A Review on the Use of Artificial Intelligence in Spinal Diseases

Artificial neural networks (ANNs) have been used in a wide variety of real-world applications and it emerges as a promising field across various branches of medicine. This review aims to identify the role of ANNs in spinal diseases. Literature were searched from electronic databases of Scopus and Medline from 1993 to 2020 with English publications reported on the application of ANNs in spinal diseases. The search strategy was set as the combinations of the following keywords: “artificial neural networks,” “spine,” “back pain,” “prognosis,” “grading,” “classification,” “prediction,” “segmentation,” “biomechanics,” “deep learning,” and “imaging.” The main findings of the included studies were summarized, with an emphasis on the recent advances in spinal diseases and its application in the diagnostic and prognostic procedures. According to the search strategy, a set of 3,653 articles were retrieved from Medline and Scopus databases. After careful evaluation of the abstracts, the full texts of 89 eligible papers were further examined, of which 79 articles satisfied the inclusion criteria of this review. Our review indicates several applications of ANNs in the management of spinal diseases including (1) diagnosis and assessment of spinal disease progression in the patients with low back pain, perioperative complications, and readmission rate following spine surgery; (2) enhancement of the clinically relevant information extracted from radiographic images to predict Pfirrmann grades, Modic changes, and spinal stenosis grades on magnetic resonance images automatically; (3) prediction of outcomes in lumbar spinal stenosis, lumbar disc herniation and patient-reported outcomes in lumbar fusion surgery, and preoperative planning and intraoperative assistance; and (4) its application in the biomechanical assessment of spinal diseases. The evidence suggests that ANNs can be successfully used for optimizing the diagnosis, prognosis and outcome prediction in spinal diseases. Therefore, incorporation of ANNs into spine clinical practice may improve clinical decision making.

Cut-off Value for Body Mass Index in Predicting Surgical Success in Patients with Lumbar Spinal Canal Stenosis

STUDY DESIGN: Case-control. PURPOSE: To determine optimal cut-off value for body mass index (BMI) in predicting surgical success in patients with lumbar spinal canal stenosis (LSCS). OVERVIEW OF LITERATURE: BMI is an essential variable in the assessment of patients with LSCS. METHODS: We conducted a prospective study with obese and non-obese LSCS surgical patients and analyzed data on age, sex, duration of symptoms, walking distance, morphologic grade of stenosis, BMI, postoperative complications, and functional disability. Obesity was defined as BMI of ≥30 kg/m². Patients completed the Oswestry Disability Index (ODI) questionnaire before surgery and 2 years after surgery. Surgical success was defined as ≥30% improvement from the baseline ODI score. Receiver operating characteristic (ROC) analysis was used to estimate the optimal cut-off values of BMI to predict surgical success. In addition, correlation was assessed between BMI and stenosis grade based on morphology as defined by Schizas and colleague in total, 189 patients were eligible to enter the study. RESULTS: Mean age of patients was 61.5±9.6 years. Mean follow-up was 36±12 months. Most patients (88.4%) were classified with grades C (severe stenosis) and D (extreme stenosis). Post-surgical success was 85.7% at the 2-year follow-up. A weak correlation was observed between morphologic grade of stenosis and BMI. Rates of postoperative complications were similar between patients who were obese and those who were non-obese. Both cohorts had similar degree of improvement in the ODI at the 2-year follow-up. However, patients who were non-obese presented significantly higher surgical success than those who were obese. In ROC curve analysis, a cut-off value of ≤29.1 kg/m² for BMI in patients with LSCS was suggestive of surgical success, with 81.1% sensitivity and 82.2% specificity (area under the curve, 0.857; 95% confidence interval, 0.788–0.927). CONCLUSION: This study showed that the BMI can be considered a parameter for predicting surgical success in patients with LSCS and can be useful in clinical practice.

