Are large language models valid tools for patient information on lumbar disc herniation? The spine surgeons' perspective.

Introduction: Generative AI is revolutionizing patient education in healthcare, particularly through chatbots that offer personalized, clear medical information. Reliability and accuracy are vital in AI-driven patient education. Research question: How effective are Large Language Models (LLM), such as ChatGPT and Google Bard, in delivering accurate and understandable patient education on lumbar disc herniation? Material and methods: Ten Frequently Asked Questions about lumbar disc herniation were selected from 133 questions and were submitted to three LLMs. Six experienced spine surgeons rated the responses on a scale from "excellent" to "unsatisfactory," and evaluated the answers for exhaustiveness, clarity, empathy, and length. Statistical analysis involved Fleiss Kappa, Chi-square, and Friedman tests. Results: Out of the responses, 27.2% were excellent, 43.9% satisfactory with minimal clarification, 18.3% satisfactory with moderate clarification, and 10.6% unsatisfactory. There were no significant differences in overall ratings among the LLMs (p = 0.90); however, inter-rater reliability was not achieved, and large differences among raters were detected in the distribution of answer frequencies. Overall, ratings varied among the 10 answers (p = 0.043). The average ratings for exhaustiveness, clarity, empathy, and length were above 3.5/5. Discussion and conclusion: LLMs show potential in patient education for lumbar spine surgery, with generally positive feedback from evaluators. The new EU AI Act, enforcing strict regulation on AI systems, highlights the need for rigorous oversight in medical contexts. In the current study, the variability in evaluations and occasional inaccuracies underline the need for continuous improvement. Future research should involve more advanced models to enhance patient-physician communication.

A decade of experience in over 300 surgically treated spine patients with long-term oral anticoagulation: a propensity score matched cohort study.

PURPOSE: The aim of this study was to investigate the risks and outcomes of patients with long-term oral anticoagulation (OAC) undergoing spine surgery. METHODS: All patients on long-term OAC who underwent spine surgery between 01/2005 and 06/2015 were included. Data were prospectively collected within our in-house Spine Surgery registry and retrospectively supplemented with patient chart and administrative database information. A 1:1 propensity score-matched group of patients without OAC from the same time interval served as control. Primary outcomes were post-operative bleeding, wound complications and thromboembolic events up to 90 days post-surgery. Secondary outcomes included intraoperative blood loss, length of hospital stay, death and 3-month post-operative patient-rated outcomes. RESULTS: In comparison with the control group, patients with OAC (n = 332) had a 3.4-fold (95%CI 1.3-9.0) higher risk for post-operative bleeding, whereas the risks for wound complications and thromboembolic events were comparable between groups. The higher bleeding risk was driven by a higher rate of extraspinal haematomas (3.3% vs. 0.6%; p = 0.001), while there was no difference in epidural haematomas and haematoma evacuations. Risk factors for adverse events among patients with OAC were mechanical heart valves, posterior neck surgery, blood loss > 1000 mL, age, female sex, BMI > 30 kg/m2 and post-operative PTT levels. At 3-month follow-up, most patients reported favourable outcomes with no difference between groups. CONCLUSION: Although OAC patients have a higher risk for complications after spine surgery, the risk for major events is low and patients benefit similarly from surgery.

Cross-sectional area and fat infiltration of the lumbar spine muscles in patients with back disorders: a deep learning-based big data analysis.

PURPOSE: Validated deep learning models represent a valuable option to perform large-scale research studies aiming to evaluate muscle quality and quantity of paravertebral lumbar muscles at the population level. This study aimed to assess lumbar spine muscle cross-sectional area (CSA) and fat infiltration (FI) in a large cohort of subjects with back disorders through a validated deep learning model. METHODS: T2 axial MRI images of 4434 patients (n = 2609 females, n = 1825 males; mean age: 56.7 ± 16.8) with back disorders, such as fracture, spine surgery or herniation, were retrospectively collected from a clinical database and automatically segmented. CSA, expressed as the ratio between total muscle area (TMA) and the vertebral body area (VBA), and FI, in percentages, of psoas major, quadratus lumborum, erector spinae, and multifidus were analyzed as primary outcomes. RESULTS: Male subjects had significantly higher CSA (6.8 ± 1.7 vs. 5.9 ± 1.5 TMA/VBA; p < 0.001) and lower FI (21.9 ± 8.3% vs. 15.0 ± 7.3%; p < 0.001) than females. Multifidus had more FI (27.2 ± 10.6%; p < 0.001) than erector spinae (22.2 ± 9.7%), quadratus lumborum (17.5 ± 7.0%) and psoas (13.7 ± 5.8%) whereas CSA was higher in erector spinae than other lumbar muscles. A high positive correlation between age and total FI was detected (rs = 0.73; p < 0.001) whereas a negligible negative correlation between total CSA and age was observed (rs = - 0.24; p < 0.001). Subjects with fractures had lower CSA and higher FI compared to those with herniations, surgery and with no clear pathological conditions. CONCLUSION: CSA and FI values of paravertebral muscles vary a lot in accordance with subjects' sex, age and clinical conditions. Given also the large inter-muscle differences in CSA and FI, the choice of muscles needs to be considered with attention by spine surgeons or physiotherapists when investigating changes in lumbar muscle morphology in clinical practice.

