Development and Validation of a Prediction Model for Pain and Functional Outcomes After Lumbar Spine Surgery

Multicenter external validation of prediction models for clinical outcomes after spinal fusion for lumbar degenerative disease

BACKGROUND

Clinical prediction models (CPM), such as the SCOAP-CERTAIN tool, can be utilized to enhance decision-making for lumbar spinal fusion surgery by providing quantitative estimates of outcomes, aiding surgeons in assessing potential benefits and risks for each individual patient. External validation is crucial in CPM to assess generalizability beyond the initial dataset. This ensures performance in diverse populations, reliability and real-world applicability of the results. Therefore, we externally validated the tool for predictability of improvement in oswestry disability index (ODI), back and leg pain (BP, LP).

METHODS

Prospective and retrospective data from multicenter registry was obtained. As outcome measure minimum clinically important change was chosen for ODI with ≥ 15-point and ≥ 2-point reduction for numeric rating scales (NRS) for BP and LP 12 months after lumbar fusion for degenerative disease. We externally validate this tool by calculating discrimination and calibration metrics such as intercept, slope, Brier Score, expected/observed ratio, Hosmer-Lemeshow (HL), AUC, sensitivity and specificity.

RESULTS

We included 1115 patients, average age 60.8 ± 12.5 years. For 12-month ODI, area-under-the-curve (AUC) was 0.70, the calibration intercept and slope were 1.01 and 0.84, respectively. For NRS BP, AUC was 0.72, with calibration intercept of 0.97 and slope of 0.87. For NRS LP, AUC was 0.70, with calibration intercept of 0.04 and slope of 0.72. Sensitivity ranged from 0.63 to 0.96, while specificity ranged from 0.15 to 0.68. Lack of fit was found for all three models based on HL testing.

CONCLUSIONS

Utilizing data from a multinational registry, we externally validate the SCOAP-CERTAIN prediction tool. The model demonstrated fair discrimination and calibration of predicted probabilities, necessitating caution in applying it in clinical practice. We suggest that future CPMs focus on predicting longer-term prognosis for this patient population, emphasizing the significance of robust calibration and thorough reporting.

Worse Pain and Disability at Presentation Predicts Greater Improvement in Pain, Disability, and Mental Health in Patients Undergoing Minimally Invasive Transforaminal Lumbar Interbody Fusion for Degenerative Spondylolisthesis

STUDY DESIGN

Retrospective Review.

OBJECTIVE

To assess the impact of preoperative pain and disability on patient-reported outcome measures (PROMs) following minimally invasive transforaminal lumbar interbody fusion (MI-TLIF) for degenerative spondylolisthesis.

SUMMARY OF BACKGROUND DATA

Varying preoperative symptom severity in lumbar fusion patients alters perceptions of surgical success.

METHODS

Degenerative spondylolisthesis patients undergoing elective, primary, single-level MI-TLIF were stratified by preoperative symptom severity: Mild (VAS-B<7/ODI<50), Moderate (VAS-B≥7/ODI<50 or VAS-B<7/ODI≥50), and Severe (VAS-B≥7/ODI≥50). PROMs, Patient-reported Outcomes Measurement Information System-Physical Function (PROMIS-PF), ODI, VAS-B, VAS-Leg (VAS-L), and 9-item Patient Health Questionnaire (PHQ-9) were compared at baseline, 6 weeks, and final follow-up (μ=16.3±8.8 mo). Postoperative PROMs, magnitudes of improvement, and minimal clinically important difference (MCID) achievement rates were compared between cohorts through multivariable regression.

