Neurospine最新文献

{"title":"Rates of Subsequent Lumbar Surgery Following Spinal Fusion in Patients With Parkinson Disease: A Propensity-Score Matched Nationwide Cohort Analysis.","authors":"Chang Hwa Ham, Joo Han Kim, Jong Hyun Kim, Joonho Byun, Hong Joo Moon, Woo-Keun Kwon","doi":"10.14245/ns.26520470.0235","DOIUrl":"10.14245/ns.26520470.0235","url":null,"abstract":"<p><strong>Objective: </strong>Parkinson disease (PD) is frequently characterized by a forward-bent posture that increases biomechanical stress on the lumbar spine, which increases the rate of subsequent lumbar surgeries after spinal fusions. This study aimed to evaluate the rates of additional lumbar surgeries following spinal fusion in patients with PD.</p><p><strong>Methods: </strong>Data from the Health Insurance Review and Assessment Service of the Republic of Korea were retrospectively analyzed. PD was identified using the International Classification of Diseases, 10th Revision code G20. Patients with PD were matched with those without PD in a 3:1 ratio based on sex, age, and Charlson Comorbidity Index using the greedy nearest neighbor matching method. The primary outcome was the rate of subsequent lumbar surgeries following spinal fusion within the 7-year follow-up period. The timing of these reoperations was also assessed.</p><p><strong>Results: </strong>A total of 2,287 patients with PD and 6,861 matched patients without PD were included in this study. The prevalence of PD among patients undergoing lumbar fusion surgery remained stable throughout the study period. Patients with PD had 1.6-fold higher odds to undergo reoperation compared with the non-PD cohort. No significant difference was observed in the timing of additional surgeries between the groups.</p><p><strong>Conclusion: </strong>Patients with PD faced 1.6-fold higher odds of subsequent lumbar surgeries following spinal fusion compared to those without the disease. This finding suggests the need for a cautious treatment approach and thorough preoperative optimization when considering lumbar fusion in this population.</p>","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 3","pages":"538-546"},"PeriodicalIF":5.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13448124/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148685415","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":"Clinically Meaningful Improvement Across Ages 50-95 Years After Decompression Without Fusion for Central Lumbar Spinal Stenosis Without Spondylolisthesis.","authors":"Henrik Damm, Magnus K Karlsson, Lars Jehpsson, Niyaz Hareni, Björn E Rosengren","doi":"10.14245/ns.26520722.0361","DOIUrl":"10.14245/ns.26520722.0361","url":null,"abstract":"<p><strong>Objective: </strong>Advanced age has been proposed as a risk factor for worse outcomes and higher complication rates after spinal surgery. We assessed whether decompression for central lumbar spinal stenosis (CLSS) provided meaningful improvement in patients aged 50-95 years.</p><p><strong>Methods: </strong>We evaluated preoperative and 1-year postoperative Numerical Rating Scale (NRS) leg and back pain, Oswestry Disability Index (ODI), and complications in 17,987 patients aged ≥50 years undergoing decompression without fusion for CLSS without spondylolisthesis from the Swespine register. Meaningful improvement was defined using minimal clinically important difference (MCID) thresholds for NRS leg/back pain and ODI. Across 5-year age groups, we assessed the proportions improving ≥MCID and odds ratios (ORs) with 95% confidence intervals (CIs), using ages 65-69 years as the reference group.</p><p><strong>Results: </strong>Across age groups, 71%-80% improved ≥MCID in ≥1 outcome. Compared with the reference group, ORs (95% CI) for ≥MCID improvement were lower in ages 70-74 (0.8; 0.7-1.0), 75-79 (0.7; 0.6-0.8), 80-84 (0.6; 0.5-0.7), and 85-89 (0.6; 0.5-0.8); no other age groups differed. 5%-12% experienced complications. Compared with the reference group, ORs (95% CI) for complications were higher in ages 75-79 (1.3; 1.1-1.6), 80-84 (1.7; 1.4-2.1), and 85-89 (2.0; 1.5-2.8), and lower in ages 55-59 (0.7; 0.5-0.9).</p><p><strong>Conclusion: </strong>77% of patients aged 50-95 years improved ≥MCID after decompression without fusion for CLSS without spondylolisthesis. Although outcomes were slightly worse and complication rates higher in older than younger patients, decompression without fusion remains effective across this age range.