[Predictive value of nerve root sedimentation sign in diagnosis of lumbar spinal stenosis].

Objective: To explore the predictive value of the nerve root sedimentation sign in the diagnosis of lumbar spinal stenosis (LSS). Methods: Between January 2019 and July 2021, 201 patients with non-specific low back pain (NS-LBP) who met the selection criteria were retrospectively analyzed. There were 67 males and 134 females, with an age of 50-80 years (mean, 60.7 years). Four intervertebral spaces (L 1, 2, L 2, 3, L 3, 4, L 4, 5) of each case were studied, with a total of 804. The nerve root sedimentation sign was positive in 126 intervertebral spaces, and central canal stenosis was found in 203 intervertebral spaces. Progression to symptomatic LSS was determined by follow-up for lower extremity symptoms similar to LSS, combined with central spinal stenosis. Univariate analysis was performed for gender, age, visual analogue scale (VAS) score for low back pain at initial diagnosis, treatment, dural sac cross-sectional area at each intervertebral space, number of spinal stenosis segments, lumbar spinal stenosis grade, positive nerve root sedimentation sign, and number of positive segments between patients in the progression group and non-progression group, and logistic regression analysis was further performed to screen the risk factors for progression to symptomatic LSS in patients with NS-LBP. Results: All patients were followed up 17-48 months, with an average of 32 months. Of 201 patients with NS-LBP, 35 progressed to symptomatic LSS. Among them, 33 cases also had central spinal stenosis, which was defined as NS-LBP progressing to symptomatic LSS (33 cases in progression group, 168 cases in non-progression group). Univariate analysis showed that CSA at each intervertebral space, the number of spinal stenosis segments, lumbar spinal stenosis grade, whether the nerve root sedimentation sign was positive, and the number of nerve root sedimentation sign positive segments were the influencing factors for the progression to symptomatic LSS ( P<0.05); and further logistic regression analysis showed that positive nerve root sedimentation sign increased the risk of progression of NS-LBP to symptomatic LSS ( OR=8.774, P<0.001). Conclusion: The nerve root sedimentation sign may be associated with the progression of NS-LBP to symptomatic LSS, and it has certain predictive value for the diagnosis of LSS.

Lumbar Spinal Stenosis: Diagnosis and Management.

Lumbar spinal stenosis is a clinical syndrome that affects more than 200,000 people in the United States annually. It is a common cause of chronic insidious low back pain, especially in older patient populations (mean age = 64 years). Lumbar spinal stenosis is a degenerative condition of the spine leading to narrowing in the spaces around the neurovascular bundles and the classic symptom of low back pain that radiates to the buttocks and lower extremities bilaterally. It is typically a progressive waxing and waning process that may deteriorate over years. The pain is typically burning or cramping, which worsens with standing and walking and improves with bending forward or sitting. Magnetic resonance imaging is the recommended diagnostic test because it allows cross-sectional measurement of the spinal canal. Options for nonsurgical management include physical therapy, exercise programs, spinal injections with and without corticosteroids, chiropractic treatment, osteopathic manipulation, acupuncture, and lifestyle modifications; however, few of these treatments have high-quality randomized trials demonstrating effectiveness. Surgery may be considered if nonsurgical management is ineffective.

An Artificial Intelligence-Based Support Tool for Lumbar Spinal Stenosis Diagnosis from Self-Reported History Questionnaire.