An Outcome Measure of Functionality and Pain in Patients with Low Back Disorder: A Validation Study of the Iranian version of Low Back Outcome Score

STUDY DESIGN: Cross-sectional study. PURPOSE: This study aimed to cross-culturally translate and validate the low back outcome score (LBOS) in Iran. OVERVIEW OF LITERATURE: Lumbar disc hernia (LDH) is the most common diagnoses of low back pain and imposes a heavy burden on both individual and society. Instruments measuring patient reported outcomes should satisfy cetain psychometric properties. METHODS: The translation and cross-cultural adaptation of the original questionnaire was performed using Beaton's guideline. A total of 163 patients with LDH were asked to respond to the questionnaire at three points in time: preoperative and twice within 1-week interval after surgery assessments. The Oswestry disabilty index (ODI) was also completed. The internal consistency, test-retest, convergent validity, and responsiveness to change were assessed. Responsiveness to change also was assessed comparing patients' pre- and postoperative scores. RESULTS: The mean age of the cohort was 49.8 years (standard deviation=10.1). The Cronbach's alpha coefficients for the LBOS at preoperative and postoperative assessments ranged from 0.77 to 0.79, indicating good internal consistency. Test-retest reliability as performed by intraclass correlation coefficient was found to be 0.82 (0.62–0.91). The instrument discriminated well between sub-groups of patients who differed in the Finneson-Cooper score. The ODI correlated strongly with the LBOS score, lending support to its good convergent validity (r=––0.83; p<0.001). Further analysis also indicated that the questionnaire was responsive to change (p<0.001). CONCLUSIONS: The Iranian version of LBOS performed well and the findings suggest that it is a valid measure of back pain treatment evaluation among LDH patients.

Decision-Making Process in Patients with Thoracolumbar and Lumbar Burst Fractures with Thoracolumbar Injury Severity and Classification Score Less than Four

STUDY DESIGN: Cross-sectional. PURPOSE: To develop a strategy to determine a sound method for decision-making based on postoperative clinical outcome satisfaction. OVERVIEW OF LITERATURE: The ideal management of thoracolumbar and lumbar burst fractures (TLBF) without neurological compromise remains controversial. METHODS: This was a prospective study. Patients with thoracolumbar injury severity and classification score (TLICS) <4 were treated nonoperatively, with bed rest and bracing until the pain decreased sufficiently to allow mobilization. Surgery was undertaken in patients with intractable pain despite an appropriate nonoperative treatment (surgery group). The Oswestry disability index (ODI) measure was observed at baseline and at the last follow-up. Clinically success was defined at least a 30% improvement from the baseline ODI scores in both the conservative and surgery groups. All case records were assessed for gender, age, residual canal and angulations at the site of the fracture in order to determine which patients benefited from surgery or conservative treatment and which did not. RESULTS: In all 113 patients with T11-L5, TLBFs were treated. The patients' mean age was 49.2 years. Patients successfully completed either nonoperative (n=99) or surgical (n=14) treatment based on ODI. Clinical examinations revealed that all of the patients had intact neurology. The mean follow-up period was 29.5 months. There was a significant difference between the two groups based on age and residual canal. The mean ODI score significantly improved for both groups (p <0.01). According to the findings, a decision matrix was proposed. CONCLUSIONS: The findings confirm that TLICS <4, age, and residual canal can be used to guide the treatment of TLBF in conservative decision-making.

Outcome Measure of Pain in Patients with Lumbar Disc Herniation: Validation Study of the Iranian version of Pain Sensitivity Questionnaire

STUDY DESIGN: Cross-sectional. PURPOSE: To translate and culturally adapt an Iranian version of the Pain Sensitivity Questionnaire (PSQ) in Iran. OVERVIEW OF LITERATURE: Instruments measuring patient reported outcomes should satisfy certain psychometric properties. METHODS: The PSQ was translated following cross-cultural adaptation guidelines. A total of 101 patients with lumbar disc herniation (LDH), and 39 healthy cases were included in the study. All participants completed the PSQ and the Pain Catastrophizing Scale (PCS). The internal consistency, test-retest reliability, known group comparison, criterion validity and item-scale correlations were assessed. RESULTS: The mean age of participants was 51.7 years. Reliability, validity and correlation of PSQ and PCS showed satisfactory results. Cronbach's alpha coefficients were 0.81 for PSQ-total, 0.82 for PSQ-minor, and 0.82 for PSQ-moderate. The intraclass correlation coefficients value was 0.84 (0.616-0.932) indicating an excellent test-retest reliability. The instrument discriminated well between sub-groups of patients who differed in a standard predictive measure of LDH surgery (the Finneson-Cooper score). Total PSQ were also significantly correlated with the total scores of the PCS, lending support to its good convergent validity. Additionally, the correlation of each item with its hypothesized domain on the PSQ indicated acceptable results, suggesting that the items had a substantial relationship with their own domains. CONCLUSIONS: The adapted Iranian PSQ is a valid and reliable questionnaire for the assessment of pain in patients with LDH.