</p>","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 3","pages":"580-592"},"PeriodicalIF":5.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13448122/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148685362","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":"When Is Fusion Necessary in Addressing Symptomatic Adjacent Level Pathology - A Commentary on \"How to Treat Adjacent-Segment Pathology Following Lumbar Fusion Surgery: Decompression Alone or Decompression With Extended Fusion Surgery?\"","authors":"Marc A Arslanian, Vignessh Kumar, Lee A Tan","doi":"10.14245/ns.26521324.0662","DOIUrl":"10.14245/ns.26521324.0662","url":null,"abstract":"","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 3","pages":"561-563"},"PeriodicalIF":5.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13448103/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148685022","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":"Response Letter: Reconsidering Intraoperative Hip Positioning in Single-Position Lateral Lumbar Interbody Fusion - A Commentary on \"Optimal Positioning for Single-Position Lateral Lumbar Interbody Fusion\".","authors":"Worawat Limthongkul, Natavut Prasertkul, Pakawas Praisarnti, Maruay Tanayavong, Surachat Jaroenwareekul, Wicharn Yingsakmongkol, Weerasak Singhatanadgige, Vit Kotheeranurak","doi":"10.14245/ns.26520526.0263","DOIUrl":"10.14245/ns.26520526.0263","url":null,"abstract":"","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 3","pages":"756-757"},"PeriodicalIF":5.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13448116/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148685428","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":"Toward a Candidate Endoscopic Spine Surgery Registry Framework: Lessons From Global Spine Registry Models.","authors":"Vit Kotheeranurak, Jin-Sung Kim, Inbo Han, Hyeun-Sung Kim, Thanapol Ultarnpatumros, Chinati Puinongpo, Javier Quillo-Olvera, Lei Jiang, Christoph Siepe, Worawat Limthongkul, Weerasak Singhatanadgige, Surachat Jaroenwareekul","doi":"10.14245/ns.26520624.0312","DOIUrl":"10.14245/ns.26520624.0312","url":null,"abstract":"<p><strong>Objective: </strong>Endoscopic spine surgery (ESS) has expanded rapidly, but existing spine registries do not consistently capture ESS-specific technical variables, ultra-early recovery trajectories, selective imaging validation, or dissemination-related learning-curve effects. This review synthesizes established spine registry models, contemporary consensus initiatives, and digital follow-up approaches to propose a candidate ESS-specific registry framework and preliminary Minimum Data Set (MDS) for future validation.</p><p><strong>Methods: </strong>A structured narrative review was conducted on national and multinational spine registries, relevant consensus initiatives, and digital follow-up models. Sources were reviewed with emphasis on governance, data architecture, workflow design, patient-reported outcome measures (PROMs) integration, follow-up structure, data linkage, validation strategies, and implementation feasibility.</p><p><strong>Results: </strong>Established registries provide a methodological foundation for benchmarking, complication surveillance, longitudinal PROM capture, and real-world evidence generation. However, ESS requires modular augmentation of existing registry infrastructures to capture approach-specific operative details, early recovery, selective imaging phenotypes, and governance-controlled maturity indicators. The proposed candidate MDS is organized into 4 domains: (1) baseline case-mix and phenotyping, (2) procedure-specific technical and perioperative variables, (3) selective quantitative imaging and morphometric validation, and (4) structured longitudinal outcome surveillance. The framework prioritizes an essential core dataset while separating recommended, optional, research-oriented, and governance-controlled modules, including digitally enabled early follow-up, opioid-related outcomes, radiation exposure, advanced imaging, and learning-curve variables.</p><p><strong>Conclusion: </strong>A candidate ESS-specific registry framework may support harmonized data capture, real-world evidence generation, quality feedback, and future registry-based research. Formal Delphi consensus, multicenter feasibility testing, and staged integration into existing spine registry infrastructures are required before broader implementation.