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.

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.

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.

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.