Spine最新文献

{"title":"Pedicle Enhancement on contrast-enhanced MRI As A Risk Factor for Progressive Collapse in Acute Osteoporotic Compression Fractures.","authors":"Byung-Jou Lee, Seonghoon Jeong, Kwang Hyeon Kim, Hae-Won Koo","doi":"10.1097/BRS.0000000000005444","DOIUrl":"https://doi.org/10.1097/BRS.0000000000005444","url":null,"abstract":"<p><strong>Study design: </strong>Retrospective study.</p><p><strong>Objective: </strong>To verify the association between pedicle enhancement (PE) on contrast-enhanced magnetic resonance imaging (MRI) and progressive collapse, and analyze the correlation between the degree of PE and progressive collapse.</p><p><strong>Summary of background data: </strong>Osteoporotic compression fracture (OCF) is generally considered a stable fracture, with most patients achieving successful recovery through conservative treatment such as bracing and physical therapy. However, in some cases, progressive collapse occurs, requiring additional treatment or surgery.</p><p><strong>Methods: </strong>We enrolled 203patitents and analyzed factors related to progressive collapse. We evaluated the association between PE and progressive collapse and determined the best cult off value of the signal-to-noise ratio of PE (SNR of PE) for predicting progressive collapse. Survival analysis using Kaplan-Meier curve was performed to assess the cumulative risk of positive progressive collapse over time.</p><p><strong>Results: </strong>Presence of PE, SNR of PE, age, body mass index, and segmental kyphosis were significantly correlated with progressive collapse. The optimal cutoff point of SNR of PE was measured at 89.3 with 71.1% and 78.7% sensitivity and specificity, respectively, with an AUC of 0.781. Analysis of cumulative progressive collapse incidence revealed a significant difference between the PE and NPE groups within 1-2 months after OCF, which stabilized after three months.</p><p><strong>Conclusions: </strong>PE is a significant predictor of progressive collapse in OCF within a year, aiding spine surgeons in risk assessment of progressive collapse and management of acute OCF.</p><p><strong>Level of evidence: </strong>3.</p>","PeriodicalId":22193,"journal":{"name":"Spine","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144529611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Postoperative Physical Therapy Utilization for Anterior Cervical Discectomy and Fusion: An Analysis of Practice Patterns in the United States.","authors":"Justin M Lantz, William J Karakash, Andy T Ton, Andreas Remis, Henry Avetisian, David B Anderson, Yogi Matharu, Ram K Alluri, Zorica Buser","doi":"10.1097/BRS.0000000000005442","DOIUrl":"https://doi.org/10.1097/BRS.0000000000005442","url":null,"abstract":"<p><strong>Study design/setting: </strong>Retrospective Cohort Study.</p><p><strong>Objective: </strong>To describe postoperative physical therapy (PostopPT) utilization patterns and evaluate predictors of utilization after anterior cervical discectomy and fusion (ACDF).</p><p><strong>Background context: </strong>ACDF is the most common cervical spine procedure. PostopPT may improve outcomes, but current usage and program characteristics are unknown.</p><p><strong>Methods: </strong>PearlDiver Database identified patients who underwent ACDF between 2010-April 2023. PostopPT utilization was assessed 7-365 days postoperatively. Demographics, comorbidities, and procedural characteristics were analyzed. Univariate and multivariate logistic regression identified predictors of PostopPT utilization.