OBJECTIVES: Symptomatic lumbar spinal stenosis (LSS) leads to functional impairment and pain. While radiologic characterization of the morphological stenosis grade can aid in the diagnosis, it may not always correlate with patient symptoms. Artificial intelligence (AI) may diagnose symptomatic LSS in patients solely based on self-reported history questionnaires. METHODS: We evaluated multiple machine learning (ML) models to determine the likelihood of LSS using a self-reported questionnaire in patients experiencing low back pain and/or numbness in the legs. The questionnaire was built from peer-reviewed literature and a multidisciplinary panel of experts. Random forest, lasso logistic regression, support vector machine, gradient boosting trees, deep neural networks, and automated machine learning models were trained and performance metrics were compared. RESULTS: Data from 4827 patients (4690 patients without LSS: mean age 62.44, range 27-84 years, 62.8% females, and 137 patients with LSS: mean age 50.59, range 30-71 years, 59.9% females) were retrospectively collected. Among the evaluated models, the random forest model demonstrated the highest predictive accuracy with an area under the receiver operating characteristic curve (AUROC) between model prediction and LSS diagnosis of 0.96, a sensitivity of 0.94, a specificity of 0.88, a balanced accuracy of 0.91, and a Cohen's kappa of 0.85. CONCLUSIONS: Our results indicate that ML can automate the diagnosis of LSS based on self-reported questionnaires with high accuracy. Implementation of standardized and intelligence-automated workflow may serve as a supportive diagnostic tool to streamline patient management and potentially lower health care costs.

Comparison analysis of safety outcomes and the rate of subsequent spinal procedures between interspinous spacer without decompression versus minimally invasive lumbar decompression.

INTRODUCTION: Treatment for degenerative lumbar spinal stenosis (LSS) typically begins with conservative care and progresses to minimally invasive procedures, including interspinous spacer without decompression or fusion (ISD) or minimally invasive lumbar decompression (MILD). This study examined safety outcomes and the rate of subsequent spinal procedures among LSS patients receiving an ISD versus MILD as the first surgical intervention. METHODS: 100% Medicare Standard Analytical Files were used to identify patients with an ISD or MILD (first procedure=index date) from 2017 to 2021. ISD and MILD patients were matched 1:1 using propensity score matching based on demographics and clinical characteristics. Safety outcomes and subsequent spinal procedures were captured from index date until end of follow-up. Cox models were used to analyze rates of subsequent surgical interventions, LSS-related interventions, open decompression, fusion, ISD, and MILD. Cox models were used to assess postoperative complications during follow-up and logistic regression to analyze life-threatening complications within 30 days of index procedure. RESULTS: A total of 3682 ISD and 5499 MILD patients were identified. After matching, 3614 from each group were included in the analysis (mean age=74 years, mean follow-up=20.0 months). The risk of undergoing any intervention, LSS-related intervention, open decompression, and MILD were 21%, 28%, 21%, and 81% lower among ISD compared with MILD patients. Multivariate analyses showed no significant differences in the risk of undergoing fusion or ISD, experiencing postoperative complications, or life-threatening complications (all p≥0.241) between the cohorts. CONCLUSIONS: These results showed ISD and MILD procedures have an equivalent safety profile. However, ISDs demonstrated lower rates of open decompression and MILD.

A new comprehensive MRI classification and grading system for lumbosacral central and lateral stenosis: clinical application and comparison with previous systems.

PURPOSE: The purpose of our study was to provide a novel schematized and comprehensive classification of causes and severity grading system for lumbosacral stenosis. MATERIALS AND METHODS: The MRI system proposed consisted of a severity grading scale for central and lateral (recess and foramen) stenosis, together with a schematized indication of the main causes of the disease (disc, arthritis, epidural lipomatosis, and their combinations). The system was applied to a cohort of patients from a single Institution in the last 2-years. Two radiologists evaluated all the MRIs to determine intra- and inter-observer reliability according to Cohen Kappa (Kc, for non-ordered categorical variables) and weighted Kappa (Kw, for ordered variables). Two orthopaedic surgeons clinically evaluated all patients and provided a schematic grading system with a central and lateral stenosis clinical score (CS-CS and LS-CS). Associations between ordinals were tested with chi-square test and measured with the Goodman and Kruskal's gamma index (Gi, with 95% confidence interval [95% CI]). Lastly, the most used previous MRI systems were applied, and their performances were compared to the new system proposed. RESULTS: One hundred and twelve patients were included (55 females-mean age 63.3 ± 10.7 years). An almost perfect intra-observer agreement for the assessment of central stenosis, foramen stenosis, and lateral recess stenosis was found (Kw = 0.929, 0.928, and 0.924, respectively). The inter-observer agreement was almost perfect for central stenosis and foramen stenosis and substantial for lateral recess stenosis (Kw = 0.863, 0.834, and 0.633, respectively). Whatever the aetiologies involved in central and lateral stenosis, the intra-observer agreement was perfect (all Kc = 1), whereas the inter-observer agreements were almost perfect for arthritis (Kc = 0.838) and lipomatosis (Kc = 0.955) and substantial for disc (Kc = 0.691) regarding central stenosis. The inter-observer agreement for the causes of lateral stenosis was lower and variable, ranging from perfect (lipomatosis) to fair (disc, Kc = 0.224). The grading system revealed a strong association with CS-CS for both readers, with GI = 0.671 (95% CI 0.535-0.807) and 0.603 (95% CI = 0.457-0.749), respectively. The association with MRI grading and LS-CS was moderate for foraminal stenosis and for the concomitant presence of foraminal and lateral recess stenosis, with Gi = 0.337 (95% CI 0.121-0.554) and Gi = 0.299 (95% CI 0.098-0.500), respectively. A weak association was found between lateral recess grading alone and LS-CS with Gi = 0.102 (95% CI 0.193-0.397). The new grading systems showed higher Gi for associations with clinical symptoms, compared with previous ones, both for CS-CS and LS-CS. CONCLUSIONS: A standardized visual grading system for lumbar spinal stenosis that takes into account all of the major contributing factors-including disc, arthritis, and lipomatosis, for the central canal, lateral recess, and neural foramina could be a useful and practical tool for defining the stenosis, lowering inter-observer variability, and directing the various treatment options.

