic adjacent segment disease (ASDis) in some patients. However, existing risk assessment approaches are limited by heterogeneous risk factors, insufficient model interpretability, and limited external validation. Machine-learning methods may improve perioperative risk stratification by integrating clinical, radiographic, surgical, and functional variables. Methods.: Clinical data were retrospectively collected from two hospitals. The internal cohort included 570 patients who underwent posterior short-segment lumbar fusion for lumbar degenerative disease, and an independent cohort of 150 patients from another institution was used for external validation. The internal cohort was randomly divided into training and internal test sets at a 7:3 ratio using stratified sampling according to ASDeg status. Feature selection was performed exclusively in the training set using least absolute shrinkage and selection operator regression (LASSO), random forest-recursive feature elimination (RE-RFE), and Boruta. Five algorithms were developed and compared: logistic regression, random forest (RF), extreme gradient boosting (XGBoost), Light Gradient Boosting Machine(LightGBM), and multilayer perceptron (MLP). Model performance was evaluated using discrimination, calibration, precision-recall (P-R) analysis, and decision-curve analysis(DCA). Shapley Additive Explanations (SHAP) were used for model interpretation. Results.: Radiographic ASDeg occurred in 212 of 570 patients in the internal cohort. Five perioperative variables were retained for model construction: preoperative intervertebral space height (ISH), postoperative pelvic incidence-lumbar lordosis (PI-LL) mismatch, frailty, Coflex implantation, and preoperative Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC)-defined lower-extremity dysfunction. Among the candidate algorithms, the RF model showed the highest discriminative performance, with an AUROC of 0.782 in the internal test set and 0.749 in the external validation cohort. SHAP analysis identified preoperative ISH as the strongest contributor to model output. Conclusions.: This externally validated RF-based model provides a structured and interpretable framework for postoperative radiographic ASDeg risk stratification after short-segment lumbar fusion. By integrating clinically accessible perioperative variables, the model may support individualized imaging follow-up and provide a preliminary basis for future studies using symptomatic adjacent segment disease or revision surgery as clinically oriented endpoints.
- 3 August 2026
- Published by Wolters Kluwer Health in Spine
Open AccessExplainable Machine Learning for Perioperative Risk Stratification of Radiographic Adjacent Segment Degeneration After Short-Segment Lumbar Fusion
Study Design.: Retrospective Cohort Study. Objectives.: To develop and externally validate an explainable machine-learning framework for perioperative risk stratification of radiographic adjacent segment degeneration (ASDeg) after short-segment lumbar fusion. Summary of Background Data.: Radiographic ASDeg is frequently observed after lumbar fusion and may represent an early structural phenotype preceding symptomatic adjacent segment disease (ASDis) in some patients. However, existing risk assessment approaches are limited by heterogeneous risk factors, insufficient model interpretability, and limited external validation. Machine-learning methods may improve perioperative risk stratification by integrating clinical, radiographic, surgical, and functional variables. Methods.: Clinical data were retrospectively collected from two hospitals. The internal cohort included 570 patients who underwent posterior short-segment lumbar fusion for lumbar degenerative disease, and an independent cohort of 150 patients from another institution was used for external validation. The internal cohort was randomly divided into training and internal test sets at a 7:3 ratio using stratified sampling according to ASDeg status. Feature selection was performed exclusively in the training set using least absolute shrinkage and selection operator regression (LASSO), random forest-recursive feature elimination (RE-RFE), and Boruta. Five algorithms were developed and compared: logistic regression, random forest (RF), extreme gradient boosting (XGBoost), Light Gradient Boosting Machine(LightGBM), and multilayer perceptron (MLP). Model performance was evaluated using discrimination, calibration, precision-recall (P-R) analysis, and decision-curve analysis(DCA). Shapley Additive Explanations (SHAP) were used for model interpretation. Results.: Radiographic ASDeg occurred in 212 of 570 patients in the internal cohort. Five perioperative variables were retained for model construction: preoperative intervertebral space height (ISH), postoperative pelvic incidence-lumbar lordosis (PI-LL) mismatch, frailty, Coflex implantation, and preoperative Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC)-defined lower-extremity dysfunction. Among the candidate algorithms, the RF model showed the highest discriminative performance, with an AUROC of 0.782 in the internal test set and 0.749 in the external validation cohort. SHAP analysis identified preoperative ISH as the strongest contributor to model output. Conclusions.: This externally validated RF-based model provides a structured and interpretable framework for postoperative radiographic ASDeg risk stratification after short-segment lumbar fusion. By integrating clinically accessible perioperative variables, the model may support individualized imaging follow-up and provide a preliminary basis for future studies using symptomatic adjacent segment disease or revision surgery as clinically oriented endpoints.
