Association of lumbar disc degeneration with low back pain in middle age in the Northern Finland Birth Cohort 1966

The prevalence of depression in patients with lumbar degenerative disk disease: A systematic review and meta-analysis

BACKGROUND

Lumbar degenerative disc disease (DDD) is a prevalent musculoskeletal disorder characterized by significant pain, disability, and reduced quality of life. Depression frequently coexists with chronic pain conditions, intensifying symptoms and complicating management. Despite its clinical relevance, the prevalence of depression specifically among patients with lumbar DDD remains inadequately understood.

AIM

This systematic review and meta-analysis aimed to assess the prevalence of depression among patients with lumbar DDD and to identify potential sources of heterogeneity.

METHODS

A comprehensive literature search was conducted using PubMed, Web of Science, ScienceDirect, Academic Search Complete, and Google Scholar to identify relevant studies published between 2015 and 2022. Studies reporting the prevalence of depression among patients with lumbar DDD were included in the analysis. Pooled prevalence estimates were calculated using random-effects models, and subgroup analyses were performed to investigate sources of heterogeneity.

RESULTS

Seven studies met the inclusion criteria, encompassing 3485 patients with lumbar DDD. The pooled prevalence of depression was estimated at 20.19% (95% CI 8.94-39.46%). Subgroup analyses revealed significant variations in prevalence estimates across different geographic regions and assessment tools. Sensitivity analyses confirmed the robustness of the findings, while meta-regression analyses did not identify significant associations between prevalence rates and factors such as age or year of publication.

CONCLUSIONS

This study highlights a substantial burden of depression among patients with lumbar DDD, emphasizing the need for comprehensive mental health assessment and management in this population. The findings contribute to a better understanding of the psychological comorbidities associated with lumbar DDD and have implications for clinical practice and future research.

A comparison of Contractile properties of posterior chain muscles and trunk strength in females with non-specific chronic low back pain

ObjectiveThe purpose of this study was to compare the contractile properties of posterior chain muscles and isokinetic trunk strength in females with or without non-specific chronic low back pain (NSCLBP).MethodAll participants (control group: n = 22, NSCLBP group: n = 22) were assessed using tensiomyography to evaluate the contractile properties of the posterior chain muscles, and all participants were also assessed for isokinetic trunk strength. An independent t-test was performed to compare the tensiomyography variables and isokinetic trunk strength test results between group.ResultsResult of tensiomyography, we found that the contraction time significant differences in the maximal radial muscle displacement, and velocity of contraction between groups in erector spinae. Semitendinosus revealed significant differences in all variables between groups. Additionally, the isokinetic trunk strength test revealed significant differences in all variables between groups.ConclusionThese findings suggest that due to the characteristics of NSCLBP, such as increased muscle stiffness, fat infiltration, and muscle fatigue, kinesiophobia, physical deconditioning syndrome, the posterior chain muscles of the NSCLBP group showed higher muscle stiffness and slower contraction speed than the control group. Also in the NSCLBP group, trunk isokinetic muscle strength was lower than in the control group, and flexor and extensor muscles were unbalanced.

The association of lumbar intervertebral disc degeneration with low back pain is modified by underlying genetic propensity to pain

BACKGROUND CONTEXT

Associations between magnetic resonance imaging (MRI)-detected lumbar intervertebral disc degeneration (LDD) and LBP are often of modest magnitude. This association may be larger in specific patient subgroups.

PURPOSE

To examine whether the association between LDD and LBP is modified by underlying genetic predispositions to pain.

STUDY DESIGN

Cross-sectional study in UK Biobank (UKB) and Twins UK.

PATIENT SAMPLES

A genome-wide association study (GWAS) of the number of anatomical chronic pain locations was conducted in 347,538 UKB participants. The GWAS was used to develop a genome-wide polygenic risk score (PRS) in a holdout sample of 30,000 UKB participants. The PRS model was then used in analyses of 645 TwinsUK participants with standardized LDD MRI assessments.