Automatic classification of the vertebral endplate lesions in magnetic resonance imaging by deep learning model.

Introduction: A novel classification scheme for endplate lesions, based on T2-weighted images from magnetic resonance imaging (MRI) scan, has been recently introduced and validated. The scheme categorizes intervertebral spaces as "normal," "wavy/irregular," "notched," and "Schmorl's node." These lesions have been associated with spinal pathologies, including disc degeneration and low back pain. The exploitation of an automatic tool for the detection of the lesions would facilitate clinical practice by reducing the workload and the diagnosis time. The present work exploits a deep learning application based on convolutional neural networks to automatically classify the type of lesion. Methods: T2-weighted MRI scans of the sagittal lumbosacral spine of consecutive patients were retrospectively collected. The middle slice of each scan was manually processed to identify the intervertebral spaces from L1L2 to L5S1, and the corresponding lesion type was labeled. A total of 1,559 gradable discs were obtained, with the following types of distribution: "normal" (567 discs), "wavy/irregular" (485), "notched" (362), and "Schmorl's node" (145). The dataset was divided randomly into a training set and a validation set while preserving the original distribution of lesion types in each set. A pretrained network for image classification was utilized, and fine-tuning was performed using the training set. The retrained net was then applied to the validation set to evaluate the overall accuracy and accuracy for each specific lesion type. Results: The overall rate of accuracy was found equal to 88%. The accuracy for the specific lesion type was found as follows: 91% (normal), 82% (wavy/irregular), 93% (notched), and 83% (Schmorl's node). Discussion: The results indicate that the deep learning approach achieved high accuracy for both overall classification and individual lesion types. In clinical applications, this implementation could be employed as part of an automatic detection tool for pathological conditions characterized by the presence of endplate lesions, such as spinal osteochondrosis.

The lumbar adjacent-level syndrome: analysis of clinical, radiological, and surgical parameters in a large single-center series.

OBJECTIVE: The development of specific clinical and neurological symptoms and radiological degeneration affecting the segment adjacent to a spinal arthrodesis comprise the framework of adjacent-level syndrome. Through the analysis of a large surgical series, this study aimed to identify possible demographic, clinical, radiological, and surgical risk factors involved in the development of adjacent-level syndrome. METHODS: A single-center retrospective analysis of adult patients undergoing lumbar fusion procedures between January 2014 and December 2018 was performed. Clinical, demographic, radiological, and surgical data were collected. Patients who underwent surgery for adjacent-segment disease (ASD) were classified as the ASD group. All patients were evaluated 1 month after the surgical procedure clinically and radiologically (with lumbar radiographs) and 3 months afterward with CT scans. The last follow-up was performed by telephone interview. The median follow-up for patients included in the analysis was 67.2 months (range 39-98 months). RESULTS: A total of 902 patients were included in this study. Forty-nine (5.4%) patients required reoperation for ASD. A significantly higher BMI value was observed in the ASD group (p < 0.001). Microdiscectomy and microdecompression procedures performed at the upper or lower level of an arthrodesis without fusion extension have a statistically significant impact on the development of ASD (p = 0.001). Postoperative pelvic tilt in the ASD group was higher than in the non-ASD group. Numeric rating scale, Core Outcome Measures Index, and Oswestry Disability Index scores at the last follow-up were significantly higher in patients in the ASD group and in patients younger than 65 years. CONCLUSIONS: Identifying risk factors for the development of adjacent-level syndrome allows the implementation of a prevention strategy in patients undergoing lumbar arthrodesis surgery. Age older than 65 years, high BMI, preexisting disc degeneration at the adjacent level, and high postoperative pelvic tilt are the most relevant factors. In addition, patients older than 65 years achieve higher levels of clinical improvement and postsurgical satisfaction than do younger patients.