RESULTS

A total of 177 patients were included. Acute postoperative pain and narcotic consumption were highest in the severe cohort (P≤0.003). All preoperative PROMs worsened from mild to severe cohorts (P<0.001). All PROMs continued to be significantly different between cohorts at 6 weeks and final follow-up, with the worst scores in the Severe cohort (P≤0.003). At 6 weeks, all cohorts improved in ODI, VAS-B, VAS-L, and PHQ-9 (P≤0.003), with the Moderate cohort also improving in PROMIS-PF (P=0.017). All Cohorts improved across PROMs at the final follow-up (P≤0.044). Magnitudes of improvement in ODI, VAS-B, and PHQ-9 increased with worsening preoperative symptom severity (P≤0.042). The Moderate and Severe cohorts demonstrated higher MCID achievement in ODI, VAS-B, and PHQ-9 rates than the Mild cohort.

CONCLUSIONS

Despite preoperative pain and disability severity, patients undergoing MI-TLIF for degenerative spondylolisthesis report significant improvement in physical function, pain, disability, and mental health postoperatively. Patients with increasing symptom severity continued to report worse severity postoperatively compared with those with milder symptoms preoperatively but were more likely to report larger improvements and achieve clinically meaningful improvement in disability, pain, and mental health.

Impact of preoperative clinical state on 2-year clinical outcomes following degenerative lumbar scoliosis surgery

To assess the preoperative clinical state's impact on clinical outcomes after surgery for degenerative lumbar scoliosis (DLS) based on the minimal clinically important difference (MCID). Preoperative and follow-up (FU) scores in each Scoliosis Research Society-22 (SRS-22) domain were compared with age- and sex-matched normative references. At baseline, patients were classified by differences from normative values in four groups: Worst, Severe, Poor, and Moderate. At 2 years postoperative FU, patients were divided into four groups (Worst Severe Poor Asymptomatic) based on the difference in MCID between postoperative and normal values. The changes in MCID were considered as the criterion for surgical efficacy. In addition, we calculated the classification of preoperative and FU clinical symptom severity in each domain in same patient. The distinction among curve types was also performed based on the SRS-Schwab classification. A total of 123 patients were included. During FU, patients with more severe preoperative clinical symptoms were more likely to achieve clinical changes (>1 MCID, p < 0.05), but the rate of reaching "asymptomatic" was lower (p < 0.05). Kendall's tau-b correlation analysis found that preoperative clinical severity was correlated with clinical changes category in Activity (Tau-b = 0.252; p = 0.002), Pain (Tau-b = 0.230; p = 0.005), Appearance (Tau-b = 0.307; p < 0.001), and Mental (Tau-b = 0.199; p = 0.016), and it also was correlated with FU clinical severity in Activity (Tau-b = 0.173; p = 0.023), Pain (Tau-b = 0.280; p < 0.001), and Mental (Tau-b = 0.349; p < 0.001). There was a correlation between preoperative clinical severity and FU SRS-22 score outcomes. Patients with severe preoperative clinical symptoms can experience better treatment outcomes during FU, but it is also more difficult to recover to the normal reference.

Does Preoperative Back Pain Impact Patient-reported Outcomes in Patients Undergoing Minimally Invasive Transforaminal Lumbar Interbody Fusion for Isthmic Spondylolisthesis?

STUDY DESIGN

Retrospective review.

OBJECTIVE

To determine postoperative clinical outcomes in patients undergoing minimally invasive (MIS) transforaminal lumbar interbody fusion (TLIF) for isthmic spondylolisthesis (IS).

BACKGROUND

Few studies have examined the postoperative clinical trajectory in patients undergoing MIS-TLIF specifically for IS.

METHODS

Patients were separated into two cohorts based on the previously defined Visual Analog Scale (VAS) back pain (BP) for severe pain: VAS-BP <7 and VAS-BP ≥7. Patient-reported outcome measures (PROMs) of Patient-Reported Outcomes Measurement Information System-physical function (PF), 12-item Short Form (SF-12) Physical/Mental Component Score, Patient Health Questionnaire-9, VAS-BP, VAS leg pain, and Oswestry Disability Index were collected preoperatively and up to 2-year postoperatively. Minimum clinically important difference (MCID) was calculated through previously defined thresholds.