</p><p><strong>Results: </strong>Of 309,230 ACDF patients, 17.16% utilized PostopPT within one year. Among users, the average number of visits was 7.4, with mean initiation at 88 days (median: 61 d). PostopPT users were younger, had higher comorbidity burden, higher income, were more often female, and more likely to present with combined radiculopathy and myelopathy (P<0.001).Demographic predictors included commercial insurance (OR: 1.37), residence in the Northeast (OR: 1.35) or Midwest (OR: 1.31), income >$75,000 (OR: 1.17), female gender (OR: 1.14), and age <50 (OR: 1.10) (all P<0.001). Comorbidity predictors included fibromyalgia (OR: 1.37), osteoarthritis (OR: 1.30), obesity (OR: 1.29), depression (OR: 1.26), osteoporosis (OR: 1.19), ECI ≥4 (OR: 1.13), diabetes (OR: 1.08), and tobacco use (OR: 1.07) (all P<0.001). Procedural predictors included mixed myelopathy/radiculopathy (OR: 1.29), fusion ≥3 levels (OR: 1.22), orthopedic surgeon as provider (OR: 1.10), inpatient surgery (OR: 1.09), and two-level fusion (OR: 1.08) (all P<0.001).Patients with myelopathy alone were more likely to receive gait training, aquatic therapy, and group training, but less likely to receive manual therapy, electrical stimulation, hot/cold therapy, or ultrasound (all P<0.001).</p><p><strong>Conclusions: </strong>PostopPT usage following ACDF is limited. Distinct demographic, comorbidity, and procedural factors predicted usage. PostopPT programs varied in timing, frequency, and intervention type.</p>","PeriodicalId":22193,"journal":{"name":"Spine","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144529612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sex Differences in Patient-Rated Outcomes After Lumbar Spinal Fusion for Degenerative Disease: A Multicenter Cohort Study.","authors":"Olga Ciobanu-Caraus, Alexandra Grob, Jonas Rohr, Vittorio Stumpo, Luca Ricciardi, Nicolai Maldaner, Hubert A J Eversdijk, Moira Vieli, Antonino Raco, Massimo Miscusi, Andrea Perna, Luca Proietti, Giorgio Lofrese, Michele Dughiero, Francesco Cultrera, Marcello D'Andrea, Seong B An, Yoon Ha, Aymeric Amelot, Jorge B Cadelo, Jose M Viñuela-Prieto, Maria L Gandía-González, Pierre-Pascal Girod, Sara Lener, Nikolaus Kögl, Anto Abramovic, Christoph J Laux, Mazda Farshad, Dave O'Riordan, Markus Loibl, Fabio Galbusera, Anne F Mannion, Alba Scerrati, Pasquale De Bonis, Granit Molliqaj, Enrico Tessitore, Marc L Schröder, Martin N Stienen, Giovanna Brandi, Luca Regli, Carlo Serra, Victor E Staartjes","doi":"10.1097/BRS.0000000000005183","DOIUrl":"10.1097/BRS.0000000000005183","url":null,"abstract":"<p><strong>Study design: </strong>Heterogeneous data collection through a mix of prospective, retrospective, and ambispective methods.</p><p><strong>Objective: </strong>To evaluate the effect of biological sex on patient-reported outcomes after spinal fusion surgery for lumbar degenerative disease.</p><p><strong>Summary of background data: </strong>Current literature suggests sex differences regarding clinical outcome after spine surgery may exist. Substantial methodological heterogeneity and limited comparability of studies warrants further investigation of sex-related differences in treatment outcomes.</p><p><strong>Materials and methods: </strong>We analyzed patients who underwent spinal fusion with or without pedicle screw insertion for lumbar degenerative disease included within a multinational study, comprising patients from 11 centers in seven countries. Absolute values and change scores (change from preoperative baseline to postoperative follow-up) for 12-month functional impairment [Oswestry disability index (ODI)] and back and leg pain severity [numeric rating scale (NRS)] were compared between male and female patients. Minimum clinically important difference (MCID) was defined as >30% improvement.</p><p><strong>Results: </strong>Six-hundred sixty (59%) of 1115 included patients were female. Female patients presented with significantly baseline ODI (51.5±17.2 vs. 47.8±17.9, P <0.001), back pain (6.96±2.32 vs. 6.60±2.30, P =0.010) and leg pain (6.49±2.76 vs. 6.01±2.76, P =0.005). At 12 months, female patients still reported significantly higher ODI (22.76±16.97 vs. 20.50±16.10, P =0.025), but not higher back (3.13±2.38 vs. 3.00±2.40, P =0.355) or leg pain (2.62±2.55 vs. 2.34±2.43, P =0.060). Change scores at 12 months did not differ significantly among male and female patients in ODI (∆1.31, 95% CI: -3.88 to 1.25, P =0.315), back (∆0.22, 95% CI: -0.57 to 0.12, P =0.197), and leg pain (∆0.16, 95% CI: -0.56 to 0.24, P =0.439). MCID at 12 months was achieved in 330 (77.5%) male patients and 481 (76.3%) female patients ( P =0.729) for ODI.