Outcome Measure of Pain in Patients with Lumbar Disc Herniation: Validation Study of the Iranian version of Pain Sensitivity Questionnaire

STUDY DESIGN: Cross-sectional. PURPOSE: To translate and culturally adapt an Iranian version of the Pain Sensitivity Questionnaire (PSQ) in Iran. OVERVIEW OF LITERATURE: Instruments measuring patient reported outcomes should satisfy certain psychometric properties. METHODS: The PSQ was translated following cross-cultural adaptation guidelines. A total of 101 patients with lumbar disc herniation (LDH), and 39 healthy cases were included in the study. All participants completed the PSQ and the Pain Catastrophizing Scale (PCS). The internal consistency, test-retest reliability, known group comparison, criterion validity and item-scale correlations were assessed. RESULTS: The mean age of participants was 51.7 years. Reliability, validity and correlation of PSQ and PCS showed satisfactory results. Cronbach's alpha coefficients were 0.81 for PSQ-total, 0.82 for PSQ-minor, and 0.82 for PSQ-moderate. The intraclass correlation coefficients value was 0.84 (0.616-0.932) indicating an excellent test-retest reliability. The instrument discriminated well between sub-groups of patients who differed in a standard predictive measure of LDH surgery (the Finneson-Cooper score). Total PSQ were also significantly correlated with the total scores of the PCS, lending support to its good convergent validity. Additionally, the correlation of each item with its hypothesized domain on the PSQ indicated acceptable results, suggesting that the items had a substantial relationship with their own domains. CONCLUSIONS: The adapted Iranian PSQ is a valid and reliable questionnaire for the assessment of pain in patients with LDH.

Surgical Outcomes and Correlation of the Copenhagen Neck Functional Disability Scale and Modified Japanese Orthopedic Association Assessment Scales in Patients with Cervical Spondylotic Myelopathy

STUDY DESIGN: Cross-sectional. PURPOSE: Clinical outcome study comparing the Copenhagen Neck Functional Disability Scale (CNFDS) and modified Japanese orthopedic association (mJOA) assessment scales in patients with cervical spondylotic myelopathy (CSM). OVERVIEW OF LITERATURE: Comparison of instruments that measure patient-reported outcomes is needed. METHODS: A cross-sectional analysis was conducted. Ninety five patients with CSM were entered into the study and completed the CNFDS and the mJOA preoperatively and postoperatively. Correlation between the CNFDS and the mJOA was evaluated preoperatively and at the end of follow-up. Responsiveness to change of CNFDS and mJOA was also assessed. Clinical outcomes were also measured with the recovery rate of mJOA score at end of follow-up. RESULTS: The mean age of patients was 58.2 (standard deviation, SD=8.7) years. Mean follow-up was 2.1 years (range, 1 to 4 years). The mJOA correlated strongly with the CNFDS score preoperatively and postoperatively (r=-0.81 and -0.82, respectively; p<0.001). The CNFDS and the mJOA were able to detect changes after the surgery (p<0.001). The mean mJOA recovery rate was 51.8% (SD=13.1%). CONCLUSIONS: Surgery for the treatment of patients with CSM is an efficacious procedure. CNFDS and mJOA scores have a strong correlation in measuring disability among CSM patients.

Surgical Outcomes and Correlation of the Copenhagen Neck Functional Disability Scale and Modified Japanese Orthopedic Association Assessment Scales in Patients with Cervical Spondylotic Myelopathy

STUDY DESIGN: Cross-sectional. PURPOSE: Clinical outcome study comparing the Copenhagen Neck Functional Disability Scale (CNFDS) and modified Japanese orthopedic association (mJOA) assessment scales in patients with cervical spondylotic myelopathy (CSM). OVERVIEW OF LITERATURE: Comparison of instruments that measure patient-reported outcomes is needed. METHODS: A cross-sectional analysis was conducted. Ninety five patients with CSM were entered into the study and completed the CNFDS and the mJOA preoperatively and postoperatively. Correlation between the CNFDS and the mJOA was evaluated preoperatively and at the end of follow-up. Responsiveness to change of CNFDS and mJOA was also assessed. Clinical outcomes were also measured with the recovery rate of mJOA score at end of follow-up. RESULTS: The mean age of patients was 58.2 (standard deviation, SD=8.7) years. Mean follow-up was 2.1 years (range, 1 to 4 years). The mJOA correlated strongly with the CNFDS score preoperatively and postoperatively (r=-0.81 and -0.82, respectively; p<0.001). The CNFDS and the mJOA were able to detect changes after the surgery (p<0.001). The mean mJOA recovery rate was 51.8% (SD=13.1%). CONCLUSIONS: Surgery for the treatment of patients with CSM is an efficacious procedure. CNFDS and mJOA scores have a strong correlation in measuring disability among CSM patients.