RESULTS

A total of 160 patients were recorded, with 58 patients in the VAS-BP <7 cohort. The VAS-BP <7 cohort demonstrated significant improvement in all PROMs at one or more postoperative time points. The VAS-BP ≥7 demonstrated significant improvement at 3 or more postoperative time points in all PROMs except for SF-12 Mental Component Score. The VAS-BP <7 cohort reported significantly superior preoperative and postoperative PROMs in all domains, except for SF-12 Physical Component Score. The VAS-BP ≥7 cohort had higher MCID achievement rates at one or more time points in multiple PROMs.

CONCLUSION

Patients undergoing MIS-TLIF for IS demonstrated significant postoperative improvement in PF, mental function, pain, and disability outcomes independent of preoperative severity of BP. Patients with lower preoperative BP demonstrated superior outcomes in PF, mental function, pain, and disability. However, patients with greater preoperative BP achieved higher rates of MCID in mental function, BP, and disability outcomes. Patients with greater severity of preoperative BP undergoing MIS-TLIF for IS may experience greater rates of clinically relevant improvement in mental function, BP, and disability outcomes.

Impact of preoperative mental health diagnosis on postoperative opioid use patterns in spine fusion surgery: A systematic literature review

Opioids are frequently prescribed for patients undergoing procedures such as spinal fusion surgery for the management of chronic back pain. However, the association between a preoperative mental health illness, such as depression or anxiety, and opioid use patterns after spinal fusion surgery remain unclear. Therefore, we performed a systematic literature review in accordance with PRISMA guidelines to identify articles from the PubMed Database that analyzed the relationship between preoperative mental health illness and postoperative opioid usage after spinal fusion surgery on June 1, 2023. The Methodological Index for Nonrandomized Studies (MINORS) was utilized to evaluate the quality of included articles. Seven studies with 139,580 patients and a mean MINORS score of 18 ± 0.5 were included in qualitative synthesis. The most common spine surgery performed was lumbar fusion (59 %) and the mean age across studies ranged from 50 to 62 years. The range of postoperative opioid usage patterns analyzed ranged from 1 to 24 months. The majority of studies (6/7; 86 %) reported that a preoperative diagnosis of mental health illness was associated with increased opioid dependence after spinal fusion surgery. Preoperative use of opioids for protracted periods was shown to be associated with postoperative chronic opioid dependence. Consensus findings suggest that having a preoperative diagnosis of a mental health illness such as depression or anxiety is associated with increased postoperative opioid use after spinal fusion surgery. Patient comorbidities, including diagnoses of mental health illness, must be considered by the spine surgeon in order to reduce rates of postoperative opioid dependence.

Do Six-Week Postoperative Patient-Reported Outcomes Predict Long-Term Clinical Outcomes Following Lumbar Decompression?

BACKGROUND

Little research has been done to evaluate the prognostic value of short-term postoperative patient-reported outcomes (PROs) on long-term PROs following lumbar decompression (LD). We evaluated the prognostic value of short-term PROs on long-term PROs through 2 years after LD.

METHODS

A single spine surgeon database was retrospectively queried for patients undergoing primary LD with 6-week postoperative PROs reported. The demographics, perioperative traits, and preoperative, 6-month, 1-year, and 2-year PROs were recorded. The PROs included the visual analog scale (VAS) for back pain, VAS for leg pain, PRO measure information system for physical function (PROMIS-PF), and Oswestry disability index. Two-step multivariate linear regression was performed to determine the predictive value of 6-week PROs for the 6-month, 1-year, and 2-year PROs.

RESULTS

A total of 277 patients were included. The 6-week Oswestry disability index, VAS for leg pain, and 9-item patient health questionnaire (PHQ-9) are all positive predictors for their respective outcomes at 6 months. Additionally, the 6-week PROMIS-PF was a negative predictor of the 6-month PHQ-9. The 6-week PROMIS-PF positively predicted the PROMIS-PF through 1 year, and the PHQ-9 was a positive predictor of the PHQ-9 at 1 and 2 years postoperatively.

