Machine Learning Models for Predicting Disability and Pain Following Lumbar Disc Herniation Surgery.

Importance: Lumber disc herniation surgery can reduce pain and disability. However, a sizable minority of individuals experience minimal benefit, necessitating the development of accurate prediction models. Objective: To develop and validate prediction models for disability and pain 12 months after lumbar disc herniation surgery. Design, Setting, and Participants: A prospective, multicenter, registry-based prognostic study was conducted on a cohort of individuals undergoing lumbar disc herniation surgery from January 1, 2007, to May 31, 2021. Patients in the Norwegian Registry for Spine Surgery from all public and private hospitals in Norway performing spine surgery were included. Data analysis was performed from January to June 2023. Exposures: Microdiscectomy or open discectomy. Main Outcomes and Measures: Treatment success at 12 months, defined as improvement in Oswestry Disability Index (ODI) of 22 points or more; Numeric Rating Scale (NRS) back pain improvement of 2 or more points, and NRS leg pain improvement of 4 or more points. Machine learning models were trained for model development and internal-external cross-validation applied over geographic regions to validate the models. Model performance was assessed through discrimination (C statistic) and calibration (slope and intercept). Results: Analysis included 22 707 surgical cases (21 161 patients) (ODI model) (mean [SD] age, 47.0 [14.0] years; 12 952 [57.0%] males). Treatment nonsuccess was experienced by 33% (ODI), 27% (NRS back pain), and 31% (NRS leg pain) of the patients. In internal-external cross-validation, the selected machine learning models showed consistent discrimination and calibration across all 5 regions. The C statistic ranged from 0.81 to 0.84 (pooled random-effects meta-analysis estimate, 0.82; 95% CI, 0.81-0.84) for the ODI model. Calibration slopes (point estimates, 0.94-1.03; pooled estimate, 0.99; 95% CI, 0.93-1.06) and calibration intercepts (point estimates, -0.05 to 0.11; pooled estimate, 0.01; 95% CI, -0.07 to 0.10) were also consistent across regions. For NRS back pain, the C statistic ranged from 0.75 to 0.80 (pooled estimate, 0.77; 95% CI, 0.75-0.79); for NRS leg pain, the C statistic ranged from 0.74 to 0.77 (pooled estimate, 0.75; 95% CI, 0.74-0.76). Only minor heterogeneity was found in calibration slopes and intercepts. Conclusion: The findings of this study suggest that the models developed can inform patients and clinicians about individual prognosis and aid in surgical decision-making.

Predicting the outcome of persistent sciatica using conditioned pain modulation: 1-year results from a prospective cohort study.

Background and aims Recovery in patients hospitalised with severe sciatica is unpredictable. Prognostic tools to aid clinicians in the early identification of patients at risk of developing chronic sciatic pain are warranted. Conditioned pain modulation (CPM) is a psychophysical measure of the endogenous pain modulatory pathways. Several studies have suggested CPM as a potentially important predictive biomarker for the development of chronic pain. The aim of the study was to determine whether CPM effect in patients still suffering from leg pain 6 weeks after hospital discharge for severe sciatica is associated with persistent leg pain at 12 months. A potential association would suggest that measuring CPM effect could be a valuable prognostic tool in the hospital management of sciatica. Methods A prospective cohort study in which CPM effect was measured 6 weeks after hospital discharge following an acute admission with sciatica as the main complaint. The impact of CPM effect on the outcome was analysed using logistic regression. The outcome measured was self-reported leg pain score of ≥1 in the past week on a 0-10 numeric rating scale (NRS) at 12 months post discharge. Results A total of 111 patients completed the entire study, 51 of whom received non-randomised surgical treatment. Crude and confounder adjusted analyses showed no significant association between CPM effect and leg-pain measured at 12 months, crude Odds Ratio 0.87, 95% CI 0.7-1.1, p = 0.23. Conclusions Our results suggest that CPM assessment has limited prognostic value for the long-term outcome in severe sciatica when measured 6 weeks after hospital discharge. Implications The present study adds important knowledge concerning the limited clinical use of late CPM testing in sciatica patients. The heterogeneity in patients, the wide range of treatments received and a generally favourable outcome are factors that may affect CPM's clinical value as a prognostic factor for severe sciatica.

Lumbar spine surgery across 15 years: trends, complications and reoperations in a longitudinal observational study from Norway.