</p><p><strong>Conclusion: </strong>Both sexes experienced a similar benefit from surgery in terms of relative improvement in scores for functional impairment and pain. Although female patients reported a higher degree of functional impairment and pain preoperatively, at 12 months only their average scores for functional impairment remained higher than those for their male counterparts, while absolute pain scores were similar for female and male patients.</p>","PeriodicalId":22193,"journal":{"name":"Spine","volume":" ","pages":"924-931"},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12147751/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142508391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Posterior Ligamentous Augmentation is Associated With Reduced Rates of Proximal Junctional Kyphosis and Failure in Adult Spinal Deformity Surgery: A Systematic Review and Meta-Analysis of 1333 Patients.","authors":"Pavlos Texakalidis, Stavros Matsoukas, Mykhaylo Krushelnytskyy, Kevin Swong, Najib El Tecle, Tyler R Koski, Nader S Dahdaleh","doi":"10.1097/BRS.0000000000005299","DOIUrl":"10.1097/BRS.0000000000005299","url":null,"abstract":"<p><strong>Study design: </strong>Systematic review and meta-analysis.</p><p><strong>Objective: </strong>To evaluate the impact of posterior ligamentous augmentation (PLA) on proximal junctional kyphosis (PJK) and proximal junctional failure (PJF) in adult spinal deformity (ASD) surgery.</p><p><strong>Summary of background data: </strong>Adult spinal deformity (ASD) surgery is frequently complicated by PJK and PJF, with reported rates ranging from 17% to 61.7%. Techniques such as PLA, which involves spinous process or sublaminar tethering at the upper instrumented vertebra (UIV) +1 or +2, have been investigated as potential methods to mitigate these complications.</p><p><strong>Materials and methods: </strong>A systematic literature review and meta-analysis was performed according to the PRISMA guidelines. Most studies defined PJK as an increase of ≥10° or ≥20° in the sagittal Cobb angle from UIV to UIV+2 compared with preoperative measurements. PJF was defined as PJK necessitating revision surgery.</p><p><strong>Results: </strong>Eight comparative studies comprising 1333 patients (PLA: 579; no PLA: 754) were included. The mean age ranged from 55 to 68.6 years across studies, with a mean follow-up period of 17.6 to 31.2 months. There were no significant differences between the PLA and no PLA groups in terms of age (MD: 2.53; 95% CI: -0.28 to 5.34, I2 : 64.8%), BMI (MD: 1.03; 95% CI: -0.87 to 2.93, I2 : 69%), or sagittal vertical axis (SVA) preoperatively (MD: 3.92; 95% CI: -1.90 to 9.75, I2 : 73.1%) and postoperatively (MD: -1.54; 95% CI: -4.10 to 1.01, I2 : 56.2%). However, the PLA group demonstrated significantly lower odds of developing PJK compared with the no PLA group (PLA: 25.8%; no PLA: 28.8%; OR: 0.54; 95% CI: 0.34-0.85, I2 : 37.4%). Furthermore, PLA was associated with significantly lower odds of PJF (PLA: 3.3%; no PLA: 12.3%; OR: 0.23; 95% CI: 0.12-0.47, I2 : 17.9%).</p><p><strong>Conclusions: </strong>PLA in ASD surgery is associated with reduced odds of developing PJK and PJF over a follow-up period of 17.6 to 31.2 months.</p>","PeriodicalId":22193,"journal":{"name":"Spine","volume":" ","pages":"932-939"},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143459557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preoperative Symptom Duration and the Effect on Clinical Outcomes and PROMIS-PF in Patients Undergoing Lumbar Fusion Surgery.","authors":"Andrea H Johnson, Jane C Brennan, Parimal Rana, Sarah Hall, Justin J Turcotte, Chad Patton","doi":"10.1097/BRS.0000000000005134","DOIUrl":"10.1097/BRS.0000000000005134","url":null,"abstract":"<p><strong>Study design: </strong>Retrospective review.</p><p><strong>Objective: </strong>The purpose of this study is to examine the effect of preoperative symptom duration on postoperative clinical outcomes for patients undergoing lumbar fusion surgery.