</p>","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 3","pages":"605-624"},"PeriodicalIF":5.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13448037/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148684988","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":"From the Editor-in-Chief: Featured Articles in the July 2026 Issue.","authors":"Inbo Han","doi":"10.14245/ns.26521276.0638","DOIUrl":"10.14245/ns.26521276.0638","url":null,"abstract":"","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 3","pages":"513-514"},"PeriodicalIF":5.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13448035/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148685340","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":"The MSI-20 Score Provides Reproducible Mortality Risk Stratification in Spinal Infection: A Multicenter Registry Study and External Validation.","authors":"Sara Lener, Raphael Gmeiner, Anto Abramovic, Anna Koller, Christoph Orban, Sebastian Hartmann, Alexandra Grob, Victor Staartjes, Ann Kathrin Joerger, Carolin Albrecht, Bernhard Meyer, Felipa Lange, Andreas Kramer, Florian Ringel, Christopher Marvin Jesse, Ralph T Schär, Christoph Bettag, Veit Rohde, Insa K Janssen, Karl Schaller, Julia Onken, Aminaa Sanchin, Peter Vajkoczy, Imran Shah, Rebecca Sutherland, Andreas K Demetriades, Claudius Thomé","doi":"10.14245/ns.26520814.0407","DOIUrl":"10.14245/ns.26520814.0407","url":null,"abstract":"<p><strong>Objective: </strong>Spinal infection (SI) is associated with substantial morbidity and mortality, and optimal treatment strategies remain debated, particularly in medically fragile patients. The Mortality in Spinal Infection (MSI-20) score was developed as the first dedicated prognostic tool for mortality risk estimation, but external validation in large cohorts has been lacking. This study aimed to externally validate the MSI-20 in a large multicenter registry cohort and assess its performance, clinical thresholds, and generalizability.</p><p><strong>Methods: </strong>This retrospective multi-institutional registry study included 1,122 adult patients with clinically, radiologically, and laboratory-confirmed SI treated at 6 tertiary referral centers between 2010 and 2023. The multicenter registry design enabled robust analysis of this relatively rare outcome. MSI-20 scores were calculated according to the original definition. Predictive performance was evaluated using receiver operating characteristic (ROC) analysis with 95% confidence intervals. Mortality across score strata and center-wise performance were analyzed, with exploratory assessment of additional baseline predictors.</p><p><strong>Results: </strong>Mean age was 66.4±13.1 years, and overall mortality was 18.3%. The MSI-20 demonstrated fair discriminative ability (area under the curve [AUC], 0.68; 95% confidence interval [CI], 64-72). The optimal ROC threshold was 3.5; a cutoff ≥4 yielded sensitivity 0.49 and specificity 0.74 (F1 score, 0.38). Mortality increased progressively, approaching 50% (47.4%) at scores ≥9. Performance was consistent across centers (AUC, 0.60-0.75). Exploratory univariable analyses did not identify additional baseline variables with consistent strong associations beyond the MSI-20 components.</p><p><strong>Conclusion: </strong>This large multicenter registry study provides the first external validation of the MSI-20, confirming reproducibility and generalizability. The score demonstrated fair discrimination and a clear risk gradient across increasing score categories. Given its simplicity and high negative predictive value, the MSI-20 may serve as an adjunctive tool to support risk communication, multidisciplinary discussion, patient counseling, and preoperative optimization in spinal infection.</p>","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 3","pages":"625-632"},"PeriodicalIF":5.