Preoperative paraspinal neck muscle characteristics predict early onset adjacent segment degeneration in anterior cervical fusion patients: A machine-learning modeling analysis

Morphological Changes of Deep Extensor Neck Muscles in Relation to the Maximum Level of Cord Compression and Canal Compromise in Patients With Degenerative Cervical Myelopathy

STUDY DESIGN

Cross-sectional study.

OBJECTIVES

To examine the relationship between morphological changes of the deep extensor neck muscles in patients with degenerative cervical myelopathy (DCM) and the level of maximum spinal cord compression (MSCC) and canal compromise (MCC). A secondary objective was to examine the relationship between muscle morphological changes with neck pain and functional scores related to neck pain and interference.

METHODS

A total of 171 patients with DCM were included. Total cross-sectional area (CSA), functional CSA (fat free area, FCSA), ratio of FCSA/CSA (fatty infiltration) and asymmetry of the multifidus (MF) and semispinalis cervicis (SCer) together, and cervical muscle as a group (eg, MF, SCer, semispinalis capitis, splenius capitis) were obtained from T2-weighted axial MR images at mid-disc, at the level of maximum cord compression and the level below. The relationship between the muscle parameters of interest, MSCC, MCC and functional scores including the Neck Disability Index (NDI) was assessed using multivariate linear regression models, adjusting for age, body mass index and sex.

RESULTS

Greater MF + Scer fatty infiltration was associated with greater MCC (P = .032) and MSCC (P = .049) at the same level. Greater asymmetry in MF + SCer CSA was also associated with greater MCC (P = .006). Similarly, greater asymmetry in FCSA and FCSA/CSA of the entire extensor muscle was associated with greater MCC (P = .011, P = .013). There was a negative association between asymmetry in FCSA MF + SCer, FCSA/CSA MF + SCer and FCSA/CSA group muscles with NDI score at the level below.

CONCLUSION

Greater MCC is associated with increased fatty infiltration and greater asymmetry of the deep cervical muscles in patients with DCM. A negative association between muscle asymmetry and NDI scores was also observed which has implications for clinical prediction around axial neck pain.

A comparison of traditional and net structured intersomatic cages in the lombosacral region: A biomechanical analysis for enhancing discopathy treatment

The vertebral column represents an essential element for support, mobility, and the protection of the central nervous system. Various pathologies can compromise these vital functions, leading to pain and a decrease in the quality of life. Within the scope of this study, a novel redesign of the Intersomatic Cage, traditionally used in the presence of discopathy, was proposed. The adoption of additive manufacturing technology allowed for the creation of highly complex geometries, focusing on the lumbosacral tract, particularly on the L4-L5 and L5-S1 intervertebral discs. In addition to the tensile analysis carried out using Finite Element Analysis (FEA) in static simulations, a parallel study on the range of motion (ROM) of the aforementioned vertebral pairs was conducted. The ROM represents the relative movement range between various vertebral pairs. The introduction of the intersomatic cage between the vertebrae, replacing the pulpy nucleus of the intervertebral disc, could influence the ROM, thus having significant clinical implications. For the analysis, the ligaments were modelled using a 1D approach. Their constraint reaction and deformability upon load application were analysed to better understand the potential biomechanical implications arising from the adoption of the cages. During the FEA simulations, two types of cages were analysed: LLIF for L4-L5 and ALIF for L5-S1, subjecting them to four different loading conditions. The results indicate that the stresses exhibited by cages with a NET structure are generally lower compared to those of traditional cages. This stress reduction in cages with NET structure suggests a more optimal load distribution, but it is essential to assess potential repercussions on the surrounding bone structure.

Radiographic Risk Factors for Adjacent Segment Disease Following Anterior Cervical Discectomy and Fusion (ACDF): A Systematic Review and Meta-Analysis

STUDY DESIGN

Systematic review and meta-analysis.

OBJECTIVES

To assess the radiographic risk factors for adjacent segment disease (ASD) following anterior cervical discectomy and fusion (ACDF) for degenerative cervical spine pathologies.