OUTCOME MEASURES

Ever having had LBP associated with disability lasting ≥1 month (LBP1).

METHODS

Using the PRS as a proxy for "genetically-predicted propensity to pain", we stratified TwinsUK participants into PRS quartiles. A "basic" model examined the association between an LDD summary score (LSUM) and LBP1, adjusting for covariates. A "fully-adjusted" model also adjusted for PRS quartile and LSUM x PRS quartile interaction terms.

RESULTS

In the basic model, the odds ratio (OR) of LBP1 was 1.8 per standard deviation of LSUM (95% confidence interval [CI] 1.4-2.3). In the fully-adjusted model, there was a statistically significant LSUM-LBP1 association in quartile 4, the highest PRS quartile (OR=2.5 [95% CI 1.7-3.7], p=2.6×10-6), and in quartile 3 (OR=2.0, [95% CI 1.3-3.0]; p=.002), with small-magnitude and/or nonsignificant associations in the lowest 2 PRS quartiles. PRS quartile was a significant effect modifier of the LSUM-LBP1 association (interaction p≤.05).

CONCLUSIONS

Genetically-predicted propensity to pain modifies the LDD-LBP association, with the strongest association present in people with the highest genetic propensity to pain. Lumbar MRI findings may have stronger connections to LBP in specific subgroups of people.

Gut microbiome dysbiosis is associated with lumbar degenerative spondylolisthesis in symptomatic patients

Background

Lumbar degenerative spondylolisthesis (LDS), characterized as degeneration of the intervertebral disc and structural changes of the facet joints, is a condition with varying degrees of instability that may lead to pain, canal stenosis, and subsequent surgical intervention. However, the etiology of LDS remains inconclusive. Gut microbiome dysbiosis may stimulate systemic inflammation in various disorders. However, the role of such dysbiosis upon spine health remains under-studied. The current study assessed the association of gut microbiome dysbiosis in symptomatic patients with or without LDS.

Methods

A cross-sectional analysis within the framework of a prospective study was performed. DNA was extracted from fecal samples collected from adult symptomatic patients with (n = 21) and without LDS (n = 12). Alpha and beta diversity assessed differences in fecal microbial community between groups. Taxon-by-taxon analysis identified microbial features with differential relative abundance between groups. Subject demographics and imaging parameters were also assessed.

Results

There was no significant group differences in age, sex, race, body mass index, smoking/alcohol history, pain profiles, spinopelvic alignment, and Modic changes (p >0.05). LDS subjects had significantly higher disc degeneration severity (p = 0.018) and alpha diversity levels compared to non-LDS subjects (p = 0.002-0.003). Significant differences in gut microbial community structure were observed between groups (p = 0.046). Subjects with LDS exhibited distinct differences at the phylum level, with a significantly higher Firmicutes to Bacteroidota ratio compared to non-LDS (p = 0.003). Differential relative abundance analysis identified six taxa with significant differences between the two groups, with LDS demonstrating an increase in putative pro-inflammatory bacteria (Dialister, CAG-352) and a decrease in anti-inflammatory bacteria (Slackia, Escherichia-Shigella).

Conclusion

This study is the first to report a significant association of gut microbiome dysbiosis and LDS in symptomatic patients, noting pro-inflammatory bacterial taxa. This work provides a foundation for future studies addressing the role of the gut microbiome in association with spine health and disease.

EXPLORING THE FEASIBILITY OF PLATELET-RICH PLASMA INJECTIONS FOR INTERVERTEBRAL DISCOPATHY: A PILOT STUDY

Objective

This longitudinal pilot study aimed to evaluate the feasibility, safety and potential benefits of Platelet-Rich Plasma injections into the lumbar intervertebral discs in patients with low back pain and degenerative intervertebral monodiscopathy, assessing potential efficacy on disability.

Design

Longitudinal pilot study.