Outcome Measures of Functionality, Social Interaction, and Pain in Patients with Cervical Spondylotic Myelopathy: A Validation Study for the Iranian Version of the Copenhagen Neck Functional Disability Scale

STUDY DESIGN: Cross-sectional. PURPOSE: To translate and validate the Iranian version of the Copenhagen Neck Functional Disability Scale (CNFDS). OVERVIEW OF LITERATURE: Instruments measuring patient-reported outcomes should satisfy certain psychometric properties. METHODS: Ninety-three cases of cervical spondylotic myelopathy were entered into the study and completed the CNFDS pre and postoperatively at the 6 month follow-up. The modified Japanese Orthopedic Association Score was also completed. The internal consistency, test-retest, convergent validity, construct validity (item scale correlation), and responsiveness to change were assessed. RESULTS: Mean age of the patients was 54.3 years (standard deviation, 8.9). The Cronbach alpha coefficient was satisfactory (alpha=0.84). Test-retest reliability as assessed by the intraclass correlation coefficient analysis was 0.95 (95% confidence interval, 0.92-0.98). The modified Japanese Orthopedic Association score correlated strongly with the CNFDS score, lending support to its good convergent validity (r=-0.80; p<0.001). Additionally, the correlation of each item with its hypothesized domain on the CNFDS was acceptable, suggesting that the items had a substantial relationship with their own domains. These results also indicate that the instrument was responsive to change (p<0.0001). CONCLUSIONS: The findings suggest that the Iranian version of the CNFDS is a valid measure to assess functionality, social interaction, and pain among patients with cervical spondylotic myelopathy.

Lumbar Spinal Canal Stenosis Classification Criteria: A New Tool

STUDY DESIGN: Case-control study. PURPOSE: To design a new tool for classifying lumbar spinal canal stenosis (CLSCS). OVERVIEW OF LITERATURE: Grading of patients with lumbar spinal canal stenosis (LSCS) is controversial. METHODS: The Oswestry disability index (ODI) and the neurogenic claudication outcome score (NCOS) were recorded. Four parameters, which indicate the severity of LSCS disease, including Hufschmidt-grade, grading of magnetic resonance imaging, self-paced walking test, and stenosis ratio (SR) were employed. For the SR, quartile analysis was applied for classifying LSCS and the Hufschmidt-grade was modified into a 4-grade score. An initial score was assigned to each metric based on the severity of LSCS. Using the inverse-variance weighting method, the relative weights of these domains and their categories were determined. The score for all of the cases was obtained based on their weight by summing up the points of the four variables. Quartile analysis was used and a CLSCS score was proposed. Finally, intra- and interobserver reliability, and validity were assessed. RESULTS: A total of 357 patients were studied. The final CLSCS score for each case ranged from 4 to 16.5. Based on the quartile analysis, using the new criteria set, the CLSCS score was divided into four categories: CLSCS<7 (grade 0); 7< or =CLSCS<10 (grade 1); 10< or =CLSCS<13 (grade 2); and 13< or =CLSCS< or =16.5 (grade 3). The kappa values of for the CLSCS score indicated a perfect agreement. The CLSCS was correlated with the ODI and NCOS. All patients with grade 3 CLSCS were observed in the surgical group. CONCLUSIONS: The CLSCS score can be helpful for classifying LSCS patients and in the decision-making process.