METHODS

PubMed, Embase and the Cochrane Library databases were searched up to December 2023. The primary inclusion criteria were degenerative spinal conditions treated with ACDF, comparing radiological parameters in patients with and without postoperative ASD. The radiographic parameters included intervertebral disc height, cervical sagittal alignment, sagittal segmental alignment, range of motion, segmental height, T1 slope, sagittal vertical axis (SVA), thoracic inlet angle (TIA), and plate to disc distance (PPD). Risk of bias was assessed for all studies. The Cochrane Review Manager was utilized to perform the meta-analysis.

RESULTS

From 7044 articles, 13 retrospective studies were included in the final analysis. Three studies had "not serious" bias and the other 10 studies had serious or very serious bias. The total number of patients in the included studies was 1799 patients. Five studies included single-level ACDF, 2 studies included multi-level ACDF, and 6 studies included single or multi-level ACDF. On meta-analysis, the significant risk factors associated with ASD development were reduced postoperative cervical lordosis (mean difference [MD] = 3.35°, P = .002), reduced last-follow-up cervical lordosis (MD = -3.02°, P = .0003), increased preoperative to postoperative cervical sagittal alignment change (MD = -3.68°, P = .03), and the presence of developmental cervical canal stenosis (Odds ratio [OR] = 4.17, P < .001).

CONCLUSIONS

Decreased postoperative cervical lordosis, greater change in cervical sagittal alignment and developmental cervical canal stenosis were associated with an increased risk of ASD following ACDF.

Incidence of Adjacent Segment Degeneration and Its Associated Risk Factors Following Anterior Cervical Discectomy and Fusion: A Meta-Analysis

OBJECTIVE

This study aimed to investigate the incidence of adjacent segment degeneration (ASD) and its associated risk factors in adults after anterior cervical discectomy and fusion (ACDF) surgery.

METHODS

An exhaustive search across multiple databases was conducted, including Embase, PubMed, Cochrane Library, and the Web of Science, to identify pertinent studies. We collected such patient data as demographic variables (including age, gender, body mass index), cervical spondylosis type (such as radiculopathy and myelopathy), diabetes status, smoking and drinking history, and radiological risk factors (such as preoperative ASD status, developmental spinal stenosis, T1 slope, and postoperative less cervical lordosis). Incidence estimates were calculated based on relevant data. Risk factors were assessed using odds ratios and weighted mean differences with 95% confidence intervals (CIs).

RESULTS

Our analysis incorporated a total of 21 studies for incidence analysis. The overall incidence of CASD following ACDF was found to be 11% and radiographical ASD was 30%. Old age (weighted mean difference = 3.21; 95% CI: 0.06, 6.36; P = 0.05), preoperative ASD status (odds ratio = 2.65; 95% CI: 1.53, 4.60; P < 0.01), developmental spinal stenosis (odds ratio = 2.46; 95% CI: 1.61, 3.77; P < 0.01), and postoperative reduction in cervical lordosis were identified as significant risk factors for the occurrence of CASD.

CONCLUSIONS

The incidence of CASD following ACDF was 11%. Risk factors for CASD included old age, preoperative adjacent segment degeneration, developmental spinal stenosis, and postoperative reduction in cervical lordosis. These findings provide valuable insights for the assessment of adjacent segment disease risk after ACDF, aiding surgeons in diagnosis and treatment decisions.