[Red flags of cardiac amyloidosis in patients with spinal stenosis and yellow ligament hypertrophy]. / «Banderas rojas¼ de amiloidosis cardiaca en pacientes con estenosis de canal lumbar e hipertrofia de ligamento amarillo.

INTRODUCTION: Studies addressing the prevalence of cardiac amyloidosis (CA) among patients with spinal stenosis (SS) are lacking. The identification of the red flags (RF) of CA could lead to early detection of cases of CA. The primary objective of this study was to address the prevalence of RF of CA among patients with SS. METHODS: Transversal study including consecutive cases with SS and yellow ligament hypertrophy (YLH). A clinical assessment that included electrocardiogram, echocardiogram and urine and blood test was performed. A clinical suspicion of CA was defined by the presence of left ventricular hypertrophy plus any RF. RESULTS: One hundred and three patients with SS and YLH were assessed. The prevalence of RF was high: heart failure: 18.4%; aortic stenosis: 1.9%; carpal tunnel syndrome: 7.8%; bicipital tendon rupture: 1.9%; arterial hypotension: 17.4%; polyneuropathy symptoms: 51.5%; pseudoinfarction pattern: 3.9%; low voltages: 15.5%; conduction abnormalities: 15.5%; decreased longitudinal strain: 25.3%; apical sparing pattern: 3.9%. The 57.3% of the cohort met the CA suspicion criteria. CONCLUSION: The prevalence of RF of CA is high among patients with SS and YLH. A high proportion of patients met the CA suspicion criteria.

Association between frailty and locomotive syndrome in elderly patients with lumbar spinal stenosis: A retrospective longitudinal analysis.

AIMS: With the aging society worldwide, lumbar spinal stenosis (LSS) has become common, and its incidence has been increasing worldwide. Frailty and locomotive syndrome significantly overlap as disorders in older people. The current study aimed to validate the association between frailty and locomotive syndrome in patients with LSS. In particular, the involvement of frailty in locomotive syndrome following surgery was examined. METHODS: We retrospectively reviewed the time-course data of consecutive patients aged ≥65 years who underwent lumbar spinal surgery for LSS. The locomotive syndrome stages were determined using the 25-Question Geriatric Locomotive Function Scale: stage 0, score ≤6; stage 1, score ≥7; stage 2, score ≥16; and Stage 3, score ≥24. Robust, pre-frailty, and frailty were defined as a modified frailty index-11 score of 0, <0.21, and >0.21, respectively. RESULTS: This study included 234 patients. All patients except one were diagnosed with locomotive syndrome preoperatively. Approximately 24.8% of participants were diagnosed with frailty. LSS surgery improved locomotive syndrome regardless of frailty severity. Meanwhile, multivariable analysis indicated that frailty could significantly inhibit improvement in locomotive syndrome after surgery in old patients with LSS (estimated relative risk: 0.6; 95% confidence interval: 0.4-0.9). CONCLUSIONS: This study first assessed the association between locomotive syndrome and frailty in patients with LSS. Locomotive syndrome could be managed effectively with surgery regardless of frailty severity in old patients with LSS. However, our findings emphasize the need to screen for frailty preoperatively in this patient group. Geriatr Gerontol Int 2024; 24: 116-122.