- Open Access
- 20 July 2026
- Published by Wolters Kluwer Health in Spine
Cognitive Impairment as an Effect Modifier of Perioperative Risk in Elderly Patients Undergoing Lumbar Fusion Surgery
Study Design.: A retrospective study. Objective.: To identify perioperative risk factors with differential impacts under varying preoperative cognitive states in elderly patients (≥75 y) undergoing lumbar fusion and to investigate whether cognitive function exerts an effect-modifying role on the risk of major postoperative complications. Summary of Background Data.: Cognitive impairment is a risk factor for elderly patients undergoing lumbar fusion and is difficult to improve with short-term interventions; however, how other risk factors affect surgical outcomes in the presence of cognitive impairment remains unclear. Methods.: According to the education-adjusted Mini-Mental State Examination, Elderly patients who underwent lumbar fusion surgery were categorized into a cognitive impairment group (CI) and a non-cognitive impairment group (Non-CI). Postoperative outcomes were compared between groups, and multivariable regression analyses were performed to explore independent risk factors for major complications under different cognitive states. Interaction models were subsequently constructed to evaluate the effect-modifying role of cognitive status on candidate risk factors. Results.: Among 186 Non-CI patients and 57 CI patients, the incidence of major postoperative complications was significantly higher in the CI group (42.1% vs. 33.9%, P =0.023). In the overall cohort, cognitive impairment (AOR 0.89, 95% CI 0.83–0.95, P <0.001) were identified as independent risk factors for major complications. Interaction analyses confirmed significant interactions between cognitive impairment and diabetes, frailty, and intraoperative transfusion volume. Conclusions.: Preoperative cognitive impairment is not only an independent risk factor for major postoperative complications in elderly patients undergoing lumbar fusion but also functions as an effect modifier that significantly amplifies the impact of frailty, diabetes, and intraoperative transfusion volume on outcomes. Level of Evidence.: III.
- 20 July 2026
- Published by Wolters Kluwer Health in Spine
Open AccessCognitive Impairment as an Effect Modifier of Perioperative Risk in Elderly Patients Undergoing Lumbar Fusion Surgery
Study Design.: A retrospective study. Objective.: To identify perioperative risk factors with differential impacts under varying preoperative cognitive states in elderly patients (≥75 y) undergoing lumbar fusion and to investigate whether cognitive function exerts an effect-modifying role on the risk of major postoperative complications. Summary of Background Data.: Cognitive impairment is a risk factor for elderly patients undergoing lumbar fusion and is difficult to improve with short-term interventions; however, how other risk factors affect surgical outcomes in the presence of cognitive impairment remains unclear. Methods.: According to the education-adjusted Mini-Mental State Examination, Elderly patients who underwent lumbar fusion surgery were categorized into a cognitive impairment group (CI) and a non-cognitive impairment group (Non-CI). Postoperative outcomes were compared between groups, and multivariable regression analyses were performed to explore independent risk factors for major complications under different cognitive states. Interaction models were subsequently constructed to evaluate the effect-modifying role of cognitive status on candidate risk factors. Results.: Among 186 Non-CI patients and 57 CI patients, the incidence of major postoperative complications was significantly higher in the CI group (42.1% vs. 33.9%, P =0.023). In the overall cohort, cognitive impairment (AOR 0.89, 95% CI 0.83–0.95, P <0.001) were identified as independent risk factors for major complications. Interaction analyses confirmed significant interactions between cognitive impairment and diabetes, frailty, and intraoperative transfusion volume. Conclusions.: Preoperative cognitive impairment is not only an independent risk factor for major postoperative complications in elderly patients undergoing lumbar fusion but also functions as an effect modifier that significantly amplifies the impact of frailty, diabetes, and intraoperative transfusion volume on outcomes. Level of Evidence.: III.