Trends of Low Back Pain Research in Older and Working-Age Adults from 1993 to 2023: A Bibliometric Analysis

Although the number of publications focusing on low back pain in older adults (LBP-O) and working-age adults (LBP-W) has been growing for decades, comparative research trends in these two populations, which may help to guide future investigation, have not been rigorously explored. This analysis aimed to describe publication patterns and trends of research targeting LBP-O and LBP-W over the last three decades. Peer-reviewed LBP-O and LBP-W articles published between 1993 and 2023 were retrieved from the Web of Science, which provided the details of annual publication volume, and prominent journals/countries/institutions. The relationship between the annual publication volumes and years was analyzed by Spearman correlation analysis. The hot topics and emerging trends were analyzed by VOSviewer and CiteSpace, respectively. A total of 4217 LBP-O-related and 50,559 LBP-W-related documents were included. The annual publication volumes of LBP-O and LBP-W articles increased over the years (r=0.995 to 0.998, p<0.001). The United States had the highest number of prominent institutions publishing relevant articles. The most prolific journal for LBP-O (5.4%) and LBP-W-related (6.1%) papers is the journal "Spine". Cognitive behavioral therapy, intervertebral disc (IVD) degeneration, physiotherapy, physical activity, and walking were the recent hot topics and physical activity was an emerging trend in LBP-O, while surgery and IVD degeneration (also a hot topic) were emerging trends in LBP-W. This study highlights the paucity of LBP-O-related research in the past. The United States and the journal Spine stand out in LBP research. The research trend of physical activity in LBP-O is consistent with the recognized importance of physical activity for older adults in general, and for managing LBP-O in particular. Conversely, the emerging trends of surgery and intervertebral disc degeneration in LBP-W research highlight a focus on the biomedical model of LBP despite LBP being a biopsychosocial condition.

Cervical muscle morphometry and composition demonstrate prognostic value in degenerative cervical myelopathy outcomes

Objectives

This study aimed to examine whether preoperative cervical muscle size, composition, and asymmetry from magnetic resonance imaging (MRI) can predict post-operative outcomes in patients with degenerative cervical myelopathy (DCM).

Methods

A total of 171 patients with DCM were included. Relative total cross-sectional area (RCSA), functional CSA (fat-free area, FCSA), ratio of FCSA/CSA (fatty infiltration) and asymmetry of the multifidus (MF) and semispinalis cervicis (SCer) together (MF + SCer), and cervical muscle as a group (MF, SCer, semispinalis capitis, and splenius capitis) were obtained from T2-weighted axial MR images at the mid-disk, at the level of maximum cord compression and the level below. Univariate and multivariate linear regression analyses were used to assess the relationship between baseline cervical muscle measurements of interest with the modified Japanese Orthopedic Association (mJOA), Nurick Classification, Neck Disability Index (NDI), and SF-36 health survey at 6-month and 12-month post-surgery.

Results

Lower RCSA of MF + SCer, less CSA MF + SCer asymmetry and greater FCSA/CSA for the cervical muscle group (e.g., less fatty infiltration), and younger age were significant predictors of higher mJOA scores (e.g., less disability) at 6-month and 12-month post-surgery (all p < 0.05). Greater CSA asymmetry in MF + SCer and lower FCSA/CSA (e.g., more fatty infiltration) for the cervical muscle group were significant predictors of higher Nurick scores (e.g., more disability) at 6-month and 12-month post-surgery (all p < 0.05). Lower FCSA MF + Scer asymmetry, lower FCSA/CSA asymmetry of the muscle group, and greater RCSA MF + SCer were significant predictors of higher NDI scores at 6-month and 12-month post-surgery. Finally, greater FCSA/CSA asymmetry of the MF + SCer, greater FCSA asymmetry of the muscle group, greater RCSA of the muscle group, and greater CSA asymmetry of MF + SCer were significant predictors of lower post-operative SF-36 scores at 6- and 12-month post-surgery.

Conclusion

Our result suggested that cervical paraspinal muscle morphology, specifically greater asymmetry, and fatty infiltration may be important predictors of functional recovery and post-surgical outcomes in patients with DCM.

Outcomes of different zero-profile spacers in the treatment of two-level cervical degenerative disk disease

PURPOSE

The purpose of this study was to analyze the clinical and radiological outcomes of two different zero-profile spacers (ROI-C and anchor-C) in contiguous two-level ACDF for CDDD patients.

METHODS

We retrospectively analyzed patients who underwent contiguous two-level ACDF due to CDDD between January 2015 and December 2020 in our hospital. Patients who received ROI-C and anchor-C were included as the study groups, and those who underwent plate-cage construct (PCC) were included as the control group. The primary outcome measures were radiographical parameters, and the secondary outcome measures were dysphagia, JOA scores and VAS scores for these patients.

RESULTS

A total of 91 patients were enrolled in the study; there were 31, 21 and 39 patients in the ROI-C, anchor-C and PCC groups, respectively. The mean follow-up duration was 24.52 months (range, 18-48 months) in the ROI-C group, 24.38 months (range, 16-52 months) in the anchor-C group and 25.18 months (range, 15-54 months) in the PCC group. The loss of the intervertebral space height and cage subsidence rate in the ROI-C group were significantly higher than those in the anchor-C group and PCC group at the final follow-up (P < 0.05). The ROI-C group showed a lower incidence of adjacent segment degeneration than the anchor-C group and PCC group, but the difference was not significant. The fusion rates were not different among these three groups. The early dysphagia rate was significantly lower in the patients with zero-profile spacers than in the PCC group (P < 0.05), but the difference was not significant at the last follow-up. No relevant differences were found in the JOA scores and VAS scores.

CONCLUSIONS

Zero-profile spacers showed promising clinical outcomes in CDDD patients having contiguous two-level ACDF. However, ROI-C resulted in a higher intervertebral space height loss and a higher cage subsidence rate than anchor-C during the follow-up.

The association between paraspinal muscle parameters and vertebral pedicle microstructure in patients undergoing lumbar fusion surgery

PURPOSE

Lumbar fusion surgery has become a standard procedure in spine surgery and commonly includes the posterior placement of pedicle screws. Bone quality is a crucial factor that affects pedicle screw purchase. However, the relationship between paraspinal muscles and the bone quality of the pedicle is unknown. The aim of the study was to determine the relationship between paraspinal muscles and the ex vivo bony microstructure of the lumbar pedicle.

METHODS

Prospectively, collected data of patients undergoing posterior lumbar fusion for degenerative spinal conditions was analyzed. Pre-operative lumbar magnetic resonance imaging (MRI) scans were evaluated for a quantitative assessment of the cross-sectional area (CSA), functional cross-sectional area (fCSA), and the proportion of intramuscular fat (FI) for the psoas muscle and the posterior paraspinal muscles (PPM) at L4. Intra-operative bone biopsies of the lumbar pedicle were obtained and analyzed with microcomputed tomography (µCT) scans. The following cortical (Cort) and trabecular (Trab) bone parameters were assessed: bone volume fraction (BV/TV), trabecular number (Tb.N), trabecular thickness (Tb.Th), connectivity density (CD), bone-specific surface (BS/BV), apparent density (AD), and tissue mineral density (TMD).

RESULTS

A total of 26 patients with a mean age of 59.1 years and a mean BMI of 29.8 kg/m2 were analyzed. fCSAPPM showed significant positive correlations with BV/TVTrab (ρ = 0.610; p < 0.001), CDTrab (ρ = 0.679; p < 0.001), Tb.NTrab (ρ = 0.522; p = 0.006), Tb.ThTrab (ρ = 0.415; p = 0.035), and ADTrab (ρ = 0.514; p = 0.007). Cortical bone parameters also demonstrated a significant positive correlation with fCSAPPM (BV/TVCort: ρ = 0.584; p = 0.002; ADCort: ρ = 0.519; p = 0.007). FIPsoas was negatively correlated with TMDCort (ρ =  - 0.622; p < 0.001).

CONCLUSION

This study highlights the close interactions between the bone microstructure of the lumbar pedicle and the paraspinal muscle morphology. These findings give us further insights into the interaction between the lumbar pedicle microstructure and paraspinal muscles.