Methods

Six participants with chronic low back pain and lumbar degenerative intervertebral disc (monodiscopathy) disease underwent 1 Platelet-Rich Plasma injection, with a 1-year follow-up. Platelet-Rich Plasma injections were administered into the lumbar intervertebral disc, and outcomes were measured using the Roland Morris Disability Questionnaire, numeric rating scale for pain, Tampa scale for kinesiophobia and lumbar flexion range. Magnetic resonance imaging analysis assessed disc changes.

Results

No adverse events were reported. At the end of the 1-year follow-up, half of the patients showed significant improvements in disability scores at 1 year, while 3 of the 6 patients had no change. Magnetic resonance imaging revealed no significant disc changes.

Conclusion

Platelet-Rich Plasma injections show promise for some patients with low back pain and degenerative intervertebral discopathy patients. However, caution is warranted due to study limitations, including small sample size and lack of a control group. Further research is needed to define Platelet-Rich Plasma therapy protocols.

Correlation of MRI-Evaluated Degenerative Disc Disease with Positivity on Single-Photon Emission Computed Tomography Imaging in Patients with Chronic Low Back Pain

OBJECTIVE

Chronic low back pain, affecting up to 58% of the population, often stems from intervertebral disc degeneration. Although magnetic resonance imaging (MRI) is commonly used for diagnostics, challenges arise in pinpointing pain sources due to frequent asymptomatic findings. Single-photon emission tomography (SPECT) integrated with computed tomography (CT) offers a promising approach, enhancing sensitivity and specificity.

METHODS

In this retrospective study, spanning 2016 to 2022, SPECT/CT imaging was performed on 193 patients meeting specific criteria. We correlated SPECT/CT findings with lumbar MRI results, utilizing Pfirrmann and Rajasekaran classifications for disc degeneration and endplate damage assessment. Logistic regression analysis adjusted for age and sex evaluated associations.

RESULTS

Of 965 spinal levels assessed, SPECT/CT positivity strongly correlated with higher Pfirrmann grades and Rajasekaran endplate classifications. Notably, Modic changes (MCs) on MRI displayed a nonsignificant relationship with SPECT/CT positivity. Significant associations were observed in older patients with positive MCs, Pfirrmann grades, and Rajasekaran classifications.

CONCLUSIONS

This comprehensive study, the largest of its kind, establishes a significant link between SPECT/CT positivity and advanced lumbar degenerative changes. Higher Pfirrmann grades and increased Rajasekaran endplate damage demonstrated substantial correlations with SPECT/CT positivity. Notably, MCs did not exhibit such association. Our findings underscore the potential of SPECT/CT in identifying pain generators in degenerative spinal conditions, offering valuable insights for future interventions.

Relationship of disc degeneration after pubertal growth spurt to future low back pain: a longitudinal cohort study

PURPOSE

In this longitudinal cohort study, we investigated the relationship of disc degeneration (DD) after pubertal growth spurt to future low back pain (LBP).

METHODS

A group of healthy volunteers underwent a semi-structured interview about LBP without trauma and a 1.5T lumbar MRI at ages 18 and 34. A Pfirrmann Summary Score (PSS) was calculated by adding up the Pfirrmann grades of the three lowest lumbar discs of each subject (range 3-15). The relationship of PSS at age 18 to LBP at age 34 was analyzed.

RESULTS

Forty-one participants had full data at both time points. Mean PSS at age 18 was 6.8 (SD 1.1) and 5.6 (SD 1.2) for participants with or without LBP at age 34, respectively (p = 0.009). The OR (95% CI) of PSS at age 18 for LBP at age 34 was 5.46 (1.22 to 24.47) when adjusted for sex, BMI, smoking and physical activity. All participants but one with PSS greater than 6 at age 18 reported LBP at age 34.

CONCLUSION

This is the first study to suggest that DD may be associated with future LBP and the critical time frame seems to be the pubertal growth spurt. Every 1-point increase in Pfirrmann grade at age 18 increased the risk of LBP 5.5-fold at age 34 when adjusted for sex, BMI, smoking and physical activity at age 34. All participants but one with at least one disc with Pfirrmann grade 3 or higher at age 18 reported LBP at age 34.