Stability and Instrumentation Stresses Among Sacropelvic Fixation Techniques With Novel Porous Fusion/Fixation Implants: A Finite Element Study.

BACKGROUND: Sacropelvic fixation is frequently combined with thoracolumbar instrumentation for correcting spinal deformities. This study aimed to characterize sacropelvic fixation techniques using novel porous fusion/fixation implants (PFFI). METHODS: Three T10-pelvis finite element models were created: (1) pedicle screws and rods in T10-S1, PFFI bilaterally in S2 alar-iliac (S2AI) trajectory; (2) fixation in T10-S1, PFFI bilaterally in S2AI trajectory, triangular implants bilaterally above the PFFI in a sacro-alar-iliac trajectory (PFFI-IFSAI); and (3) fixation in T10-S1, PFFI bilaterally in S2AI trajectory, PFFI in sacro-alar-iliac trajectory stacked cephalad to those in S2AI position (2-PFFI). Models were loaded with pure moments of 7.5 Nm in flexion-extension, lateral bending, and axial rotation. Outputs were compared against 2 baseline models: (1) pedicle screws and rods in T10-S1 (PED), and (2) pedicle screws and rods in T10-S1, and S2AI screws. RESULTS: PFFI and S2AI resulted in similar L5-S1 motion; adding another PFFI per side (2-PFFI) further reduced this motion. Sacroiliac joint (SIJ) motion was also similar between PFFI and S2AI; PFFI-IFSAI and 2-PFFI demonstrated a further reduction in SIJ motion. Additionally, PFFI reduced max stresses on S1 pedicle screws and on implants in the S2AI position. CONCLUSION: The study shows that supplementing a long construct with PFFI increases the stability of the L5-S1 and SIJ and reduces stresses on the S1 pedicle screws and implants in the S2AI position. CLINICAL RELEVANCE: The findings suggest a reduced risk of pseudarthrosis at L5-S1 and screw breakage. Clinical studies may be performed to demonstrate applicability to patient outcomes. LEVEL OF EVIDENCE: Not applicable (basic science study).

Proximal Junction Failure in Spine Surgery: Integrating Geometrical and Biomechanical Global Descriptors Improves GAP Score-Based Assessment.

STUDY DESIGN: Retrospective observational study. OBJECTIVE: Biomechanical and geometrical descriptors are used to improve global alignment and proportion (GAP) prediction accuracy to detect proximal junctional failure (PJF). SUMMARY OF BACKGROUND DATA: PJF is probably the most important complication after sagittal imbalance surgery. The GAP score has been introduced as an effective predictor for PJF, but it fails in certain situations. In this study, 112 patient records were gathered (57 PJF; 55 controls) with biomechanical and geometrical descriptors measured to stratify control and failure cases. PATIENTS AND METHODS: Biplanar EOS radiographs were used to build 3-dimensional full-spine models and determine spinopelvic sagittal parameters. The bending moment (BM) was calculated as the upper body mass times, the effective distance to the body center of mass at the adjacent upper instrumented vertebra +1. Other geometrical descriptors such as full balance index (FBI), spino-sacral angle (SSA), C7 plumb line/sacrofemoral distance ratio (C7/SFD ratio), T1-pelvic angle (TPA), and cervical inclination angle (CIA) were also evaluated. The respective abilities of the GAP, FBI, SSA, C7/SFD, TPA, CIA, body weight, body mass index, and BM to discriminate PJF cases were analyzed through receiver operating characteristic curves and corresponding areas under the curve (AUC). RESULTS: GAP (AUC = 0.8816) and FBI (AUC = 0.8933) were able to discriminate PJF cases but the highest discrimination power (AUC = 0.9371) was achieved with BM at upper instrumented vertebra + 1. Parameter cutoff analyses provided quantitative thresholds to characterize the control and failure groups and led to improved PJF discrimination, with GAP and BM being the most important contributors. SSA (AUC = 0.2857), C7/SFD (AUC = 0.3143), TPA (AUC = 0.5714), CIA (AUC = 0.4571), body weight (AUC = 0.6319), and body mass index (AUC = 0.7716) did not adequately predict PJF. CONCLUSION: BM reflects the quantitative biomechanical effect of external loads and can improve GAP accuracy. Sagittal alignments and mechanical integrated scores could be used to better prognosticate the risk of PJF.