An exploratory study to understand how people use Twitter to share experiences or information about spinal stenosis

BACKGROUND

Spinal stenosis is a narrowing of the spinal canal that may compress neurological tissues resulting in pain and disability. Although previous qualitative studies have solicited data regarding the life experience of patients with spinal stenosis or their opinions on relevant non-surgical treatments, their data was collected from participants in a controlled setting. Therefore, it remains unclear whether patients' or caregivers' concerns/opinions about spinal stenosis would be different in a non-experimental environment. Since Twitter is a popular online platform for people to share information and interact, it may reveal people's thoughts and attitudes about spinal stenosis. This study aimed to identify tweets that are related to spinal stenosis on Twitter, and to categorize them into common themes.

METHODS

A social media monitoring and analysis software program (TalkWalker) was used to search relevant tweets using the keywords 'spinal stenosis' and 'stenosis' between 29 May 2019 and 24 June 2020. Two independent reviewers screened and conducted content analysis of the tweets and classified the tweets into different themes.

RESULTS

Of 510 identified tweets, 362 tweets met the selection criteria. Five themes were identified: (1) compromised physical, psychological, and social wellbeing (n = 173); (2) diverse treatment options (n = 69); (3) coping strategies (n = 30); (4) dissemination of scientific information (n = 86); and (5) health policy (n = 4). Most of the tweets revealed negative impacts of spinal stenosis on patients' physical and psychosocial wellbeing. People with spinal stenosis shared their experiences and sought helps from others, while some people used Twitter to disseminate relevant information and research findings.

CONCLUSIONS

This is the first study exploring Twitter using an online analytical tool to identify themes related to spinal stenosis. The approach not only helps understand people's concerns about spinal stenosis in an uncontrolled environment, but also can be adopted to monitor influences of diseases or public health education on Twitter users.

Risk Factors for Adjacent Segment Disease Following Anterior Cervical Discectomy and Fusion with Plate Fixation: A Systematic Review and Meta-Analysis

BACKGROUND

Adjacent segment disease (ASD) following anterior cervical discectomy and fusion with plating (ACDF-P) may yield a poor prognosis or reoperation. This review aimed to summarize risk factors for radiographic ASD (RASD) and clinical ASD (CASD) after ACDF-P.

METHODS

Six electronic databases were searched from inception to October 30, 2021. Four reviewers independently screened titles, abstracts, and full-text articles to identify relevant studies. Methodological quality of the included studies was evaluated. Meta-analyses for risk factors were conducted, if possible.

RESULTS

Sixteen cohort and 3 case-control studies (3,563 participants) were included. These studies showed low (n = 2), moderate (n = 9), and high (n = 8) risk of bias. One risk factor for RASD was pooled for 2 meta-analyses based on the follow-up period. Four different risk factors for CASD at ≥4 years were pooled for meta-analyses. Limited evidence showed that multi-level fusion, greater asymmetry in total or functional cross-sectional area of the cervical paraspinal muscle, and preoperative degeneration in a greater number of segments were associated with a higher RASD incidence <4 years after ACDF-P. In contrast, no significant risk factors were identified for CASD <4 years after ACDF-P. At ≥4 years after ACDF-P, limited evidence supported that both cephalad and caudal plate-to-disc distances of <5 mm were associated with a higher RASD incidence, and very limited evidence supported that developmental canal stenosis, preoperative RASD, unfused C5-C6 or C6-C7 adjacent segments, use of autogenous bone graft, and spondylosis-related ACDF-P were associated with a higher CASD incidence.

CONCLUSIONS

Although several risk factors for RASD and CASD development after ACDF-P were identified, the supporting evidence was very limited to limited. Future prospective studies should extend the existing knowledge by more robustly identifying risk factors for RASD and CASD after ACDF-P to inform clinical practice.

LEVEL OF EVIDENCE

Prognostic Level IV. See Instructions for Authors for a complete description of levels of evidence.

The effect of age on psoas and paraspinal muscle morphology in patients undergoing posterior lumbar fusion surgery

PURPOSE

The aim of this study was to determine the effect of age on the psoas and posterior paraspinal muscles (PPM; multifidus muscle and erector spinae) and to evaluate potential sex-related differences.