Associations of socioeconomic and lifestyle characteristics, psychological symptoms, multimorbidity, and multisite pain with sciatica - a 15-year longitudinal study

BACKGROUND CONTEXT

Sciatica is defined as pain radiating from the low back to the leg, usually below the knee. It is a disabling condition that causes a major burden to health care and society. Previous evidence of the multifactorial etiology of sciatica comes mostly from cross-sectional studies. Larger, longitudinal studies with a multidimensional set of variables are needed.

PURPOSE

To examine how socioeconomic and lifestyle characteristics, psychological symptoms, multimorbidity, and multisite pain are associated with sciatica.

STUDY DESIGN

A longitudinal study of the Northern Finland Birth Cohort 1966.

PATIENT SAMPLE

In total 6,683 working-aged members of the Northern Finland Birth Cohort 1966.

OUTCOME MEASURES

Self-reported sciatic pain status over a 15-year study period.

METHODS

We conducted a 15-year longitudinal study from the age of 31 to 46. We used multivariable generalized estimation equations analysis to examine how socioeconomic characteristics (low education, unemployment, and living alone), lifestyle characteristics (overweight, obesity, current smoking, and physical inactivity), psychological symptoms (depression, anxiety), multimorbidity, and multisite pain were associated with sciatica.

RESULTS

At the age of 31, 21.1% of the study population reported sciatic pain and at the age of 46, 36.7%. Multisite pain was clearly the strongest factor associated with sciatica (odds ratio [OR] 2.61, 95% confidence interval [CI] 2.34‒2.92). In descending order of effect size, older age, low education, psychological symptoms, multimorbidity, overweight, obesity, physical inactivity and current smoking were positively associated with sciatica. Their ORs varied between 1.17 and 2.18. Living alone was negatively associated with sciatica (OR 0.81, 95% CI 0.72‒0.90).

CONCLUSIONS

Multisite pain had the strongest association with sciatica. The effect sizes of the other factors were clearly smaller. To our knowledge this is the first study to evaluate the association of multisite pain with sciatica. This finding may have considerable implications for clinical work treating patients with sciatica.

Causal association of leisure sedentary behavior and cervical spondylosis, sciatica, intervertebral disk disorders, and low back pain: a Mendelian randomization study

Background

Some studies suggest sedentary behavior is a risk factor for musculoskeletal disorders. This study aimed to investigate the potential causal association between leisure sedentary behavior (LSB) (including television (TV) viewing, computer use, and driving) and the incidence of sciatica, intervertebral disk degeneration (IVDD), low back pain (LBP), and cervical spondylosis (CS).

Methods

We obtained the data of LSB, CS, IVDD, LBP, sciatica and proposed mediators from the gene-wide association studies (GWAS). The causal effects were examined by Inverse Variance Weighted (IVW) test, MR-Egger, weighted median, weighted mode and simple mode. And sensitivity analysis was performed using MR-Pleiotropy Residual Sum and Outlier (MR-PRESSO) and MR-Egger intercept test. Multivariable MR (MVMR) was conducted to investigate the independent factor of other LSB; while two-step MR analysis was used to explore the potential mediators including Body mass index (BMI), smoking initiation, type 2 diabetes mellitus (T2DM), major depressive disorder (MDD), schizophrenia, bipolar disorder between the causal association of LSB and these diseases based on previous studies.