</p><p><strong>Summary of background data: </strong>Lumbar fusion surgery can be significantly beneficial for lumbar spondylolisthesis and spinal stenosis. Surgical treatment is typically preceded by some amount of nonoperative intervention and there is no consensus on the optimal timing between symptom onset and surgical intervention.</p><p><strong>Materials and methods: </strong>A retrospective review of 144 patients undergoing a one-level to three-level lumbar fusion from June 2020 to December 2023 was performed. Demographics, preoperative symptom onset, primary diagnosis, and surgical procedure were compared between patients with less than or greater than two years of symptoms. Postoperative outcomes and PROMIS-PF were compared between groups. Univariate and multivariate analyses were performed.</p><p><strong>Results: </strong>Fifty-two (36.1%) had symptoms for two years or longer while 92 (63.9%) had symptoms for less than two years. There was no difference in demographics, procedure type, primary diagnosis, or preoperative symptoms between those who had symptoms for greater than or less than two years. Those who had symptoms for 2+ years had a significantly lower change in PF (4.7±7.1 vs. 7.7±9.0; P =0.029) and lower rate of MCID achievement (44.2% vs. 65.2%; P =0.023). There was no difference in outcomes by symptom duration. On multivariate analysis those with symptoms of two years or more were 2.4 times less likely to achieve an MCID (OR: 0.42, 95% CI: 0.19-0.92; P =0.031).</p><p><strong>Conclusion: </strong>Patients undergoing lumbar fusion with greater than two years of symptoms before surgery have a smaller increase in PROMIS-PF and are less likely to achieve MCID on PROMIS-PF. Further study is needed to determine the optimal timing for lumbar fusion surgery following symptom onset.</p>","PeriodicalId":22193,"journal":{"name":"Spine","volume":" ","pages":"E248-E252"},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142081602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Thoracolumbar Sagittal Morphology and Segmental Inclination: A Cross-sectional Cohort Study of Asymptomatic Adult Volunteers.","authors":"Weipeng Qiu, Zhuoran Sun, Siyu Zhou, Zimu Chen, Gengyu Han, Da Zou, Yi Zhao, Ze Chen, Qiang Qi, Weishi Li","doi":"10.1097/BRS.0000000000005189","DOIUrl":"10.1097/BRS.0000000000005189","url":null,"abstract":"<p><strong>Study design: </strong>A cross-sectional cohort study.</p><p><strong>Objective: </strong>To present a normative value reference of spinal segmental inclination stratified by age and pelvic incidence (PI), and to clarify the impact of segmental inclination on spinal sagittal morphology.</p><p><strong>Summary of background data: </strong>Thoracolumbar segmental inclination has been shown to correlate with the clinical outcomes of adult spinal deformity surgery. However, there currently exists no normative value reference in a large sample of asymptomatic population.</p><p><strong>Materials and methods: </strong>Asymptomatic adult volunteers were enrolled from the community. All volunteers underwent a standing full-spine anteroposterior and lateral radiograph. Lumbar tilt (LT) and thoracic tilt (TT) were measured to quantify the segmental inclination of the lumbar and thoracic spine. Regional curvature, global balance, and thoracolumbar apex were analyzed across different age and PI groups. The correlation between sagittal parameters and age was analyzed using Pearson correlation tests.</p><p><strong>Results: </strong>A total of 618 volunteers were included with a mean age of 38.7 ± 17.1 years (range 18-82 yr). As age increased, the LT and TT significantly increased ( P <0.001). The LT was significantly correlated with PI (r=0.410, P <0.001), with the low PI group exhibiting a greater negative LT. The TT remained constant across different PI groups. Compared with the young and middle-aged groups, the thoracic apex and lumbar apex were located more caudally in the elderly group ( P <0.001). Subjects with a more caudal lumbar apex exhibited a greater negative LT, and those with a more caudal thoracic apex exhibited a greater positive TT.