METHODS

MRI-based quantitative assessments of the cross-sectional area (CSA), the functional cross-sectional area (fCSA), the fat area (FAT) and the proportion of intramuscular fat (FI) were conducted on patients undergoing lumbar fusion surgery between 2014 and 2021. The regions of interest were the psoas muscle and the PPM at the superior endplate of L4. The left and right sides of the muscle groups were summarized and normalized by the patient's height (cm2/m2). The relationships between age and muscular parameters were analyzed stratified by sex.

RESULTS

A total of 195 patients (57.9%female) with a median age of 64.2 years and a body mass index of 28.3 kg/m2 were analyzed. The CSAPsoas was 7.7 cm2/m2 and differed significantly between females and males (p < 0.001); likewise, the fCSAPsoas differed significantly between the sexes. The CSAPPM was 18.8 cm2/m2 with no sex-specific differences. Significant differences were found in the FIPPM (males: 41.1% vs. females: 47.9%; p < 0.001), but not in the FIPsoas (males: 3.7% vs. females: 4.5%; p = 0.276). Considering the effect of age on FI, a significant positive correlation was observed for the PPMs for both sexes. Only in women, there was a negative correlation between age and CSAPsoas (ρ =  - 0.248; p = 0.008), FATPsoas (ρ =  - 0.421; p < 0.001) and FIPsoas (ρ =  - 0.371; p < 0.001).

CONCLUSION

This study demonstrated sex-specific differences in spinal muscle morphology in relation to patient age. With increasing age there was a decrease in FIPsoas in women only, unlike in the PPMs in which there was increased FI that was significantly higher in women compared to men.

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.

Artificial intelligence in predicting early-onset adjacent segment degeneration following anterior cervical discectomy and fusion

PURPOSE

Anterior cervical discectomy and fusion (ACDF) is a common surgical treatment for degenerative disease in the cervical spine. However, resultant biomechanical alterations may predispose to early-onset adjacent segment degeneration (EO-ASD), which may become symptomatic and require reoperation. This study aimed to develop and validate a machine learning (ML) model to predict EO-ASD following ACDF.

METHODS

Retrospective review of prospectively collected data of patients undergoing ACDF at a quaternary referral medical center was performed. Patients > 18 years of age with > 6 months of follow-up and complete pre- and postoperative X-ray and MRI imaging were included. An ML-based algorithm was developed to predict EO-ASD based on preoperative demographic, clinical, and radiographic parameters, and model performance was evaluated according to discrimination and overall performance.

RESULTS

In total, 366 ACDF patients were included (50.8% male, mean age 51.4 ± 11.1 years). Over 18.7 ± 20.9 months of follow-up, 97 (26.5%) patients developed EO-ASD. The model demonstrated good discrimination and overall performance according to precision (EO-ASD: 0.70, non-ASD: 0.88), recall (EO-ASD: 0.73, non-ASD: 0.87), accuracy (0.82), F1-score (0.79), Brier score (0.203), and AUC (0.794), with C4/C5 posterior disc bulge, C4/C5 anterior disc bulge, C6 posterior superior osteophyte, presence of osteophytes, and C6/C7 anterior disc bulge identified as the most important predictive features.

CONCLUSIONS

Through an ML approach, the model identified risk factors and predicted development of EO-ASD following ACDF with good discrimination and overall performance. By addressing the shortcomings of traditional statistics, ML techniques can support discovery, clinical decision-making, and precision-based spine care.