Endplate abnormalities, Modic changes and their relationship to alignment parameters and surgical outcomes in the cervical spine.

Modic changes (MC) and endplate abnormalities (EA) have been shown to impact preoperative symptoms and outcomes following spinal surgery. However, little is known about how these phenotypes impact cervical alignment. This study aimed to evaluate the impact that these phenotypes have on preoperative, postoperative, and changes in cervical alignment in patients undergoing anterior cervical discectomy and fusion (ACDF). We performed a retrospective study of prospectively collected data of ACDF patients at a single institution. Preoperative magnetic resonance imagings (MRIs) were used to assess for the MC and EA. Patients were subdivided into four groups: MC-only, EA-only, the combined Modic-Endplate-Complex (MEC), and patients without either phenotype. Pre and postoperative MRIs were used to assess alignment parameters. Associations with imaging phenotypes and alignment parameters were assessed, and statistical significance was set at p < 0.5. A total of 512 patients were included, with 84 MC-only patients, 166 EA-only patients, and 71 patients with MEC. Preoperative MC (p = 0.031) and the MEC (p = 0.039) had significantly lower preoperative T1 slope compared to controls. Lower preoperative T1 slope was a risk factor for MC (p = 0.020) and MEC (p = 0.029) and presence of MC (Type II) and the MEC (Type III) was predictive of lower preoperative T1 slope. There were no differences in postoperative alignment measures or patient reported outcome measures. MC and endplate pathologies such as the MEC appear to be associated with worse cervical alignment at baseline relative to patients without these phenotypes. Poor alignment may be an adaptive response to these degenerative findings or may be a risk factor for their development.

Association between sagittal alignment and loads at the adjacent segment in the fused spine: a combined clinical and musculoskeletal modeling study of 205 patients with adult spinal deformity.

PURPOSE: Sagittal malalignment is a risk factor for mechanical complications after surgery for adult spinal deformity (ASD). Spinal loads, modulated by sagittal alignment, may explain this relationship. The aims of this study were to investigate the relationships between: (1) postoperative changes in loads at the proximal segment and realignment, and (2) absolute postoperative loads and postoperative alignment measures. METHODS: A previously validated musculoskeletal model of the whole spine was applied to study a clinical sample of 205 patients with ASD. Based on clinical and radiographic data, pre-and postoperative patient-specific alignments were simulated to predict loads at the proximal segment adjacent to the spinal fusion. RESULTS: Weak-to-moderate associations were found between pre-to-postop changes in lumbar lordosis, LL (r = - 0.23, r = - 0.43; p < 0.001), global tilt, GT (r = 0.26, r = 0.38; p < 0.001) and the Global Alignment and Proportion score, GAP (r = 0.26, r = 0.37; p < 0.001), and changes in compressive and shear forces at the proximal segment. GAP score parameters, thoracic kyphosis measurements and the slope of upper instrumented vertebra were associated with changes in shear. In patients with T10-pelvis fusion, moderate-to-strong associations were found between postoperative sagittal alignment measures and compressive and shear loads, with GT showing the strongest correlations (r = 0.75, r = 0.73, p < 0.001). CONCLUSIONS: Spinal loads were estimated for patient-specific full spinal alignment profiles in a large cohort of patients with ASD pre-and postoperatively. Loads on the proximal segments were greater in association with sagittal malalignment and malorientation of proximal vertebra. Future work should explore whether they provide a causative mechanism explaining the associated risk of proximal junction complications.

Effect of Sacropelvic Hardware on Axis and Center of Rotation of the Sacroiliac Joint: A Finite Element Study.