</p><p><strong>Conclusions: </strong>The thoracic spine naturally adapts to a relatively neutral position, yet it tends to tilt forward with aging. The physiological lumbar inclination is predominantly determined by the PI value with a slight backward tilt and tends to counteract the anterior truncal inclination with advanced age. Physiological segmental inclination should be considered in spinal surgical planning.</p>","PeriodicalId":22193,"journal":{"name":"Spine","volume":" ","pages":"916-923"},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142508405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Glucagon-Like Peptide-1 Receptor Agonist Medications Alter Outcomes of Spine Surgery: A Study Among Over 15,000 Patients.","authors":"Joshua M Wiener, Parshva A Sanghvi, Katelyn Vlastaris, Thomas Mroz, Jonathan Belding, David C Kaelber, Thomas Olson, Kevin P Francis, John S Adams, Nicholas Bernthal, William L Sheppard","doi":"10.1097/BRS.0000000000005283","DOIUrl":"10.1097/BRS.0000000000005283","url":null,"abstract":"<p><strong>Study design: </strong>Retrospective cohort study.</p><p><strong>Objective: </strong>To investigate the relationship between perioperative glucagon-like peptide-1 receptor agonists (GLP-1 RAs) and postoperative outcomes after spinal fusion in obese and diabetic patient populations.</p><p><strong>Background: </strong>GLP-1 RAs have been shown to be beneficial when used perioperatively in clinical orthopedic arthroplasty literature. Minimal evidence exists showing efficacy with respect to spinal fusion.</p><p><strong>Materials and methods: </strong>This retrospective, multi-center study accessed the TriNetX platform, using the research database to identify diabetic patients who underwent spinal fusion between 2008 and 2022. Cohorts were created based on body mass index and GLP-1 RA usage. Propensity score matching was employed to create balanced cohorts utilizing body mass index, hemoglobin A1c, surgical intervention, as well as other demographic characteristics. Orthopedic outcomes were compared between GLP-1 RA users and non-users. The primary outcomes included postoperative infection, readmission, revision surgery, and quality of life metrics.</p><p><strong>Results: </strong>After matching, the study cohort consisted of 2263 patients, with 1560 classified as obese. GLP-1 RA use was associated with significantly reduced postoperative infection rates [obese: HR = 0.168 (0.086, 0.328), not obese: HR = 0.250 (0.102, 0.612)], fewer revisions [obese: HR = 0.505 (0.368, 0.693), not obese: HR = 0.439 (0.272, 0.708)], decreased postoperative readmission rates [obese: HR = 0.283 (0.243, 0.329), not obese: HR = 0.241 (0.193, 0.301)], and reduced mobility abnormalities [obese: HR = 0.355 (0.230, 0.549), not obese: HR = 0.508 (0.269, 0.959)]. No significant differences were observed in rates of fracture rates between GLP-1 RA users and non-users.</p><p><strong>Conclusions: </strong>GLP-1 RA use in spinal fusion patients was associated with improved postoperative outcomes, including lower infection rates, fewer revisions, and better quality of life metrics. These findings suggest that GLP-1 RAs may be a valuable adjunctive therapy in managing surgical outcomes in diabetic and obese patients undergoing spinal fusion. Further prospective and animal-based studies are needed to confirm these findings and explore the underlying mechanisms.</p>","PeriodicalId":22193,"journal":{"name":"Spine","volume":" ","pages":"871-880"},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143080943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Invited Comment to Letter to the Editor Regarding the Manuscript \"Adjacent Level Canal Area Changes up to 2 Years After Lumbar Spinal Stenosis Decompressive Surgery\".","authors":"Helena Brisby, Erland Hermansen","doi":"10.1097/BRS.0000000000005378","DOIUrl":"https://doi.org/10.1097/BRS.0000000000005378","url":null,"abstract":"","PeriodicalId":22193,"journal":{"name":"Spine","volume":"50 13","pages":"E269"},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144267264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Scoliosis Cobb Angle Classification in Biplanar Radiograph Imaging With Explainable Machine Learning Models.","authors":"Jennifer Yu, Yash S Lahoti, Kyle C McCandless, Nikan K Namiri, Matthew S Miyasaka, Hamza Ahmed, Junho Song, John J Corvi, Daniel C Berman, Samuel K Cho, Jun S Kim","doi":"10.1097/BRS.0000000000005312","DOIUrl":"10.1097/BRS.0000000000005312","url":null,"abstract":"<p><strong>Study design: </strong>Retrospective cohort study.