Similar improvements in patient-reported outcomes for non-specific low back pain patients with and without lumbar spinal stenosis symptoms following a structured education and exercise therapy program.

BACKGROUND: People with nonspecific low back pain (NSLBP) can also experience overlapping symptoms of lumbar spinal stenosis (LSS), but the impact on treatment outcomes is unknown. This study investigated differences in treatment outcomes for disability, back pain intensity, and leg pain intensity following an education and exercise therapy program for NSLBP patients with and without comorbid LSS symptoms. METHODS: This was a longitudinal analysis of 655 Danish participants in the GLA:D® Back program; an education and exercise therapy program for people with persistent NSLBP. Participants were classified as having comorbid LSS symptoms based on self-report. Linear mixed models were used to assess differences in change in disability (Oswestry Disability Index [0-100]) and back and leg pain intensity (Numeric Rating Scale [0-10]) at 3-, 6-, and 12-months between those with and without LSS symptoms. RESULTS: 28% of participants reported LSS symptoms. No certain differences in change in disability or back pain intensity improvement were observed at any time-point between those with and without LSS symptoms. Participants with LSS symptoms had slightly greater improvement in leg pain intensity at 6- (-0.7, 95% CI -1.2 to -0.2) and 12-months (-0.6, 95% CI -1.2 to -0.1). CONCLUSION: Compared to those without LSS symptoms, patients with persistent NSLBP and LSS symptoms can expect similar improvements in disability and back pain intensity, and slightly greater improvements in leg pain intensity with treatment. Therefore, education and exercise therapy programs designed for NSLBP are likely helpful for those also experiencing LSS symptoms.

Low back pain improvement after cervical laminoplasty in patients without tandem lumbar stenosis.

PURPOSE: This study aimed to demonstrate the impact of lumbar spinal stenosis (LSS) on LBP after cervical laminoplasty for cervical spinal stenosis by analyzing the clinical characteristics and surgical outcomes. METHODS: This retrospective cohort study analyzed 56 consecutive patients with cervical spinal stenosis who underwent cervical laminoplasty. Data on age, sex, Japanese Orthopaedic Association (JOA) scores, JOA Back Pain Evaluation Questionnaire (BPEQ), and visual analog scale (VAS) were collected. The patients with VAS for LBP ≥ 30 or more were included and divided into two groups: without LSS [LSS (-)]or with LSS [LSS (+)]. Preoperative clinical characteristics and postoperative changes were compared between the groups. RESULTS: Preoperative VAS for LBP were 50.7 ± 16.2 mm and 59.8 ± 19.5 mm in the LSS (+) and LSS (-), respectively (p = 0.09). Patients in the LSS (-) were younger (57.6 ± 11.2 vs. 70.7 ± 8.6, p < 0.001) and showed significantly milder preoperative lumbar symptoms in terms of JOA and BPEQ. Patients in the LSS (-) group showed more postoperative changes in low back pain (18.3 ± 26.4 vs. - 8.3 ± 37.6, p = 0.005) and lumbar function (10.8 ± 25.7 vs. - 2.0 ± 22.5, p = 0.04) at BPEQ, and higher recovery in terms of VAS of LBP (23.0 ± 23.8 mm vs. 5.3 ± 25.9 mm, p = 0.008) and buttocks and low limbs (12.5 ± 35.0 mm vs. - 4.3 ± 24.4 mm, p = 0.029). Nine patients in the LSS (+) group underwent lumbar surgery at 12.8 ± 8.5 months after cervical laminoplasty. CONCLUSION: LBP improved after cervical laminoplasty in patients without lumbar stenosis.