CONCLUSIONS

The 6-week postoperative PROs are predictive of the same outcomes at 6 months, the PROMIS-PF is predictive through 1 year, and the PHQ-9 is predictive through 2 years. Determining the predictive value of early postoperative PROs can be helpful in understanding the likely postoperative trajectory following LD and informing patient expectations.

Assessment of the External Validity of Dialogue Support for Predicting Lumbar Spine Surgery Outcomes in a US Cohort

STUDY DESIGN

External validation using prospectively collected data.

OBJECTIVES

To determine the model performance of "Dialogue Support" (DS) in predicting outcomes after lumbar spine surgery.

SUMMARY OF BACKGROUND DATA

To help clinicians discuss risk versus benefit with patients considering lumbar fusion surgery, DS has been made available online. As DS was created using a Swedish sample, there is a need to study how well DS performs in alternative populations.

PATIENTS AND METHODS

Preoperative data from patients enrolled in the Quality Outcomes Database were entered into DS. The probability for each patient to report satisfaction, achieve success (leg pain improvement ≥3), or have no leg pain 12 months after surgery was extracted and compared with their actual 12-month postoperative data. The ability of DS to identify patients in the Quality Outcomes Database who report satisfaction, achieve success, or have no leg pain 12 months after surgery was determined using Receiver operating characteristic curve analysis, goodness-of-fit tests, and calibration plots.

RESULTS

There was a significant improvement in all outcomes in 23,928 cases included in the analysis from baseline to 12 months postoperative. Most (84%) reported satisfaction, 67% achieved success, and 44% were pain-free 12 months postoperative. Receiver operating characteristic analysis showed that DS had a low ability to predict satisfaction [area under the curve (AUC) = 0.606], success (AUC = 0.546), and being pain-free (AUC = 0.578) at 12 months postoperative; poor fit for satisfaction (<0.001) and being pain-free ( P = 0.004), but acceptable fit for success ( P = 0.052). Calibration plots showed underestimation for satisfaction and success, but acceptable estimates for being pain-free.

CONCLUSION

DS is not directly transferable to predict satisfaction and success after lumbar surgery in a US population. This may be due to differences in patient characteristics, weights of the variables included, or the exclusion of unknown variables associated with outcomes. Future studies to better understand and improve the transferability of these models are needed.

Performance of the streamlined quality outcomes database web-based calculator: internal and external validation

BACKGROUND CONTEXT

With an increasing number of web-based calculators designed to provide the probabilities of an individual achieving improvement after lumbar spine surgery, there is a need to determine the accuracy of these models.

PURPOSE

To perform an internal and external validation study of the reduced Quality Outcomes Database web-based Calculator (QOD-Calc).

STUDY DESIGN

Observational longitudinal cohort.

PATIENT SAMPLE

Patients enrolled study-wide in Quality Outcomes Database (QOD) and patients enrolled in DaneSpine at a single institution who had elective lumbar spine surgery with baseline data to complete QOD-Calc and 12-month postoperative data.

OUTCOME MEASURES

Oswestry Disability Index (ODI), Numeric Rating Scales (NRS) for back and leg pain, EuroQOL-5D (EQ-5D).

METHODS

Baseline data elements were entered into QOD-Calc to determine the probability for each patient having Any Improvement and 30% Improvement in NRS leg pain, back pain, EQ-5D and ODI. These probabilities were compared with the actual 12-month postop data for each of the QOD and DaneSpine cases. Receiver-operating characteristics analyses were performed and calibration plots created to assess model performance.

RESULTS

24,755 QOD cases and 8,105 DaneSpine lumbar cases were included in the analysis. QOD-Calc had acceptable to outstanding ability (AUC: 0.694-0.874) to predict Any Improvement in the QOD cohort and moderate to acceptable ability (AUC: 0.658-0.747) to predict 30% Improvement. QOD-Calc had acceptable to exceptional ability (AUC: 0.669-0.734) to predict Any improvement and moderate to exceptional ability (AUC: 0.619-0.862) to predict 30% Improvement in the DaneSpine cohort. AUCs for the DaneSpine cohort was consistently lower that the AUCs for the QOD validation cohort.