BACKGROUND: The sacroiliac joint (SIJ) transfers the load of the upper body to the lower extremities while allowing a variable physiological movement among individuals. The axis of rotation (AoR) and center of rotation (CoR) of the SIJ can be evaluated to analyze the stability of the SIJ, including when the sacrum is fixed. The purpose of this study was to determine how load intensity affects the SIJ for the intact model and to characterize how sacropelvic fixation performed with different techniques affects this joint. METHODS: Five T10-pelvis models were used: (1) intact model; (2) pedicle screws and rods in T10-S1; (3)pedicle screws and rods in T10-S1, and bilateral S2 alar-iliac screws (S2AI); (4) pedicle screws and rods in T10-S1, bilateral S2AI screws, and triangular implants inserted bilaterally in a sacral alar-iliac trajectory ; and (5) pedicle screws and rods in T10-S1, bilateral S2AI screws, and 2 bilateral triangular implants inserted in a lateral trajectory. Outputs of these models under flexion-extension were compared: AoR and CoR of the SIJ at incremental steps from 0 to 7.5 Nm for the intact model and AoR and CoR of the SIJ for the instrumented models at 7.5 Nm. RESULTS: The intact model was validated against an in vivo study by comparing range of motion and displacement of the sacrum. Increasing the load intensity for the intact model led to an increase of the rotation of the sacrum but did not change the CoR. Comparison among the instrumented models showed that sacropelvic fixation techniques reduced the rotation of the sacrum and stabilized the SIJ, in particular with triangular implants. CONCLUSION: The study outcomes suggest that increasing load intensity increases the rotation of the sacrum but does not influence the CoR, and use of sacropelvic fixation increases the stability of the SIJ, especially when triangular implants are employed. CLINICAL RELEVANCE: The choice of the instrumentation strategy for sacropelvic fixation affects the stability of the construct in terms of both range of motion and axes of rotation, with direct consequences on the risk of failure and mobilization. Clinical studies should be performed to confirm these biomechanical findings.

Perioperative adverse events in adult and pediatric spine surgery: A prospective cohort analysis of 364 consecutive patients.

Introduction: A precise knowledge of the possible Adverse Events (AEs) related to spinal surgical procedures is crucial in clinical practice. Research Question: Purposes of this study are: to determine the prevalence and severity of perioperative AEs associated with pediatric and adult spine surgery in a high volume center; to estimate the impact of perioperative AEs on length of hospital stay (LOS). Material and Methods: This is a prospective, observational, monocenter study, including 346 consecutive patients (294 adults and 52 pediatrics). The SAVES-V2 questionnaire was used to record AEs. The form was updated by the medical staff every time an adverse event was recorded during hospitalization. Results: 21,2% of pediatric patients and 20,7% of adults had at least 1 perioperative AEs. In adults, dural tear (3.1%) and neuropathic pain (4,8%), were the most frequent intraoperative and postoperative AE, respectively. In pediatric patients, neurologic deterioration was the most frequent postoperative AE. A diagnosis of deformity (p=0.01), an ASA grade equal or superior to 3 (p=0.023) and the procedure 'Posterior Spinal Fusion' (p=0.001) were associated with a higher frequency of AEs. AEs required prolonged LOS in 40 cases, 7 (70%) pediatric patients and 33 (65%) adults. Discussion and Conclusion: The overall prevalence of AEs is 20.8%, and, although the distribution is almost equal between adult and pediatric patients, their severity is related to age, being higher in pediatric patients. Deformities, deformity correction, revision surgery and AP surgery are the most impactful factors. AEs seriously affect hospitalization, with prolonged LOS (mean 6 days).

Artificial intelligence in spine care: current applications and future utility.

PURPOSE: The field of artificial intelligence is ever growing and the applications of machine learning in spine care are continuously advancing. Given the advent of the intelligence-based spine care model, understanding the evolution of computation as it applies to diagnosis, treatment, and adverse event prediction is of great importance. Therefore, the current review sought to synthesize findings from the literature at the interface of artificial intelligence and spine research. METHODS: A narrative review was performed based on the literature of three databases (MEDLINE, CINAHL, and Scopus) from January 2015 to March 2021 that examined historical and recent advancements in the understanding of artificial intelligence and machine learning in spine research. Studies were appraised for their role in, or description of, advancements within image recognition and predictive modeling for spinal research. Only English articles that fulfilled inclusion criteria were ultimately incorporated in this review. RESULTS: This review briefly summarizes the history and applications of artificial intelligence and machine learning in spine. Three basic machine learning training paradigms: supervised learning, unsupervised learning, and reinforced learning are also discussed. Artificial intelligence and machine learning have been utilized in almost every facet of spine ranging from localization and segmentation techniques in spinal imaging to pathology specific algorithms which include but not limited to; preoperative risk assessment of postoperative complications, screening algorithms for patients at risk of osteoporosis and clustering analysis to identify subgroups within adolescent idiopathic scoliosis. The future of artificial intelligence and machine learning in spine surgery is also discussed with focusing on novel algorithms, data collection techniques and increased utilization of automated systems. CONCLUSION: Improvements to modern-day computing and accessibility to various imaging modalities allow for innovative discoveries that may arise, for example, from management. Given the imminent future of AI in spine surgery, it is of great importance that practitioners continue to inform themselves regarding AI, its goals, use, and progression. In the future, it will be critical for the spine specialist to be able to discern the utility of novel AI research, particularly as it continues to pervade facets of everyday spine surgery.