</p><p><strong>Objective: </strong>To quantify the pathology of the spine in patients with scoliosis through one-dimensional feature analysis.</p><p><strong>Summary of background data: </strong>Biplanar radiograph (EOS) imaging is a low-dose technology offering high-resolution spinal curvature measurement, crucial for assessing scoliosis severity and guiding treatment decisions. Machine learning (ML) algorithms, utilizing one-dimensional image features, can enable automated Cobb angle classification, improving accuracy and efficiency in scoliosis evaluation while reducing the need for manual measurements, thus supporting clinical decision-making.</p><p><strong>Methods: </strong>This study used 816 annotated AP EOS spinal images with a spine segmentation mask and a 10° polynomial to represent curvature. Engineered features included the first and second derivatives, Fourier transform, and curve energy, normalized for robustness. XGBoost selected the top 32 features. The models classified scoliosis into multiple groups based on curvature degree, measured through Cobb angle. To address the class imbalance, stratified sampling, undersampling, and oversampling techniques were used, with 10-fold stratified K-fold cross-validation for generalization. An automatic grid search was used for hyperparameter optimization, with K-fold cross-validation (K=3).</p><p><strong>Results: </strong>The top-performing model was Random Forest, achieving an ROC AUC of 91.8%. An accuracy of 86.1%, precision of 86.0%, recall of 86.0%, and an F1 score of 85.1% were also achieved. Of the three techniques used to address class imbalance, stratified sampling produced the best out-of-sample results. SHAP values were generated for the top 20 features, including spine curve length and linear regression error, with the most predictive features ranked at the top, enhancing model explainability.</p><p><strong>Conclusions: </strong>Feature engineering with classical ML methods offers an effective approach for classifying scoliosis severity based on Cobb angle ranges. The high interpretability of features in representing spinal pathology, along with the ease of use of classical ML techniques, makes this an attractive solution for developing automated tools to manage complex spinal measurements.</p>","PeriodicalId":22193,"journal":{"name":"Spine","volume":" ","pages":"E259-E267"},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143504331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pelvic Incidence-Dependent Clustering of Sagittal Spinal Alignment in Asymptomatic Middle-Aged and Elderly Adults: A Machine Learning Approach.","authors":"Qijun Wang, Dongfan Wang, Xiangyu Li, Weiguo Zhu, Peng Cui, Zheng Wang, Wei Wang, Jeffrey C Wang, Xiaolong Chen, Shibao Lu","doi":"10.1097/BRS.0000000000005441","DOIUrl":"https://doi.org/10.1097/BRS.0000000000005441","url":null,"abstract":"<p><strong>Study design: </strong>A cross-sectional cohort study.</p><p><strong>Objective: </strong>This study aimed to refine the sagittal morphological 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 morphological subtypes.</p><p><strong>Summary of background data: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>A total of 635 asymptomatic adults were enrolled for morphological 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.</p><p><strong>Conclusion: </strong>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.</p><p><strong>Level of evidence: </strong>Ⅲ.</p>","PeriodicalId":22193,"journal":{"name":"Spine","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144476789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}