- Open Access
- 20 July 2026
- Published by Wolters Kluwer Health in Spine
Degenerative Spinal Disease Subtypes Exhibit Distinct Gait and Neuromuscular Signatures
Study Design.: A retrospective study. Objective.: To characterize subtype-specific gait patterns and neuromuscular adaptations in DSD using integrated 3D motion capture and surface electromyography (sEMG). Background.: Degenerative spinal diseases (DSD), including lumbar spinal stenosis (LSS), adult spinal deformity (ASD), and cervical spondylotic myelopathy (CSM), commonly impair gait in elderly patients. Materials and Methods.: In this retrospective cross-sectional study, 148 participants (31 ASD, 40 LSS, 35 CSM, 42 healthy controls) underwent gait analysis with a BTS motion capture system and sEMG assessment of erector spinae, multifidus, gluteus maximus, and rectus abdominis muscles. Spatiotemporal parameters, root mean square maximum (RMSmax) and median frequencies (MF) were compared across stance and swing phases. Nonparametric statistical analyses were performed with significance at P P P P <0.001), indicating compromised neuromuscular control related to disease-specific pathology. Conclusion.: The study systematically revealed abnormal gait parameters and distinct activation patterns of core muscles in patients with degenerative spinal conditions, along with their underlying causes. Patients in the DSD group exhibited poorer bilateral lower limb gait stability and walking speed, with different muscle activation patterns due to varying causes. Level of Evidence.: Level IV
- 20 July 2026
- Published by Wolters Kluwer Health in Spine
Open AccessDegenerative Spinal Disease Subtypes Exhibit Distinct Gait and Neuromuscular Signatures
Study Design.: A retrospective study. Objective.: To characterize subtype-specific gait patterns and neuromuscular adaptations in DSD using integrated 3D motion capture and surface electromyography (sEMG). Background.: Degenerative spinal diseases (DSD), including lumbar spinal stenosis (LSS), adult spinal deformity (ASD), and cervical spondylotic myelopathy (CSM), commonly impair gait in elderly patients. Materials and Methods.: In this retrospective cross-sectional study, 148 participants (31 ASD, 40 LSS, 35 CSM, 42 healthy controls) underwent gait analysis with a BTS motion capture system and sEMG assessment of erector spinae, multifidus, gluteus maximus, and rectus abdominis muscles. Spatiotemporal parameters, root mean square maximum (RMSmax) and median frequencies (MF) were compared across stance and swing phases. Nonparametric statistical analyses were performed with significance at P P P P <0.001), indicating compromised neuromuscular control related to disease-specific pathology. Conclusion.: The study systematically revealed abnormal gait parameters and distinct activation patterns of core muscles in patients with degenerative spinal conditions, along with their underlying causes. Patients in the DSD group exhibited poorer bilateral lower limb gait stability and walking speed, with different muscle activation patterns due to varying causes. Level of Evidence.: Level IV
- 3 April 2026
- Published by Wolters Kluwer Health in Spine
A Novel Radiomics-Based Bone Quality Assessment for Early Prediction of Proximal Junctional Kyphosis in Patients with Adult Spinal Deformity
Study Design.: A retrospective analysis. Objective.: To explore the potential of radiomics as a novel bone assessment tool for early prediction of proximal junctional kyphosis (PJK) in adult spinal deformity (ASD). Background.: PJK is a prevalent complication following ASD surgery. Since impaired bone quality is a major risk factor, accurate preoperative bone assessment is crucial for early identification of high-risk patients. However, conventional metrics such as T-score, Hounsfield unit (HU) value, and vertebral bone quality (VBQ) score exhibit limitations in accuracy and reliability. Methods.: A total of 358 ASD patients were analyzed and randomly assigned to training and test sets (7:3). Radiomic features were extracted from lumbar CT and MRI scans to construct CT and MRI radiomics scores (CTRS/MRIRS). In parallel, T-score, HU value, and VBQ score were also evaluated. Univariable prediction models were first developed for each of the five bone metrics. Subsequently, multimodal models were constructed using the best-performing bone metric as the core variable, with additional selected clinical and radiographic parameters incorporated to further enhance predictive performance. Model performance was evaluated using AUROC, net reclassification improvement (NRI), and integrated discrimination improvement (IDI). Results.: Among univariable models, CTRS (AUROC=0.780) and T-score (AUROC=0.793) exhibited superior predictive performance compared to MRIRS (AUROC=0.694), HU value (AUROC=0.713), and VBQ score (AUROC=0.658). Multimodal models significantly outperformed their univariable counterparts (CTRS/T-score multimodal AUROC=0.880/0.885), with improved reclassification ability (CTRS univariable vs. multimodal: IDI=−0.2; T-score univariable vs. multimodal: NRI=−0.332, IDI=−0.247; all P <0.001). Conclusions.: The CT-based radiomics score presents a promising alternative to conventional bone quality metrics for early prediction of PJK after ASD surgery. Integrating CTRS with clinical and radiographic factors further enhances predictive accuracy, providing a valuable framework for preoperative risk stratification. Level of Evidence.: III
- 3 April 2026
- Published by Wolters Kluwer Health in Spine
A Novel Radiomics-Based Bone Quality Assessment for Early Prediction of Proximal Junctional Kyphosis in Patients with Adult Spinal Deformity
Study Design.: A retrospective analysis. Objective.: To explore the potential of radiomics as a novel bone assessment tool for early prediction of proximal junctional kyphosis (PJK) in adult spinal deformity (ASD). Background.: PJK is a prevalent complication following ASD surgery. Since impaired bone quality is a major risk factor, accurate preoperative bone assessment is crucial for early identification of high-risk patients. However, conventional metrics such as T-score, Hounsfield unit (HU) value, and vertebral bone quality (VBQ) score exhibit limitations in accuracy and reliability. Methods.: A total of 358 ASD patients were analyzed and randomly assigned to training and test sets (7:3). Radiomic features were extracted from lumbar CT and MRI scans to construct CT and MRI radiomics scores (CTRS/MRIRS). In parallel, T-score, HU value, and VBQ score were also evaluated. Univariable prediction models were first developed for each of the five bone metrics. Subsequently, multimodal models were constructed using the best-performing bone metric as the core variable, with additional selected clinical and radiographic parameters incorporated to further enhance predictive performance. Model performance was evaluated using AUROC, net reclassification improvement (NRI), and integrated discrimination improvement (IDI). Results.: Among univariable models, CTRS (AUROC=0.780) and T-score (AUROC=0.793) exhibited superior predictive performance compared to MRIRS (AUROC=0.694), HU value (AUROC=0.713), and VBQ score (AUROC=0.658). Multimodal models significantly outperformed their univariable counterparts (CTRS/T-score multimodal AUROC=0.880/0.885), with improved reclassification ability (CTRS univariable vs. multimodal: IDI=−0.2; T-score univariable vs. multimodal: NRI=−0.332, IDI=−0.247; all P <0.001). Conclusions.: The CT-based radiomics score presents a promising alternative to conventional bone quality metrics for early prediction of PJK after ASD surgery. Integrating CTRS with clinical and radiographic factors further enhances predictive accuracy, providing a valuable framework for preoperative risk stratification. Level of Evidence.: III
- Open Access
- 30 March 2026
- Published by Elsevier in Journal of Orthopaedic Translation
- Vol. 57
TRIM59 alleviates neuronal ferroptosis and promotes functional recovery after spinal cord injury by mediating ubiquitination and degradation of ANXA2
- 30 March 2026
- Published by Elsevier in Journal of Orthopaedic Translation
- Vol. 57
Open AccessTRIM59 alleviates neuronal ferroptosis and promotes functional recovery after spinal cord injury by mediating ubiquitination and degradation of ANXA2