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13448032/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148684997","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":"Diagnostic Value of Metagenomic Next-Generation Sequencing for Suspected Native Spinal Brucella Infection: A Multicenter Study.","authors":"Zhaohui Li, Qiang Zhang, Huafeng Wang, Zehua Zhang, Jiaming Liu, Litao Li, Yuhan Lin, Yuelei Wang, Chuqiang Yin, Wenqiao Wang, Feng Shen, Zengshuai Han, Shenshen Hao, Peishan Cong, Tingting Tian, Qing Liu, XiaoTong Chen, HongQi Zhan, Tao Peng, Xiang Yu, XinKai Pu, Xiaofeng Lian, Ting Wang","doi":"10.14245/ns.2551698.849","DOIUrl":"10.14245/ns.2551698.849","url":null,"abstract":"<p><strong>Objective: </strong>The aim is to study the diagnostic positive rates of metagenomic next-generation sequencing (mNGS), microbial culture, and serologic testing in suspected native spinal brucellosis, and to evaluate the clinical value of their combined application.</p><p><strong>Methods: </strong>In this multicenter, retrospective observational study, 128 patients with suspected native spinal brucellosis from 6 medical centers (February 2020 to February 2025) were enrolled. Specimens from infection sites were subjected to microbial culture, mNGS, and serological testing (agglutination test).</p><p><strong>Results: </strong>Of the 128 patients with suspected native spinal Brucella infections, 118 patients were diagnosed with Brucella spondylitis. Among the 118 confirmed Brucella spondylitis cases, mNGS demonstrated a positivity rate of 92.37% (109 of 118), significantly higher than that of culture (26.27%, 31 of 118) and agglutination test (83.05%, 98 of 118). In the 87 culture-negative samples, mNGS detected Brucella in 91.95% (80 of 87), compared to 82.76% (72 of 87) by agglutination test. mNGS confirmed Brucella infection in all 16 cases that were agglutination test negative. mNGS combined with agglutination tests can effectively complement each other, improving the sensitivity of diagnosis and thereby minimizing missed diagnoses to the greatest extent. Among the 10 nonbrucellar spinal pathologies, agglutination test showed a high false-positive rate of 90% (9 of 10), whereas mNGS had a 10% (1 of 10) false-positive rate. Therefore, the agglutination test has a relatively high rate of false positives.</p><p><strong>Conclusion: </strong>mNGS detection represents an effective adjunct to microbial culture and the agglutination test. The concurrent use of all 3 methods enhances diagnostic accuracy and reduces the likelihood of missed and incorrect diagnoses, significantly improving patient prognosis and guiding personalized clinical treatment.</p>","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 2","pages":"487-499"},"PeriodicalIF":5.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13152692/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147840997","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":"Frailty-Muscle Phenotypes Predict Outcomes After Lumbar Fusion in Adults Aged ≥75 Years: A Retrospective Cohort Study.","authors":"Ma Chao Guo, Xiangyu Li, Shuaikang Wang, Xiaolong Chen, Chao Kong, Yuxi Liu, Shibao Lu","doi":"10.14245/ns.2551838.919","DOIUrl":"10.14245/ns.2551838.919","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate whether combining clinical frailty with magnetic resonance imaging (MRI)-derived posterior paraspinal muscle degeneration identifies perioperative risk phenotypes in adults aged ≥75 years undergoing lumbar fusion.</p><p><strong>Methods: </strong>We retrospectively studied patients aged ≥75 years undergoing lumbar fusion with preoperative lumbar MRI. Frailty was assessed using the Fried phenotype (frail: score ≥3). Posterior paraspinal muscle degeneration across L1-S1 was quantified using automated segmentation and a composite posterior frailty index (PFI); severe degeneration was defined as the upper quartile of PFI. Patients were classified into 4 frailty×muscle phenotypes. Primary outcomes were any in-hospital complication and prolonged length of stay (LOS ≥16 days).</p><p><strong>Results: </strong>Among 248 patients, phenotypes A-D (A, nonfrail/nonsevere; B, frail/nonsevere; C, nonfrail/severe; D, frail/severe) comprised 132, 54, 20, and 42 patients, respectively. Any in-hospital complication occurred in 18.2% of phenotype A compared with 50.0%-57.1% in phenotypes B-D (p<0.001). Prolonged LOS (≥16 days; cohort 75th percentile) occurred in 0.8% of phenotype A versus 38.9% (B), 35.0% (C), and 78.6% (D) (p<0.001), corresponding to absolute risk increases of +34.2 to +77.8 percentage points. After adjustment, higher-risk phenotypes remained independently associated with increased odds of any complication and prolonged LOS; however, the prolonged-LOS odds estimates were imprecise due to sparse events in the reference group. Phenotype was not independently associated with 90-day readmission. Pain improvement (ΔVAS [visual analogue scale]) was attenuated in phenotypes B and D, while differences in ΔODI (Oswestry Disability Index) were not statistically significant.