Severity of spinal degeneration does not affect the pain reduction under continuous epidural analgesia.

PURPOSE: To outline clinical effectiveness of continuous epidural analgesia (CEA) in patients with failed back surgery syndrome (FBSS) or lumbar spinal stenosis (LSS) depending on severity of spinal degeneration. METHODS: In this retrospective cohort study, all patients with FBSS or LSS who underwent CEA within an inpatient rehabilitation program were evaluated. The pain reduction was measured by VAS on an hourly basis. Substantial pain reduction was defined as a minimal clinically important difference (MCID) > 50%. Severity of spinal degeneration, side effects and patient-specific characteristics were documented. RESULT: We included a total of 148 patients with 105 patients suffering from FBSS and 48 with LSS. The average pain reduction was - 37.6 ± 19.2 in FBSS and - 38.1 ± 17.8 in LSS group (p < .001 and p < .001, respectively). In the FBSS group, sensory deficits (p = .047) and numbness (p = .002), and in the LSS group, a severe disability measured by ODI (38.2 ± 15.4 vs. 57.3 ± 11.3, p < .001) significantly contributed to a worse outcome. The severity of the spinal degeneration and psychological disorders did not affect the pain reduction in terms of MCID. CONCLUSIONS: This study provides new evidence about CEA in the treatment of FBSS and LSS. CEA provides a significant pain reduction even under intensified physiotherapeutic exercising in patients with severe spinal degeneration and a broad variety of secondary diagnoses. Neurologic deficits in case of FBSS and severe disability in case of LSS may be risk factors for less favorable outcome.

Is dynamic spino-pelvic alignment during gait associated with lumbar function in patients with degenerative lumbar spinal stenosis?

INTRODUCTION: Static spine and pelvic posture has been reported to be associated with symptoms in patients with lumbar spinal stenosis (LSS), but it is unknown whether dynamic alignment of the spine and pelvis is associated with lumbar function in daily life. This study aims to investigate the relationship between dynamic alignment of the spine and pelvis during gait and lumbar function in daily life in patients with LSS. METHODS: We evaluated lumbar function in daily life using the Oswestry Disability Index (ODI), trunk and hip muscle strength as physical function, static spinal alignment, and dynamic spinal/pelvic alignment during gait. The relationship between the ODI score and physical function or static and dynamic alignment was examined. RESULTS: A total of 35 preoperative patients with LSS participated in this study. ODI score significantly correlated with trunk extension strength (r = -0.578, p = 0.000), hip extension strength (r = -0.472, p = 0.004), maximum spinal flexion angle during gait (r = -0.473, p = 0.004) and maximum pelvic anterior tilt angle (r = 0.510, p = 0.002). Multiple regression analysis showed that trunk extension strength (standardized ß; - 0.309), hip extension strength (standardized ß; -0.287), maximum spinal flexion angle (standardized ß; - 0.306) and maximum pelvic anterior tilt angle (standardized ß; 0.271) significantly affected the ODI score, with adjusted coefficient of determination of 0.529. CONCLUSION: The results of this study showed that the patients with LSS with weak hip or trunk extensor muscles, a greater angle of pelvic tilt or a less spinal flexion during gait had a lower lumbar function in daily life.

[Low Back Pain - When Is Surgical Therapy Promising?] / Kreuzschmerzen.

Low Back Pain - When Is Surgical Therapy Promising? Abstract. Low back pain is the number one widespread disease and leads to a high socioeconomic burden. In most cases, low back pain has a non-specific cause, which can be treated conservatively. For low back pain with specific pathoanatomical causes, surgery is usually only indicated for cases refractory to conservative measures or for patients presenting with neurological deficits or mechanical instability. Especially in patients with herniated discs, spinal canal stenosis and spondylolisthesis, surgical treatment has been shown to lead to good or very good long-term patient outcomes. However, careful patient selection and education are critical for successful postoperative patient outcome.

Characteristics associated with comorbid lumbar spinal stenosis symptoms in people with knee or hip osteoarthritis: an analysis of 9,136 good life with osteoArthritis in Denmark (GLA:D®) participants.