CONCLUSION

QOD-Calc performs well in predicting outcomes in a patient population that is similar to the patients that was used to develop it. Although still acceptable, model performance was slightly worse in a distinct population, despite the fact that the sample was more homogenous. Model performance may also be attributed to the low discrimination threshold, with close to 90% of cases reporting Any Improvement in outcome. Prediction models may need to be developed that are highly specific to the characteristics of the population.

Clinical Decision Support System Used in Spinal Disorders: Scoping Review

BACKGROUND

Spinal disorders are highly prevalent worldwide with high socioeconomic costs. This cost is associated with the demand for treatment and productivity loss, prompting the exploration of technologies to improve patient outcomes. Clinical decision support systems (CDSSs) are computerized systems that are increasingly used to facilitate safe and efficient health care. Their applications range in depth and can be found across health care specialties.

OBJECTIVE

This scoping review aims to explore the use of CDSSs in patients with spinal disorders.

METHODS

We used the Joanna Briggs Institute methodological guidance for this scoping review and reported according to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) statement. Databases, including PubMed, Embase, Cochrane, CINAHL, Web of Science, Scopus, ProQuest, and PsycINFO, were searched from inception until October 11, 2022. The included studies examined the use of digitalized CDSSs in patients with spinal disorders.

RESULTS

A total of 4 major CDSS functions were identified from 31 studies: preventing unnecessary imaging (n=8, 26%), aiding diagnosis (n=6, 19%), aiding prognosis (n=11, 35%), and recommending treatment options (n=6, 20%). Most studies used the knowledge-based system. Logistic regression was the most commonly used method, followed by decision tree algorithms. The use of CDSSs to aid in the management of spinal disorders was generally accepted over the threat to physicians' clinical decision-making autonomy.

CONCLUSIONS

Although the effectiveness was frequently evaluated by examining the agreement between the decisions made by the CDSSs and the health care providers, comparing the CDSS recommendations with actual clinical outcomes would be preferable. In addition, future studies on CDSS development should focus on system integration, considering end user's needs and preferences, and external validation and impact studies to assess effectiveness and generalizability.

TRIAL REGISTRATION

OSF Registries osf.io/dyz3f; https://osf.io/dyz3f.

Elaboration and validation of a novelty nomogram for the prognostication of anxiety susceptibility in individuals suffering from low back pain

Low back pain (LBP) constitutes a distressing emotional ordeal and serves as a potent catalyst for adverse emotional states, notably anxiety. We dedicated to discerning methodologies for identifying patients who are predisposed to heightened levels of anxiety and pain. A self-assessment questionnaire was administered to patients afflicted with LBP. The pain scores were subjected to analysis in conjunction with anxiety scores, and a clustering procedure was executed using the scientific k-means methodology. Subsequently, six machine learning algorithms, including Logistics Regression (LR), K-Nearest Neighbor (KNN), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGB), were employed. Next, five pertinent variables were identified, namely Age, Course, Body Mass Index (BMI), Education, and Marital status. Furthermore, a LR model was utilized to construct a nomogram, which was subsequently subjected to assessment for discrimination, calibration, and evaluation of its clinical utility. As a result, 599 questionnaires were valid (effective rate: 99 %). The correlation analysis revealed a significant association between anxiety and pain scores (r = 0.31, P < 0.001). LBP patients could be divided into two clusters, Cluster1 had higher pain scores (P < 0.05) and SAS scores (P < 0.001). The proposed nomogram demonstrated an area under the receiver operating characteristics curve (ROC) of 0.841 (95 %CI: 0.804-0.878) and 0.800 (95 %CI: 0.733-0.867) in the training and test groups, respectively. Briefly, the established nomogram has demonstrated remarkable proficiency in discerning individuals afflicted with LBP who are at a heightened risk of experiencing anxiety.