Results

Genetically associated TV viewing was positively associated with the risk of CS (OR = 1.61, 95%CI = 1.25 to 2.07, p = 0.002), IVDD (OR = 2.10, 95%CI = 1.77 to 2.48, p = 3.79 × 10-18), LBP (OR = 1.84, 95%CI = 1.53 to 2.21, p = 1.04 × 10-10) and sciatica (OR = 1.82, 95% CI = 1.45 to 2.27, p = 1.42 × 10-7). While computer use was associated with a reduced risk of IVDD (OR = 0.66, 95%CI = 0.55 to 0.79, p = 8.06 × 10-6), LBP (OR = 0.49, 95%CI = 0.40 to 0.59, p = 2.68 × 10-13) and sciatica (OR = 0.58, 95%CI = 0.46 to 0.75, p = 1.98 × 10-5). Sensitivity analysis validated the robustness of MR outcomes. MVMR analysis showed that the causal effect of TV viewing on IVDD (OR = 1.59, 95%CI = 1.13 to 2.25, p = 0.008), LBP (OR = 2.15, 95%CI = 1.50 to 3.08, p = 3.38 × 10-5), and sciatica (OR = 1.61, 95%CI = 1.03 to 2.52, p = 0.037) was independent of other LSB. Furthermore, two-step MR analysis indicated that BMI, smoking initiation, T2DM may mediate the causal effect of TV viewing on these diseases.

Conclusion

This study provides empirical evidence supporting a positive causal association between TV viewing and sciatica, IVDD and LBP, which were potentially mediated by BMI, smoking initiation and T2DM.

Predictive value of texture analysis on lumbar MRI in patients with chronic low back pain

PURPOSE

The aim of this study was to determine whether MRI texture analysis could predict the prognosis of patients with non-specific chronic low back pain.

METHODS

A prospective observational study was conducted on 100 patients with non-specific chronic low back pain, who underwent a conventional MRI, followed by rehabilitation treatment, and revisited after 6 months. Sociodemographic variables, numeric pain scale (NPS) value, and the degree of disability as measured by the Roland-Morris disability questionnaire (RMDQ), were collected. The MRI analysis included segmentation of regions of interest (vertebral endplates and intervertebral disks from L3-L4 to L5-S1, paravertebral musculature at the L4-L5 space) to extract texture variables (PyRadiomics software). The classification random forest algorithm was applied to identify individuals who would improve less than 30% in the NPS or would score more than 4 in the RMDQ at the end of the follow-up. Sensitivity, specificity, and the area under the ROC curve were calculated.

RESULTS

The final series included 94 patients. The predictive model for classifying patients whose pain did not improve by 30% or more offered a sensitivity of 0.86, specificity 0.57, and area under the ROC curve 0.71. The predictive model for classifying patients with a RMDQ score 4 or more offered a sensitivity of 0.83, specificity of 0.20, and area under the ROC curve of 0.52.

CONCLUSION

The texture analysis of lumbar MRI could help identify patients who are more likely to improve their non-specific chronic low back pain through rehabilitation programs, allowing a personalized therapeutic plan to be established.

The Relationship between Magnetic Resonance Imaging and Functional Tests Assessment in Patients with Lumbar Disk Hernia

Although magnetic resonance imaging (MRI) findings are the gold standard for diagnosing herniated discs, there are many limitations to accessing MRI scanning devices in practice. This study aimed to evaluate the relationship between functional tests (the visual analog scale (VAS), the SLUMP test, the Sciatica Bothersomeness Index (SBI), the Oswestry Disability Index (ODI), and the LASEGUE test and MRI findings (LSA, IVDH L4-L5, IVDH L5-S1, DHS L4-L5, and DHS L5-S1) in patients diagnosed with disc herniation. Seventy-eight patients who met the inclusion criteria participated in the study. Radiologists and neurologists evaluated patients with disc herniation. After the disc hernia diagnosis, the patients were referred to a physical therapist for conservative management of the disk hernia. The physical therapists assessed the pain level and performed functional tests on patients. All statistical analyses were performed using R (Core Team) software. The correlation between the measured variables was conducted using the Pearson and Spearman tests. The study results indicated statistically significant correlations between DHS L4-L5 vertebral level and functional tests (VAS: r = 0.49, p = 0.00; SBI: r = 0.44, p = 0.00; ODI: r = 0.49, p = 0.00; LASEGUE: r = -0.48, p = 0.00; SLUMP: r = 0.50, p = 0.00). In conclusion, physiotherapists may prefer functional tests to diagnose the herniated disc, and these functional tests may contribute to performing evidence-based assessments.