Artificial Intelligence-Driven Prediction Modeling and Decision Making in Spine Surgery Using Hybrid Machine Learning Models

Healthcare systems worldwide generate vast amounts of data from many different sources. Although of high complexity for a human being, it is essential to determine the patterns and minor variations in the genomic, radiological, laboratory, or clinical data that reliably differentiate phenotypes or allow high predictive accuracy in health-related tasks. Convolutional neural networks (CNN) are increasingly applied to image data for various tasks. Its use for non-imaging data becomes feasible through different modern machine learning techniques, converting non-imaging data into images before inputting them into the CNN model. Considering also that healthcare providers do not solely use one data modality for their decisions, this approach opens the door for multi-input/mixed data models which use a combination of patient information, such as genomic, radiological, and clinical data, to train a hybrid deep learning model. Thus, this reflects the main characteristic of artificial intelligence: simulating natural human behavior. The present review focuses on key advances in machine and deep learning, allowing for multi-perspective pattern recognition across the entire information set of patients in spine surgery. This is the first review of artificial intelligence focusing on hybrid models for deep learning applications in spine surgery, to the best of our knowledge. This is especially interesting as future tools are unlikely to use solely one data modality. The techniques discussed could become important in establishing a new approach to decision-making in spine surgery based on three fundamental pillars: (1) patient-specific, (2) artificial intelligence-driven, (3) integrating multimodal data. The findings reveal promising research that already took place to develop multi-input mixed-data hybrid decision-supporting models. Their implementation in spine surgery may hence be only a matter of time.

The effect of posterior lumbar dynamic fixation and intervertebral fusion on paraspinal muscles

BACKGROUND

The aim of this study was to analyze the effect of unilateral K-rod dynamic internal fixation on paraspinal muscles for lumbar degenerative diseases.

METHODS

This study retrospectively collected 52 patients who underwent lumbar surgery with the K-rod group or PLIF. The operation time, intraoperative blood loss, postoperative drainage volume, postoperative exercise time were compared in the two groups. The visual analog scale (VAS) score and the oswestry dysfunction index (ODI) were employed to evaluate the clinical outcomes. The functional cross-sectional area (FCSA) of the paraspinal muscles and paraspinal muscles fat infiltration were measured to assess on the paraspinal muscles.

RESULTS

As compared with the PLIF group, the operation time, the postoperative time in the field, and the average postoperative hospital stay in the K-rod internal fixation group were significantly shortened. At the last follow-up, both the groups showed significant improvement in the VAS score and ODI. The FCSA atrophy of the upper and lower adjacent segments (UAS and LAS) of the K-rod internal group was significantly less than that of the PLIF group. The extent of increase in the fatty infiltration of the paraspinal muscles in the K-rod group was significantly lesser than that in the PLIF group. The postoperative low back pain of the two groups of patients was significantly positively correlated with the FCSA atrophy.

CONCLUSIONS

As compared to PLIF, the posterior lumbar unilateral K-rod dynamic internal fixation showed significantly lesser paraspinal muscle atrophy and fatty infiltration, which were significantly positively correlated with postoperative low back pain.

The Role of Cervical Muscles Morphology in the Surgical Treatment of Degenerative Disc Disease: Clinical Correlations Based on Magnetic Resonance Imaging Studies

Cervical spine musculature still remains a less studied component of the cervical spine anatomical compartments, although it plays a significant role in the mobility of the head and the preservation of cervical spine alignment. The goal of this study was to extract any significant information from the literature regarding the role of cervical spine muscles morphology in the outcome of surgically treated patients for degenerative disc disease (DDD) based on preoperative magnetic resonance imaging (MRI) studies. Eleven clinical case series were found, from which four were prospective and seven were retrospective. Six studies were concentrated on anterior approaches and five studies on posterior approaches in the cervical spine. In posterior approaches aiming at the preservation of muscles attachments and overall less surgical manipulations, results on cervical lordosis, axial pain and patient’s functionality were found superior to traditional laminectomies. The study of cross-sectional areas (CSAs) of deep paraspinal muscles in the cervical spine could add significant information for the spine surgeon such as the prediction of adjacent level disease (ALD), fusion failure, axial pain persistence, postoperative cervical alignment and patient’s postoperative functionality. It seems that MRI studies focusing on muscle layers of the cervical spine could add significant information for the spinal surgeon regarding the final surgical outcome in terms of pain and function expression. Larger multicenter clinical studies are a necessity in defining the role of the muscle component of the cervical spine in the surgical treatment of DDD.