- 26 February 2026
- Published by Springer Nature in European Spine Journal
- Vol. 35 (7) , 1-10
Core offset distance: a novel metric for regional imbalance and its association with postoperative coronal malalignment in degenerative lumbar scoliosis
- 26 February 2026
- Published by Springer Nature in European Spine Journal
- Vol. 35 (7) , 1-10
Core offset distance: a novel metric for regional imbalance and its association with postoperative coronal malalignment in degenerative lumbar scoliosis
- 15 October 2025
- Published by Springer Nature in European Spine Journal
- Vol. 35 (1) , 213-223
Oblique lateral interbody fusion with prioritized core vertebral correction technology for the treatment of lumbosacral curve-driven degenerative lumbar scoliosis
Objective This study aims to assess the effectiveness of oblique lateral interbody fusion, which prioritizes the correction of core distance, in comparison to traditional posterior surgery, in patients with lumbosacral curve-driven degenerative lumbar scoliosis. Methods This retrospective study analyzed consecutive patients with lumbosacral curve-driven degenerative lumbar scoliosis at a single institution from January 2019 to December 2023. The patients were divided into two groups: the traditional posterior approach group (n = 55) (Group T) and the prioritized core vertebral correction technology group (n = 52) (Group P-CV). Preoperative and postoperative data were analyzed using the SRS-22r score and imaging. To further illustrate the significance of prioritizing the core distance, a correlation analysis was conducted between the core distance and preoperative as well as postoperative coronal parameters. Results There was no significant difference in preoperative baseline data between two groups (P>0.05). Preoperative core distance was correlated with L4 tilt, L5 tilt, thoracolumbar Cobb, Aa, and CBD (PPPP<0.05). Conclusion The core vertebrae of patients with lumbosacral curve-driven degenerative lumbar scoliosis can be identified by distance measurement. Oblique lateral interbody fusion with prioritized core vertebral correction technology can effectively prevent coronal imbalance after surgery, thereby improving the lumbosacral curve. This technique provides a safe and effective approach for treating lumbosacral curve-driven degenerative lumbar scoliosis.
- 15 October 2025
- Published by Springer Nature in European Spine Journal
- Vol. 35 (1) , 213-223
Oblique lateral interbody fusion with prioritized core vertebral correction technology for the treatment of lumbosacral curve-driven degenerative lumbar scoliosis
Objective This study aims to assess the effectiveness of oblique lateral interbody fusion, which prioritizes the correction of core distance, in comparison to traditional posterior surgery, in patients with lumbosacral curve-driven degenerative lumbar scoliosis. Methods This retrospective study analyzed consecutive patients with lumbosacral curve-driven degenerative lumbar scoliosis at a single institution from January 2019 to December 2023. The patients were divided into two groups: the traditional posterior approach group (n = 55) (Group T) and the prioritized core vertebral correction technology group (n = 52) (Group P-CV). Preoperative and postoperative data were analyzed using the SRS-22r score and imaging. To further illustrate the significance of prioritizing the core distance, a correlation analysis was conducted between the core distance and preoperative as well as postoperative coronal parameters. Results There was no significant difference in preoperative baseline data between two groups (P>0.05). Preoperative core distance was correlated with L4 tilt, L5 tilt, thoracolumbar Cobb, Aa, and CBD (PPPP<0.05). Conclusion The core vertebrae of patients with lumbosacral curve-driven degenerative lumbar scoliosis can be identified by distance measurement. Oblique lateral interbody fusion with prioritized core vertebral correction technology can effectively prevent coronal imbalance after surgery, thereby improving the lumbosacral curve. This technique provides a safe and effective approach for treating lumbosacral curve-driven degenerative lumbar scoliosis.