BACKGROUND: Previous studies have found that lumbar spinal stenosis (LSS) often co-occurs with knee or hip OA and can impact treatment response. However, it is unclear what participant characteristics may be helpful in identifying individuals with these co-occurring conditions. The aim of this cross-sectional study was to explore characteristics associated with comorbid symptoms of lumbar spinal stenosis (LSS) in people with knee or hip osteoarthritis (OA) enrolled in a primary care education and exercise program. METHODS: Sociodemographic, clinical characteristics, health status measures, and a self-report questionnaire on the presence of LSS symptoms was collected at baseline from the Good Life with osteoArthritis in Denmark primary care program for knee and hip OA. Cross-sectional associations between characteristics and the presence of comorbid LSS symptoms were assessed separately in participants with primary complaint of knee and hip OA, using domain-specific logistic models and a logistic model including all characteristics. RESULTS: A total of 6,541 participants with a primary complaint of knee OA and 2,595 participants with a primary complaint of hip OA were included, of which 40% and 50% reported comorbid LSS symptoms, respectively. LSS symptoms were associated with similar characteristics in knee and hip OA. Sick leave was the only sociodemographic variable consistently associated with LSS symptoms. For clinical characteristics, back pain, longer symptom duration and bilateral or comorbid knee or hip symptoms were also consistently associated. Health status measures were not consistently related to LSS symptoms. CONCLUSION: Comorbid LSS symptoms in people with knee or hip OA undergoing a primary care treatment program of group-based education and exercise were common and associated with a similar set of characteristics. These characteristics may help to identify people with co-occurring LSS and knee or hip OA, which can be used to help guide clinical decision-making.

Central sensitization as a predictive factor for the surgical outcome in patients with lumbar spinal stenosis: a multicenter prospective study.

PURPOSE: The impact of central sensitization (CS) on neurological symptoms and surgical outcomes in patients with lumbar spinal stenosis (LSS) remains unknown. This study aimed to investigate the influence of preoperative CS on the surgical outcomes of patients with LSS. METHODS: A total of 197 consecutive patients with LSS (mean age 69.3) who underwent posterior decompression surgery with or without fusion were included in this study. The participants completed the CS inventory (CSI) scores and the following clinical outcome assessments (COAs) preoperatively and 12 months postoperatively: the Japanese Orthopaedic Association (JOA) score for back pain, JOA back pain evaluation questionnaire, and Oswestry Disability Index (ODI). The association between preoperative CSI scores and preoperative and postoperative COAs was analyzed, and postoperative changes were statistically evaluated. RESULTS: The preoperative CSI score significantly decreased at 12 months postoperatively and was significantly correlated with all COAs preoperatively and 12 months postoperatively. Higher preoperative CSI showed worse postoperative COAs and inferior postoperative improvement rates in the JOA score, VAS score for neurological symptoms, and ODI. Multiple regression analysis demonstrated that preoperative CSI was significantly associated with postoperative low back pain (LBP), mental health, quality of life (QOL), and neurological symptoms at 12 months postoperatively. CONCLUSIONS: Preoperative CS evaluated by CSI had a significantly worse impact on surgical outcomes, including neurological symptoms, disability, and QOL, especially related to LBP and psychological factors. CSI can be used clinically as a patient-reported measure for predicting postoperative outcomes in patients with LSS.

Predictive factors for degenerative lumbar spinal stenosis: a model obtained from a machine learning algorithm technique.

BACKGROUND: Degenerative lumbar spinal stenosis (DLSS) is the most common spine disease in the elderly population. It is usually associated with lumbar spine joints/or ligaments degeneration. Machine learning technique is an exclusive method for handling big data analysis; however, the development of this method for spine pathology is rare. This study aims to detect the essential variables that predict the development of symptomatic DLSS using the random forest of machine learning (ML) algorithms technique. METHODS: A retrospective study with two groups of individuals. The first included 165 with symptomatic DLSS (sex ratio 80 M/85F), and the second included 180 individuals from the general population (sex ratio: 90 M/90F) without lumbar spinal stenosis symptoms. Lumbar spine measurements such as vertebral or spinal canal diameters from L1 to S1 were conducted on computerized tomography (CT) images. Demographic and health data of all the participants (e.g., body mass index and diabetes mellitus) were also recorded. RESULTS: The decision tree model of ML demonstrate that the anteroposterior diameter of the bony canal at L5 (males) and L4 (females) levels have the greatest stimulus for symptomatic DLSS (scores of 1 and 0.938). In addition, combination of these variables with other lumbar spine features is mandatory for developing the DLSS. CONCLUSIONS: Our results indicate that combination of lumbar spine characteristics such as bony canal and vertebral body dimensions rather than the presence of a sole variable is highly associated with symptomatic DLSS onset.