BACKGROUND: Studies from different Western countries have reported a rapid increase in spinal surgery rates, an increase that exceeds by far the growing incidence rates of spinal disorders in the general population. There are few studies covering all lumbar spine surgery and no previous studies from Norway. OBJECTIVES: The purpose of this study was to investigate trends in all lumbar spine surgery in Norway over 15 years, including length of hospital stay, and rates of complications and reoperations. DESIGN: A longitudinal observational study over 15 years using hospital patient administrative data and sociodemographic data from the National Registry in Norway. SETTING AND PARTICIPANTS: Patients aged ≥18 years discharged from Norwegian public hospitals between 1999 and 2013. OUTCOME MEASURES: Annual rates of simple (microsurgical discectomy, decompression) and complex surgical procedures (fusion, disc prosthesis) in the lumbar spine. RESULTS: The rate of lumbar spine surgery increased by 54%, from 78 (95% CI (75 to 80)) to 120 (107 to 113) per 100 000, from 1999 to 2013. More men had simple surgery whereas more women had complex surgery. Among elderly people over 75 years, lumbar surgery increased by a factor of five during the 15-year period. The rates of complications were low, but increased from 0.7% in 1999 to 2.4% in 2013. CONCLUSIONS: There was a substantial increase in lumbar spine surgery in Norway from 1999 to 2013, similar to trends in other Western world countries. The rise in lumbar surgery among elderly people represents a significant workload and challenge for health services, given our aging population.

The Rates of LSS Surgery in Norwegian Public Hospitals: A Threefold Increase From 1999 to 2013.

STUDY DESIGN: Retrospective administrative database study. OBJECTIVE: To assess temporal and regional trends, and length of hospital stay, in lumbar spinal stenosis (LSS) surgery in Norwegian public hospitals from 1999 to 2013. SUMMARY OF BACKGROUND DATA: Studies from several countries have reported increasing rates of LSS surgery over the last decades. No such data have been presented from Norway. METHODS: A database consisting of discharges from all Norwegian public hospitals was established. Inclusion criteria were discharges including a surgical procedure of lumbar spinal decompression and/or fusion in combination with an International Statistical Classification of Diseases and Related Health Problems, 10th Revision diagnosis of Spinal Stenosis (M48.0) or Other Spondylosis with Radiculopathy (M47.2), and a patient age of 18 years or older. Discharges with diagnoses indicating deformity, that is, spondylolisthesis or scoliosis were not included. RESULTS: During the 15-year period, 19,543 discharges were identified. The annual rate of decompressions increased from 10.7 to 36.2 and fusions increased from 2.5 to 4.4 per 100,000 people of the general Norwegian population. The proportion of fusion surgery decreased from 19.3% to 10.9%. Among individuals older than 65 years, the annual rate of surgery per 10,000, including both decompressions and fusions, more than quadrupled from 40.2 to 170.3. The regional variation was modest, differing with a factor of 1.4 between the region with the highest and the lowest surgical rates. The mean length of hospital stay decreased from 11.0 (standard deviation 8.0) days in 1999 to 5.0 (4.6) days in 2013, but patients who received fusion surgery stayed on average 3.6 days longer than those who received decompression only. CONCLUSION: The rate of LSS surgery more than tripled in Norway from 1999 to 2013. The mean length of hospital stay was reduced from 11 to 5 days. LEVEL OF EVIDENCE: N/A.

Prognostic Factors for Persistent Leg-Pain in Patients Hospitalized With Acute Sciatica.

STUDY DESIGN: Prospective cohort study. OBJECTIVE: To identify potential prognostic factors for persistent leg-pain at 12 months among patients hospitalized with acute severe sciatica. SUMMARY OF BACKGROUND DATA: The long-term outcome for patients admitted to hospital with sciatica is generally unfavorable. Results concerning prognostic factors for persistent sciatica are limited and conflicting. METHODS: A total of 210 patients acutely admitted to hospital for either surgical or nonsurgical treatment of sciatica were consecutively recruited and received a thorough clinical and radiographic examination in addition to responding to a comprehensive questionnaire. Follow-up assessments were done at 6 weeks, 6 months, and 12 months. Potential prognostic factors were measured at baseline and at 6 weeks. The impact of these factors on leg-pain was analyzed by multiple linear regression modeling. RESULTS: A total of 151 patients completed the entire study, 93 receiving nonrandomized surgical treatment. The final multivariate models showed that the following factors were significantly associated with leg-pain at 12 months: high psychosocial risk according to the Örebro Musculosceletal Pain Questionnaire (unstandardized beta coefficient 1.55, 95% confidence interval [CI] 0.72-2.38, P < 0.001), not receiving surgical treatment (1.11, 95% CI 0.29-1.93, P = 0.01), not actively employed upon admission (1.47, 95% CI 0.63-2.31, P < 0.01), and self-reported leg-pain recorded 6 weeks posthospital admission (0.49, 95% CI 0.34-0.63, P < 0.001). Interaction analysis showed that the Örebro Musculosceletal Pain Questionnaire had significant prognostic value only on the nonsurgically treated patients (3.26, 95% CI 1.89-4.63, P < 0.001). CONCLUSION: The results suggest that a psychosocial screening tool and the implementation of a 6-week postadmission follow-up has prognostic value in the hospital management of severe sciatica. LEVEL OF EVIDENCE: 2.