- Open Access
- 31 August 2025
- Published by Asian Spine Journal (ASJ) in Asian Spine Journal
- Vol. 19 (4) , 619-630
Characteristics of the positional and morphological parameters of sagittal spine alignment in a cohort of 623 healthy individuals aged >50 years in China
Study Design: A retrospective radiologic study.Purpose: To investigate the spinopelvic positional and morphological parameters of the sagittal spinal alignment in a healthy population from the community.Overview of Literature: The existing parameters for spinal alignment based on the Cobb angle are the primary reference values for evaluating spinal alignment and pelvic morphology. However, they do not fully capture the comprehensive characteristics of sagittal spine alignment. More attention should be given to identifying the specific characteristics of sagittal spinal alignment by focusing on the positions of the kyphotic and lordotic apices.Methods: Among 1,250 volunteers, 623 consecutive normal community volunteers aged >50 years were recruited and underwent standing postural X-ray. A customized computer application analyzed the sagittal morphological and positional parameters, examining their normal distributions and correlations.Results: The correlation between the adjacent morphological and positional parameters was strong between the distal cervical and proximal lumbar spine. In the vertical direction, a significant association was found between the location of the thoracic kyphosis (TK) to lumbar lordosis (LL) transition point (TL point) and both the upper apex of TK (T-apex) (r=0.52) and lower apex of LL (L-apex) (r=0.64). In the horizontal direction, a moderate correlation was found between the thoracic apex offset to the femoral axis (TF) and the lumbar apex offset to the femoral axis (LF) (R2=0.314), whereas LF demonstrated a strong correlation with adjacent overhang (R2=0.685). Close correlations were observed among the morphological and positional parameters. The sacral slope exhibited significant correlations with two parameters related to the lumbar region: L-apex (r=−0.60) and LF (r=0.51).Conclusions: This study found strong correlations between spinopelvic morphology and position, which is crucial for understanding sagittal alignment. Adjacent positional parameters showed significant compliance within the sagittal spine plane from the distal cervical to proximal lumbar regions, suggesting the necessity for additional research on its clinical relevance in spinal disease surgery.
- 31 August 2025
- Published by Asian Spine Journal (ASJ) in Asian Spine Journal
- Vol. 19 (4) , 619-630
Open AccessCharacteristics of the positional and morphological parameters of sagittal spine alignment in a cohort of 623 healthy individuals aged >50 years in China
Study Design: A retrospective radiologic study.Purpose: To investigate the spinopelvic positional and morphological parameters of the sagittal spinal alignment in a healthy population from the community.Overview of Literature: The existing parameters for spinal alignment based on the Cobb angle are the primary reference values for evaluating spinal alignment and pelvic morphology. However, they do not fully capture the comprehensive characteristics of sagittal spine alignment. More attention should be given to identifying the specific characteristics of sagittal spinal alignment by focusing on the positions of the kyphotic and lordotic apices.Methods: Among 1,250 volunteers, 623 consecutive normal community volunteers aged >50 years were recruited and underwent standing postural X-ray. A customized computer application analyzed the sagittal morphological and positional parameters, examining their normal distributions and correlations.Results: The correlation between the adjacent morphological and positional parameters was strong between the distal cervical and proximal lumbar spine. In the vertical direction, a significant association was found between the location of the thoracic kyphosis (TK) to lumbar lordosis (LL) transition point (TL point) and both the upper apex of TK (T-apex) (r=0.52) and lower apex of LL (L-apex) (r=0.64). In the horizontal direction, a moderate correlation was found between the thoracic apex offset to the femoral axis (TF) and the lumbar apex offset to the femoral axis (LF) (R2=0.314), whereas LF demonstrated a strong correlation with adjacent overhang (R2=0.685). Close correlations were observed among the morphological and positional parameters. The sacral slope exhibited significant correlations with two parameters related to the lumbar region: L-apex (r=−0.60) and LF (r=0.51).Conclusions: This study found strong correlations between spinopelvic morphology and position, which is crucial for understanding sagittal alignment. Adjacent positional parameters showed significant compliance within the sagittal spine plane from the distal cervical to proximal lumbar regions, suggesting the necessity for additional research on its clinical relevance in spinal disease surgery.