LSS-VGG16: Diagnosis of Lumbar Spinal Stenosis With Deep Learning.

STUDY DESIGN: This was a retrospective study. OBJECTION: Lumbar Spinal Stenosis (LSS) is a disease that causes chronic low back pain and can often be confused with herniated disk. In this study, a deep learning-based classification model is proposed to make LSS diagnosis quickly and automatically with an objective tool. SUMMARY OF BACKGROUND DATA: LSS is a disease that causes negative consequences such as low back pain, foot numbness, and pain. Diagnosis of this disease is difficult because it is confused with herniated disk and requires serious expertise. The shape and amount of this stenosis are very important in deciding the surgery and the surgical technique to be applied in these patients. When the spinal canal narrows, as a result of compression on these nerves and/or pressure on the vessels feeding the nerves, poor nutrition of the nerves causes loss of function and structure. Image processing techniques are applied in biomedical images such as MR and CT and high classification success is achieved. In this way, computer-aided diagnosis systems can be realized to help the specialist in the diagnosis of different diseases. METHODS: To demonstrate the success of the proposed model, different deep learning methods and traditional machine learning techniques have been studied. RESULTS: The highest classification success was obtained in the VGG16 method, with 87.70%. CONCLUSIONS: The proposed LSS-VGG16 model reveals that a computer-aided diagnosis system can be created for the diagnosis of spinal canal stenosis. In addition, it was observed that higher classification success was achieved compared with similar studies in the literature. This shows that the proposed LSS-VGG16 model will be an important resource for scientists who will work in this field.

Deep Learning Algorithm for Identifying Cervical Cord Compression Due to Degenerative Canal Stenosis on Radiography.

STUDY DESIGN: Cross-sectional study. OBJECTIVE: Validate the diagnostic accuracy of a deep-learning algorithm for cervical cord compression due to degenerative canal stenosis on radiography. SUMMARY OF BACKGROUND DATA: The diagnosis of degenerative cervical myelopathy is often delayed, resulting in improper management. Screening tools for suspected degenerative cervical myelopathy would help identify patients who require detailed physical evaluation. MATERIALS AND METHODS: Data from 240 patients (120 with cervical stenosis on magnetic resonance imaging and 120 age and sex-matched controls) were randomly divided into training (n = 198) and test (n = 42) data sets. The deep-learning algorithm, designed to identify the suspected stenosis level on radiography, was constructed using a convolutional neural network model called EfficientNetB2, and radiography and magnetic resonance imaging data from the training data set. The accuracy and area under the curve of the receiver operating characteristic curve were calculated for the independent test data set. Finally, the number of correct diagnoses was compared between the algorithm and 10 physicians using the test cohort. RESULTS: The diagnostic accuracy and area under the curve of the deep-learning algorithm were 0.81 and 0.81, respectively, in the independent test data set. The rate of correct responses in the test data set was significantly higher for the algorithm than for the physician's consensus (81.0% vs . 66.2%; P = 0.034). Furthermore, the accuracy of the algorithm was greater than that of each individual physician. CONCLUSIONS: We developed a deep-learning algorithm capable of suggesting the presence of cervical spinal cord compression on cervical radiography and highlighting the suspected levels on radiographic imaging when cord compression is identified. The diagnostic accuracy of the algorithm was greater than that of spine physicians. LEVEL OF EVIDENCE: Level IV.

Magnetic Resonance Imaging Grading Systems for Central Canal and Neural Foraminal Stenoses of the Lumbar and Cervical Spines With a Focus on the Lee Grading System.