Role of the Self-Administered, Self-Reported History Questionnaire to Identify Types of Lumbar Spinal Stenosis: A Sensitivity Analysis

STUDY DESIGN: Case-control design. PURPOSE: To evaluate the role of the self-administered, self-reported history questionnaire (SSHQ) in identifying types of lumbar spinal stenosis (LSS). OVERVIEW OF LITERATURE: Diagnosis of types of LSS is controversial. METHODS: A total of 235 patients with LSS were asked to respond to the SSHQ. All of these patients recovered following surgical treatment. The classification of LSS patients was based on history, physical examinations, and imaging studies. It is considered to be the gold standard. Radicular and neurogenic claudication types of LSS were based on the SSHQ developed by Konno et al. Two categories of LSS were determined based on the SSHQ tool and gold standard. Finally, a sensitivity analysis was carried out to evaluate the diagnostic value of the SSHQ. RESULTS: The mean age of patients was 59.4 years. According to the criteria for gold standard, patients were diagnosed with the radicular type (n=103), and neurogenic claudication type (n=132). The questionnaire had desirable sensitivity, specificity, and accuracy in categorizing the two types of LSS: 97.8%, 66.6%, and 96.8% for the radicular type, and 97.0%, 80.0%, and 95.7% for the neurogenic claudication type. CONCLUSIONS: Our findings indicate that the SSHQ is a reliable and a valid measure and it may be a clinical diagnosis support tool for identifying patients with two types of LSS.

outcomes of surgical treatment of recurrent lumbar disk herniation with discectomy alone and discectomy with posterolateral interbody fusion

Recurrent lumbar disk herniation [RLDH] is one of the major causes of failure of standard discectomy. The optimal treatment method for RLDH is controversial. In the current study, we aimed to compare the clinical and functional outcomes of treating RLDH with discectomy alone and discectomy associated with posterolateral interbody fusion [PLIF]. There were 41 patients with RLHD after primary discectomy in the current retrospective study. Patients were assigned to 2 groups based on the surgical method: discectomy alone [17 patients] and discectomy with PLIF [21 patients]. At the final visit the following variables were measured and compared between groups: the back and radicular pain intensity using visual analogue scale [VAS], functional outcome using oswestry low back pain disability scale [ODI], return to previous work and complication. Patients were followed for 13.9 +/- 2.8 and 15 +/- 3 months in discectomy alone and discectomy with PLIF groups, retrospectively. Complete fusion was achieved in 24 patients of PLIF group. The back pain intensity was the same; however the radicular pain intensity was significantly lower in PLIF group [1.5 +/- 0.9 V.s 2.3 +/- 1; p=0.017]. Also, the mean of ODI scale was the same. 82.3% of patients in discectomy group and 87.5% of patients in PLIF group returned to previous work and the difference was not significant. One patient in discectomy group and 2 patients in PLIF group developed temporary neurological deficit which disappeared after 3 months. Although both discectomy alone and discectomy with PLIF were associated with favorable mid-term results in treating patients with RLDH, however, the authors recommend using discectomy with PLIF for lower radicular pain

[Evaluation of the thoracolumbar injury classification system [TLICS] in thoracolumbar fractures]

Due to refer patients with thoracolumbar fractures, and the importance of treatment results in these patients, type of treatment, prediction of treatment outcome, the shortcomings of the current scoring In these patients, reports of success of scoring Thoracolumbar Injury Classification System [TLICS] and lack of experience in Iran, Therefore, this study was conducted to determine the score of TLICS and evaluate the success of this method in patients who referred to Imam Hossein hospital during 2008-2010. Descriptive analysis study was conducted. All patients who had undergone surgery due to the thoracolumbar fractures were studied. Clinical and radiologic data, classifying the trauma according to the Frankel classification, the Magerl/AO classification, and the TLICS score for fractures were evaluated. The results were statistically analyzed by Fisher's exact test and correlation coefficient. The study was conducted on 67 eligible patients during two years. The average age of the patients was 30 +/- 11 years [range 19-60 years], and the average follow-up time was 18 months [range 6-24 months]. 63 [94%] of patients had a TLICS score? 4. The TLICS score ranged from 2 to 9 [average of 6.5]. Frankel classification status remained unchanged in 61 of cases and 6 of them had some improvement. A statistic correlation was established between the neurologic status and the TLICS score [P<0.004]. An elevated correlation coefficient were found between the AO type fracture and Frankel classification status with the TLICS score [r=0.8] and [r=0.78] respectively. It seems that the TLICS score is a good approach in determining the severity of thoracolumbar fractures and the prediction of surgical management. Our results will need to be confirmed with further clinical trial studies