The Influence of Baseline Clinical Status and Surgical Strategy on Early Good to Excellent Result in Spinal Lumbar Arthrodesis: A Machine Learning Approach.

The study aims to create a preoperative model from baseline demographic and health-related quality of life scores (HRQOL) to predict a good to excellent early clinical outcome using a machine learning (ML) approach. A single spine surgery center retrospective review of prospectively collected data from January 2016 to December 2020 from the institutional registry (SpineREG) was performed. The inclusion criteria were age ≥ 18 years, both sexes, lumbar arthrodesis procedure, a complete follow up assessment (Oswestry Disability Index-ODI, SF-36 and COMI back) and the capability to read and understand the Italian language. A delta of improvement of the ODI higher than 12.7/100 was considered a "good early outcome". A combined target model of ODI (Δ ≥ 12.7/100), SF-36 PCS (Δ ≥ 6/100) and COMI back (Δ ≥ 2.2/10) was considered an "excellent early outcome". The performance of the ML models was evaluated in terms of sensitivity, i.e., True Positive Rate (TPR), specificity, i.e., True Negative Rate (TNR), accuracy and area under the receiver operating characteristic curve (AUC ROC). A total of 1243 patients were included in this study. The model for predicting ODI at 6 months' follow up showed a good balance between sensitivity (74.3%) and specificity (79.4%), while providing a good accuracy (75.8%) with ROC AUC = 0.842. The combined target model showed a sensitivity of 74.2% and specificity of 71.8%, with an accuracy of 72.8%, and an ROC AUC = 0.808. The results of our study suggest that a machine learning approach showed high performance in predicting early good to excellent clinical results.

Accounting for Biomechanical Measures from Musculoskeletal Simulation of Upright Posture Does Not Enhance the Prediction of Curve Progression in Adolescent Idiopathic Scoliosis.

A major clinical challenge in adolescent idiopathic scoliosis (AIS) is the difficulty of predicting curve progression at initial presentation. The early detection of progressive curves can offer the opportunity to better target effective non-operative treatments, reducing the need for surgery and the risks of related complications. Predictive models for the detection of scoliosis progression in subjects before growth spurt have been developed. These models accounted for geometrical parameters of the global spine and local descriptors of the scoliotic curve, but neglected contributions from biomechanical measurements such as trunk muscle activation and intervertebral loading, which could provide advantageous information. The present study exploits a musculoskeletal model of the thoracolumbar spine, developed in AnyBody software and adapted and validated for the subject-specific characterization of mild scoliosis. A dataset of 100 AIS subjects with mild scoliosis and in pre-pubertal age at first examination, and recognized as stable (60) or progressive (40) after at least 6-months follow-up period was exploited. Anthropometrical data and geometrical parameters of the spine at first examination, as well as biomechanical parameters from musculoskeletal simulation replicating relaxed upright posture were accounted for as predictors of the scoliosis progression. Predicted height and weight were used for model scaling because not available in the original dataset. Robust procedure for obtaining such parameters from radiographic images was developed by exploiting a comparable dataset with real values. Six predictive modelling approaches based on different algorithms for the binary classification of stable and progressive cases were compared. The best fitting approaches were exploited to evaluate the effect of accounting for the biomechanical parameters on the prediction of scoliosis progression. The performance of two sets of predictors was compared: accounting for anthropometrical and geometrical parameters only; considering in addition the biomechanical ones. Median accuracy of the best fitting algorithms ranged from 0.76 to 0.78. No differences were found in the classification performance by including or neglecting the biomechanical parameters. Median sensitivity was 0.75, and that of specificity ranged from 0.75 to 0.83. In conclusion, accounting for biomechanical measures did not enhance the prediction of curve progression, thus not supporting a potential clinical application at this stage.