Intervertebral disc degeneration-Current therapeutic options and challenges

Degeneration of the intervertebral disc (IVD) is a normal part of aging. Due to the spine's declining function and the development of pain, it may affect one's physical health, mental health, and socioeconomic status. Most of the intervertebral disc degeneration (IVDD) therapies today focus on the symptoms of low back pain rather than the underlying etiology or mechanical function of the disc. The deteriorated disc is typically not restored by conservative or surgical therapies that largely focus on correcting symptoms and structural abnormalities. To enhance the clinical outcome and the quality of life of a patient, several therapeutic modalities have been created. In this review, we discuss genetic and environmental causes of IVDD and describe promising modern endogenous and exogenous therapeutic approaches including their applicability and relevance to the degeneration process.

Early disc degeneration in radiotherapy-treated childhood brain tumor survivors

BACKGROUND

Childhood brain tumor (BT) survivors have an increased risk of treatment-related late effects, which can reduce health-related quality of life and increase morbidity. This study aimed to investigate lumbar disc degeneration in magnetic resonance imaging (MRI) in adult survivors of radiotherapy-treated childhood BT compared to age and sex-matched population controls.

METHODS

In this cross-sectional comparative study, 127 survivors were identified from hospital registries. After a mean follow-up of 20.7 years (range 5-33.1), 67 survivors (mean age 28.4, range 16.2-43.5) were investigated with MRI and compared to 75 sex-matched population-based controls. Evaluated MRI phenotypes included Pfirrmann grading, , intervertebral disc protrusions, extrusions, and high-intensity-zone-lesions (HIZ). Groups were also compared for known risk factors of lumbar intervertebral disc (IVD) degeneration.

RESULTS

Childhood BT survivors had higher Pfirrmann grades than controls at all lumbar levels (all p < 0.001). Lumbar disc protrusions at L4-5 (p = 0.02) and extrusions at L3-4 (p = 0.04), L4-5 (p = 0.004), and L5-S1 (p = 0.01) were significantly more common in the BT group compared to the control. The survivor cohort also had significantly more HIZ-lesons than the controls (n=13 and n=1, p=0.003). Age at diagnosis was associated with lower degree of IVD degeneration (p < 0.01). Blood pressure correlated with IVD degeneration (P < 0.05).

CONCLUSIONS

Signs of early disc degeneration related to tumor treatment can be seen in the IVDs of survivors. Disc degeneration was more severe in children treated in adolescence.

ISSLS PRIZE in Clinical Science 2023: comparison of degenerative MRI features of the intervertebral disc between those with and without chronic low back pain. An exploratory study of two large female populations using automated annotation

OBJECTIVES

The relationship of degeneration to symptoms has been questioned. MRI detects apparently similar disc degeneration and degenerative changes in subjects both with and without back pain. We aimed to overcome these problems by re-annotating MRIs from asymptomatic and symptomatics groups onto the same grading system.

METHODS

We analysed disc degeneration in pre-existing large MRI datasets. Their MRIs were all originally annotated on different scales. We re-annotated all MRIs independent of their initial grading system, using a verified, rapid automated MRI annotation system (SpineNet) which reported degeneration on the Pfirrmann (1-5) scale, and other degenerative features (herniation, endplate defects, marrow signs, spinal stenosis) as binary present/absent. We compared prevalence of degenerative features between symptomatics and asymptomatics.

RESULTS

Pfirrmann degeneration grades in relation to age and spinal level were very similar for the two independent groups of symptomatics over all ages and spinal levels. Severe degenerative changes were significantly more prevalent in discs of symptomatics than asymptomatics in the caudal but not the rostral lumbar discs in subjects < 60 years. We found high co-existence of degenerative features in both populations. Degeneration was minimal in around 30% of symptomatics < 50 years.

CONCLUSIONS

We confirmed age and disc level are significant in determining imaging differences between asymptomatic and symptomatic populations and should not be ignored. Automated analysis, by rapidly combining and comparing data from existing groups with MRIs and information on LBP, provides a way in which epidemiological and 'big data' analysis could be advanced without the expense of collecting new groups.