</p><p><strong>Conclusion: </strong>Integrating frailty and MRI-based posterior paraspinal degeneration provides actionable stratification of complication and prolonged LOS risk after lumbar fusion in older adults.</p>","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 2","pages":"242-254"},"PeriodicalIF":5.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13152687/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147840973","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":"From Pixels to Precision: Generative Artificial Intelligence as a Paradigm Shift in Spine Imaging-Technical Foundations, Clinical Applications, and the Path to Safe Clinical Deployment.","authors":"Daniyal Ashraf, Vivek Sanker, Linda Liverani, Chelsea Park, Ravi Teja Medikonda, Maria Jose Cavagnaro, Ikchan Jeon, John Ratliff, Atman Desai","doi":"10.14245/ns.2551862.931","DOIUrl":"10.14245/ns.2551862.931","url":null,"abstract":"<p><p>Spine imaging represents a complex diagnostic frontier characterized by anatomical variability, motion artifacts, metallic instrumentation interference, and significant inter-reader diagnostic variability (κ=0.20 across institutions). While conventional discriminative artificial intelligence (AI) models achieve >95% accuracy in detecting degenerative changes, they remain limited by data scarcity, heterogeneous protocols, and poor generalizability. In the spine, these limitations are particularly relevant because clinical decisions can often depend on subtle distinctions (such as differentiating levels of canal or foraminal stenosis, characterizing Modic endplate changes, or assessing pedicle and vertebral morphology), where small inconsistencies can meaningfully alter management or surgical planning. Generative AI (GenAI) systems-including generative adversarial networks (GANs), diffusion models, and vision-language models (VLMs)-offer a paradigm shift by learning underlying data structures to generate high-quality synthetic outputs rather than merely classifying existing data. This narrative review, conducted using SANRA (scale for the assessment of narrative review articles) methodology across PubMed, Scopus, Embase, and Cochrane Library, examined GenAI applications in spine imaging. Eligible studies included observational designs through randomized controlled trials exploring image reconstruction, synthetic computed tomography (CT) generation, segmentation, and surgical planning applications. GAN-generated synthetic magnetic resonance imaging sequences reduce scan times by ~40% while maintaining diagnostic confidence; diffusion models enable radiation-free synthetic CT for preoperative planning; and VLMs generate structured radiology reports with hallucination rates <1.12%. However, critical barriers impede clinical translation: external validation gaps reveal AI performance collapse in real-world cohorts (sensitivity drops to 54.9% in cervical fracture detection); hallucinations and anatomical inaccuracies risk misguiding implant sizing; bias amplification magnifies demographic underrepresentation; and fragmented, small datasets lack standardized benchmarks. Technical fragility, computational demands, clinician trust deficits, and unresolved regulatory frameworks for iteratively-updating systems remain unaddressed. Successful integration requires coordinated development across 5 priorities: (1) multi-institutional datasets with cross-vendor harmonization, (2) federated learning frameworks preserving privacy, (3) uncertainty quantification and explainability tools, (4) outcome-linked clinical validation replacing technical metrics, and (5) workflow-integrated systems with DICOM-native interfaces and provenance tracking.</p>","PeriodicalId":19269,"journal":{"name":"Neurospine","volume":"23 2","pages":"293-313"},"PeriodicalIF":5.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13152699/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147841020","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}