Radiomic Machine Learning Classifiers in Spine Bone Tumors: A Multi-Software, Multi-Scanner Study.

PURPOSE: Spinal lesion differential diagnosis remains challenging even in MRI. Radiomics and machine learning (ML) have proven useful even in absence of a standardized data mining pipeline. We aimed to assess ML diagnostic performance in spinal lesion differential diagnosis, employing radiomic data extracted by different software. METHODS: Patients undergoing MRI for a vertebral lesion were retrospectively analyzed (n = 146, 67 males, 79 females; mean age 63 ±â€¯16 years, range 8-89 years) and constituted the train (n = 100) and internal test cohorts (n = 46). Part of the latter had additional prior exams which constituted a multi-scanner, external test cohort (n = 35). Lesions were labeled as benign or malignant (2-label classification), and benign, primary malignant or metastases (3-label classification) for classification analyses. Features extracted via 3D Slicer heterogeneityCAD module (hCAD) and PyRadiomics were independently used to compare different combinations of feature selection methods and ML classifiers (n = 19). RESULTS: In total, 90 and 1548 features were extracted by hCAD and PyRadiomics, respectively. The best feature selection method-ML algorithm combination was selected by 10 iterations of 10-fold cross-validation in the training data. For the 2-label classification ML obtained 94% accuracy in the internal test cohort, using hCAD data, and 86% in the external one. For the 3-label classification, PyRadiomics data allowed for 80% and 69% accuracy in the internal and external test sets, respectively. CONCLUSIONS: MRI radiomics combined with ML may be useful in spinal lesion assessment. More robust pre-processing led to better consistency despite scanner and protocol heterogeneity.

Load-sharing biomechanics of lumbar fixation and fusion with pedicle subtraction osteotomy.

Pedicle subtraction osteotomy (PSO) is an invasive surgical technique allowing the restoration of a well-balanced sagittal profile, however, the risks of pseudarthrosis and instrumentation breakage are still high. Literature studied primary stability and posterior instrumentation loads, neglecting the load shared by the anterior column, which is fundamental to promote fusion early after surgery. The study aimed at quantifying the load-sharing occurring after PSO procedure across the ventral spinal structures and the posterior instrumentation, as affected by simple bilateral fixation alone, with interbody cages adjacent to PSO level and supplementary accessory rods. Lumbar spine segments were loaded in vitro under flexion-extension, lateral bending, and torsion using an established spine tester. Digital image correlation (DIC) and strain-gauge (SG) analyses measured, respectively, the full-field strain distribution on the ventral surface of the spine and the local strain on posterior primary rods. Ventral strains considerably decreased following PSO and instrumentation, confirming the effectiveness of posterior load-sharing. Supplemental accessory rods considerably reduced the posterior rod strains only with interbody cages, but the ventral strains were unaffected: this indicates that the load transfer across the osteotomy could be promoted, thus explaining the higher fusion rate with decreased rod fracture risk reported in clinical literature.

Cervical spine MRI phenotypes and prediction of pain, disability and adjacent segment degeneration/disease after ACDF.

Degenerative spine imaging findings have been extensively studied in the lumbar region and are associated with pain and adverse clinical outcomes after surgery. However, few studies have investigated the significance of these imaging "phenotypes" in the cervical spine. Patients with degenerative cervical spine pathology undergoing anterior cervical discectomy and fusion (ACDF) from 2008 to 2015 were retrospectively and prospectively assessed using preoperative MRI for disc degeneration, narrowing, and displacement, high-intensity zones, endplate abnormalities, Modic changes, and osteophyte formation from C2-T1. Points were assigned for these phenotypes to generate a novel Cervical Phenotype Index (CPI). Demographics were evaluated for association with phenotypes and the CPI using forward stepwise regression. Bootstrap sampling and multiple imputations assessed phenotypes and the CPI in association with patient-reported outcomes (Neck Disability Index [NDI], Visual Analog Scale [VAS]-neck, VAS-arm) and adjacent segment degeneration (ASDeg) and disease (ASDz). Of 861 patients, disc displacement was the most common (99.7%), followed by osteophytes (92.0%) and endplate abnormalities (57.3%). Most findings were associated with age and were identified at similar cervical vertebral levels; at C5-C7. Imaging phenotypes demonstrated both increased and decreased associations with adverse patient-reported outcomes and ASDeg/Dz. However, the CPI consistently predicted worse NDI (P = .012), VAS-neck (P = .007), and VAS-arm (P = .013) scores, in addition to higher odds of ASDeg (P = .002) and ASDz (P = .004). The CPI was significantly predictive of postoperative symptoms of pain/disability and ASDeg/Dz after ACDF, suggesting that the totality of degenerative findings may be more clinically relevant than individual phenotypes and that this tool may help prognosticate outcomes after surgery.