- Open Access
- 24 June 2025
- Published by Wolters Kluwer Health in Spine
- Vol. 50 (24) , 1715-1727
Pelvic Incidence-Dependent Clustering of Sagittal Spinal Alignment in Asymptomatic Middle-Aged and Elderly Adults: A Machine Learning Approach
Study Design.: A cross-sectional cohort study. Objective.: This study aimed to refine the sagittal morphologic classification of the spine in asymptomatic middle-aged and elderly adult populations using the unsupervised machine learning (ML) techniques and, by leveraging these findings, to propose and validate a surgical correction reference for adult spinal deformity (ASD) patients across different morphologic subtypes. Summary of Background Data.: Restoration of sagittal alignment is the key to preventing mechanical complications and achieving good clinical outcomes in ASD surgery. However, high variations in the reported incidence of mechanical complications and clinical outcomes under current ASD realignment strategies have severely impeded the decision-making process for the optimal surgical plan. Materials and Methods.: This study cross-sectionally enrolled asymptomatic middle-aged and elderly Chinese adults. Sagittal spinal morphology clusters and pelvic incidence-based correction criteria for ASD realignment surgery were derived from whole spine radiographs using unsupervised ML algorithms. To externally validate the realignment strategy identified in asymptomatic adults, a consecutive cohort of ASD patients with sagittal deformity who underwent realignment surgery was examined for postoperative mechanical complications, unplanned reoperation, unplanned readmission, and clinical outcomes during follow-up. Results.: A total of 635 asymptomatic adults were enrolled for morphologic stratification, and 103 ASD patients with sagittal deformity were included for validation. The unsupervised ML algorithm successfully stratified spinal morphology into four clusters. The pelvic incidence-based surgical correction criteria computed by the regression algorithm demonstrated plausible clinical relevance, evidenced by the significantly lower incidence of postoperative mechanical complications, unplanned reoperation, unplanned readmission, and superior patient-reported outcomes in the restored group (conforming to the correction criteria) during follow-up. Conclusion.: In this study, unsupervised ML algorithm effectively partitioned asymptomatic sagittal spinal morphology into four distinct clusters. Using the pelvic incidence-based proportional correction criteria, ASD patients can anticipate a reduced incidence of mechanical complications and improved clinical outcomes following spinal realignment surgery. Level of Evidence.: Level Ⅲ.
- 24 June 2025
- Published by Wolters Kluwer Health in Spine
- Vol. 50 (24) , 1715-1727
Open AccessPelvic Incidence-Dependent Clustering of Sagittal Spinal Alignment in Asymptomatic Middle-Aged and Elderly Adults: A Machine Learning Approach
Study Design.: A cross-sectional cohort study. Objective.: This study aimed to refine the sagittal morphologic classification of the spine in asymptomatic middle-aged and elderly adult populations using the unsupervised machine learning (ML) techniques and, by leveraging these findings, to propose and validate a surgical correction reference for adult spinal deformity (ASD) patients across different morphologic subtypes. Summary of Background Data.: Restoration of sagittal alignment is the key to preventing mechanical complications and achieving good clinical outcomes in ASD surgery. However, high variations in the reported incidence of mechanical complications and clinical outcomes under current ASD realignment strategies have severely impeded the decision-making process for the optimal surgical plan. Materials and Methods.: This study cross-sectionally enrolled asymptomatic middle-aged and elderly Chinese adults. Sagittal spinal morphology clusters and pelvic incidence-based correction criteria for ASD realignment surgery were derived from whole spine radiographs using unsupervised ML algorithms. To externally validate the realignment strategy identified in asymptomatic adults, a consecutive cohort of ASD patients with sagittal deformity who underwent realignment surgery was examined for postoperative mechanical complications, unplanned reoperation, unplanned readmission, and clinical outcomes during follow-up. Results.: A total of 635 asymptomatic adults were enrolled for morphologic stratification, and 103 ASD patients with sagittal deformity were included for validation. The unsupervised ML algorithm successfully stratified spinal morphology into four clusters. The pelvic incidence-based surgical correction criteria computed by the regression algorithm demonstrated plausible clinical relevance, evidenced by the significantly lower incidence of postoperative mechanical complications, unplanned reoperation, unplanned readmission, and superior patient-reported outcomes in the restored group (conforming to the correction criteria) during follow-up. Conclusion.: In this study, unsupervised ML algorithm effectively partitioned asymptomatic sagittal spinal morphology into four distinct clusters. Using the pelvic incidence-based proportional correction criteria, ASD patients can anticipate a reduced incidence of mechanical complications and improved clinical outcomes following spinal realignment surgery. Level of Evidence.: Level Ⅲ.
- 30 May 2025
- Published by Springer Nature in European Spine Journal
- Vol. 34 (10) , 4475-4485
Thoracic and pelvic compensation during lumbar degeneration: a retrospective study of 625 asymptomatic adults
- 30 May 2025
- Published by Springer Nature in European Spine Journal
- Vol. 34 (10) , 4475-4485
Thoracic and pelvic compensation during lumbar degeneration: a retrospective study of 625 asymptomatic adults