Magnetic resonance imaging (MRI) is a standard imaging modality for diagnosing spinal stenosis, which is a common degenerative disorder in the elderly population. Standardized interpretation of spinal MRI for diagnosing and grading the severity of spinal stenosis is necessary to ensure correct communication with clinicians and to conduct clinical research. In this review, we revisit the Lee grading system for central canal and neural foraminal stenosis of the cervical and lumbar spine, which are based on the pathophysiology and radiologic findings of spinal stenosis.

A comparison between effectiveness of gluteal trigger point and epidural steroid injection in lumbosacral canal stenosis patients: a randomized clinical trial.

BACKGROUND: Lumbosacral Spinal Stenosis (LSS) is a degenerative spine disease and a major cause of pain and disability, especially in geriatrics. Primary symptom control in patients with LSS includes conservative treatment and non-surgical methods. In this study, we aimed to compare the effect of steroid injection via epidural and gluteal trigger point techniques. METHODS: Patients aged 40-75 years old who had pain and other clinical signs of spinal stenosis in the last 6 months were included in our study and divided into two groups of gluteal trigger point (TP) or epidural steroid injection (ESI). The patients were evaluated based on the visual analog scale (VAS), Roland-Morris Disability Questionnaire (RDQ), Oswestry Disability Index (ODI), and the Quebec back pain disability scales during their pre-injection period and 2 weeks after follow-ups till 8 weeks. A P value of less than 0.05 was considered significant. RESULTS: A total of 44 patients were included in our study. The TP group had a significant decrease in comparison with their follow-ups; however, in the epidural group, the significant decrease was only observed compared to the pre-injection period and the scores did not have any significant decreases after the second week regarding the ODI, RQM, and VAS scales. The TP group demonstrated significantly higher scores of decreases of ODI and Quebec score compared to the epidural group at weeks 4 and 8. Regarding RQM, the TP groups demonstrated significantly higher scores of decreases compared to the epidural group at weeks 2, 4 and 8. (p < 0.001 p = 0.008, and p < 0.001, respectively). CONCLUSION: Both epidural and TP steroid injection significantly reduced the patients' pain and improved their QoL and function; however, more satisfactory results were observed in the TP group during the patients' follow-ups, while the epidural group demonstrated only statistically significant improvement during the short-term follow-up.

Generalization of a clinical diagnosis support tool for lumbar spinal stenosis: Can the ankle brachial pressure index be replaced by palpation of the posterior tibial artery in the lumbar spinal stenosis diagnostic support tool? (DISTO project).

BACKGROUND: The Japanese Society for Spine Surgery and Related Research previously developed a diagnostic support tool for lumbar spinal stenosis (LSS-DST). Using the LSS-DST, general physicians can identify potential cases of LSS. However, in the LSS-DST, measurement of the ankle brachial pressure index (ABI) is required to exclude peripheral artery lesions in the lower limbs. We can expect further application of the LSS-DST if we can identify a simpler and easier method than ABI measurement. Therefore, in this large-scale, multicenter, cross-sectional study, we verified whether palpation of the posterior tibial (PT) artery could be used instead of ABI in the LSS-DST. METHODS: This survey was conducted at 2177 hospitals and included 28,883 participants. The sensitivity and specificity of the original LSS-DST method using the ABI and that of the LSS-DST ver2.0 with PT artery palpation were assessed to screen their ability for diagnosing LSS, using the physicians' final diagnosis based on the patients' history, physical examination and radiographic findings as the gold standard. RESULTS: The sensitivity and specificity [95%CI] of the LSS-DST were 88.2% [87.5, 88.8] and 83.9% [83.4, 84.5], respectively, whereas the sensitivity and specificity of the LSS-DST ver2.0 were 87.7% [87.0, 88.3] and 78.3% [77.7, 78.9], respectively, indicating that LSS-DST ver2.0 is a useful screening tool for LSS with good sensitivity. CONCLUSION: When the item of ABI in the LSS-DST is replaced by palpation of the PT artery (LSS-DST ver2.0), its sensitivity is maintained as a screening tool for LSS. LEVEL OF EVIDENCE: Level 3.