Cervical Spine Endplate Abnormalities and Association With Pain, Disability, and Adjacent Segment Degeneration After Anterior Cervical Discectomy and Fusion.

STUDY DESIGN: A retrospective study with prospectively-collected data. OBJECTIVE: To determine how type, location, and size of endplate lesions on magnetic resonance imaging (MRI) may be associated with symptoms and clinical outcomes after anterior cervical discectomy and fusion (ACDF). SUMMARY OF BACKGROUND DATA: Structural endplate abnormalities are important, yet understudied, phenomena in the cervical spine. ACDF is a common surgical treatment for degenerative disc disease; however, adjacent segment degeneration/disease (ASD) may develop. METHODS: Assessed the imaging, symptoms and clinical outcomes of 861 patients who underwent ACDF at a single center. MRI and plain radiographs of the cervical spine were evaluated. Endplate abnormalities on MRI were identified and stratified by type (atypical, typical), location, relation to operative levels, presence at the adjacent level, and size. These strata were assessed for association with presenting symptoms, patient-reported, and postoperative outcomes. RESULTS: Of 861 patients (mean follow-up: 17.4 months), 57.3% had evidence of endplate abnormalities, 39.0% had typical abnormalities, while 18.2% had atypical abnormalities. Patients with any endplate abnormality had greater odds of myelopathy irrespective of location or size, while sensory deficits were associated with atypical lesions (P = 0.016). Typical and atypical abnormalities demonstrated differences in patient-reported outcomes based on location relative to the fused segment. Typical variants were not associated with adverse surgical outcomes, while atypical lesions were associated with ASD (irrespective of size/location; P = 0.004) and reoperations, when a large abnormality was present at the proximal adjacent level (P = 0.025). CONCLUSION: This is the first study to examine endplate abnormalities on MRI of the cervical spine, demonstrating distinct risk profiles for symptoms, patient-reported, and surgical outcomes after ACDF. Patients with typical lesions reported worsening postoperative pain/disability, while those with atypical abnormalities experienced greater rates of ASD and reoperation. This highlights the relevance of a degenerative spine phenotypic assessment, and suggests endplate abnormalities may prognosticate clinical outcomes after surgery. LEVEL OF EVIDENCE: 3.

Biomechanical in vitro comparison between anterior column realignment and pedicle subtraction osteotomy for severe sagittal imbalance correction.

PURPOSE: To investigate the biomechanical effects of anterior column realignment (ACR) and pedicle subtraction osteotomy (PSO) on local lordosis correction, primary stability and rod strains. METHODS: Seven cadaveric spine segments (T12-S1) underwent ACR at L1-L2. A stand-alone hyperlordotic cage was initially tested and then supplemented with posterior bilateral fixation. The same specimens already underwent a PSO at L4 stabilized by two rods, a supplemental central rod (three rods) and accessory rods (four rods) with and without adjacent interbody cages (La Barbera in Eur Spine J 27(9):2357-2366, 2018). In vitro flexibility tests were performed under pure moments in flexion/extension (FE), lateral bending (LB) and axial rotation (AR) to determine the range of motion (RoM), while measuring the rod strains with strain gauge rosettes. RESULTS: Local lordosis correction with ACR (24.7° ± 3.7°) and PSO (25.1° ± 3.9°) was similar. Bilateral fixation significantly reduced the RoM (FE: 31%, LB: 2%, AR: 18%), providing a stability consistent with PSO constructs (p > 0.05); however, it demonstrates significantly higher rod strains compared to PSO constructs with lateral accessory rods and interbody cages in FE and AR (p < 0.05), while being comparable in FE or slightly higher in AR compared to PSO constructs with two and three rods. CONCLUSION: Bilateral posterior fixation is highly recommended following ACR to provide adequate primary stability. However, primary rod strains in ACR were found comparable or higher than weak PSO construct associated with frequent rod failure; therefore, caution is recommended. These slides can be retrieved under Electronic Supplementary Material.