LEVEL OF EVIDENCE I

Diagnostic: individual cross-sectional studies with consistently applied reference standard and blinding.

The role of co-occurring insomnia and mental distress in the association between lumbar disc degeneration and low back pain related disability

BACKGROUND

Lumbar disc degeneration (LDD) is associated with low back pain (LBP). Although both insomnia and mental distress appear to influence the pain experience, their role in the association between LDD and LBP is uncertain. Our objective was to investigate the role of co-occurring insomnia and mental distress in the association between LDD and LBP-related disability.

METHODS

A total of 1080 individuals who had experienced LBP during the previous year underwent 1.5-T lumbar magnetic resonance imaging, responded to questionnaires, and participated in a clinical examination at the age of 47. Full data was available for 843 individuals. The presence of LBP and LBP-related disability (numerical rating scale, range 0-10) were assessed using a questionnaire. LDD was assessed by a Pfirrmann-based sum score (range 0-15, higher values indicating higher LDD). The role of insomnia (according to the five-item Athens Insomnia Scale) and mental distress (according to the Hopkins Symptom Check List-25) in the association between the LDD sum score and LBP-related disability was analyzed using linear regression with adjustments for sex, smoking, body mass index, education, leisure-time physical activity, occupational physical exposure, Modic changes, and disc herniations.

RESULTS

A positive association between LDD and LBP-related disability was observed among those with absence of both mental distress and insomnia (adjusted B = 0.132, 95% CI = 0.028-0.236, p = 0.013), and among those with either isolated mental distress (B = 0.345 CI = 0.039-0.650, p = 0.028) or isolated insomnia (B = 0.207, CI = 0.040-0.373, p = 0.015). However, among individuals with co-occurring insomnia and mental distress, the association was not significant (B = -0.093, CI = -0.346-0.161, p = 0.470).

CONCLUSIONS

LDD does not associate with LBP-related disability when insomnia and mental distress co-occur. This finding may be useful when planning treatment and rehabilitation that aim to reduce disability among individuals with LDD and LBP. Future prospective research is warranted.

External Validation of SpineNet, an Open-Source Deep Learning Model for Grading Lumbar Disk Degeneration MRI Features, Using the Northern Finland Birth Cohort 1966

STUDY DESIGN

This is a retrospective observational study to externally validate a deep learning image classification model.

OBJECTIVE

Deep learning models such as SpineNet offer the possibility of automating the process of disk degeneration (DD) classification from magnetic resonance imaging (MRI). External validation is an essential step to their development. The aim of this study was to externally validate SpineNet predictions for DD using Pfirrmann classification and Modic changes (MCs) on data from the Northern Finland Birth Cohort 1966 (NFBC1966).

SUMMARY OF DATA

We validated SpineNet using data from 1331 NFBC1966 participants for whom both lumbar spine MRI data and consensus DD gradings were available.

MATERIALS AND METHODS

SpineNet returned Pfirrmann grade and MC presence from T2-weighted sagittal lumbar MRI sequences from NFBC1966, a data set geographically and temporally separated from its training data set. A range of agreement and reliability metrics were used to compare predictions with expert radiologists. Subsets of data that match SpineNet training data more closely were also tested.

RESULTS

Balanced accuracy for DD was 78% (77%-79%) and for MC 86% (85%-86%). Interrater reliability for Pfirrmann grading was Lin concordance correlation coefficient=0.86 (0.85-0.87) and Cohen κ=0.68 (0.67-0.69). In a low back pain subset, these reliability metrics remained largely unchanged. In total, 20.83% of disks were rated differently by SpineNet compared with the human raters, but only 0.85% of disks had a grade difference >1. Interrater reliability for MC detection was κ=0.74 (0.72-0.75). In the low back pain subset, this metric was almost unchanged at κ=0.76 (0.73-0.79).

CONCLUSIONS

In this study, SpineNet has been benchmarked against expert human raters in the research setting. It has matched human reliability and demonstrates robust performance despite the multiple challenges facing model generalizability.