Racial Disparities in Opioid Use and Lumbar Spine Surgery for Chronic Pain and in Pain and Function Over 3 Years: A Retrospective Cohort Study

This study aims to compare treatments and outcomes among Black and White patients with chronic low back pain in the United States. A retrospective cohort study was conducted within a pain research registry, including 1,443 participants with up to 3 years of follow-up. Pain treatments were measured at quarterly research encounters using reported current opioid use and prior lumbar spine surgery. Pain intensity and functional disability were also measured quarterly with a numerical rating scale and the Roland-Morris Disability Questionnaire, respectively. Longitudinal data were analyzed with generalized estimating equations, including multivariable models to measure temporal trends and adjust for potential confounders. The mean baseline age of participants was 53.5 years (SD, 13.1 years); 1,074 (74.4%) were female, and 260 (18.0%) were Black. In longitudinal multivariable analyses, Black participants reported more frequent current opioid use (odds ratio, 1.40; 95% confidence interval [CI], 1.03-1.91; P = .03) and less frequent lumbar spine surgery (odds ratio, .45; 95% CI, .28-.72; P < .001). Black participants also reported greater pain intensity (mean, 6.6; 95% CI, 6.3-6.9 vs mean, 5.6; 95% CI, 5.4-5.8; P < .001) and functional disability (mean, 15.3; 95% CI, 14.6-16.0 vs mean, 13.8; 95% CI, 13.2-14.3; P = .002). Racial disparities were clinically important (risk ratio = 1.28 and risk ratio = .49, respectively, for opioid use and surgery; and d = .46 and d = .24, respectively, for pain and function). Racial disparities in pain and function also widened over time. Thus, barriers to guideline-adherent and specialized pain care among Black patients may affect pain and function outcomes. Greater efforts are needed to address the observed racial disparities. PERSPECTIVE: Widening racial disparities in pain and function over time indicate that new approaches to chronic pain management are needed in the United States. Considering race as a social framework represents an emerging strategy for planning and improving pain treatment services for Black patients.

Utility of preoperative comorbidity burden on PROMIS outcomes after lumbar decompression: Cohort matched analysis

The influence of Charlson Comorbidity Index (CCI) burden on Patient-Reported Outcomes Measurement Information System (PROMIS) outcomes following lumbar decompression (LD) is limited. The objective of this study is to evaluate CCI burden impact on PROMIS outcomes. Retrospective review of elective LD excluding revision or surgeries for infectious, malignant, or traumatic reasons. Demographics and PROMIS scores collected preoperatively and postoperatively up to 2 years included: PROMIS-Physical Function (PF)/Sleep Disturbance (SD)/Pain Interference (PI)/Anxiety (A), VR-12 Physical/Mental Health Composite scores (VR-12 PCS/MCS)/Oswestry Disability Index (ODI). Patients were divided into two groups based on their preoperative CCI score <3 (mild) or ≥4 (moderate to severe). Descriptive statistical analysis and MCID achievement rate calculations were conducted. A total of 182 patients were included: 93 CCI < 3 and 88 CCI ≥ 4. No significant differences were reported across preoperative PROMIS/legacy PROMs or final follow-up (p > 0.05, all). At 6-weeks, VR-12 PCS and ΔPROM scores indicated improved physician function in the CCI < 3 group (p = 0.020 and p = 0.040, respectively). Significant PROMIS-A ΔPROM score at final post-op was noted for CCI < 3 group (p = 0.026). MCID achievement demonstrated no significant differences for PROMIS outcomes and legacy PROMs. Results demonstrated that PROMIS outcomes were not impacted by a greater baseline comorbidity burden. At 6-weeks, the physical function scores were improved for the lower CCI group, and at final reported less anxiety. Our data suggests that comorbidity burden has a limited effect on PROMIS and legacy outcomes in patients undergoing LD.

Implications of Preoperative Depression for Lumbar Spine Surgery Outcomes: A Systematic Review and Meta-Analysis

Importance

Comorbid depression is common among patients with degenerative lumbar spine disease. Although a well-researched topic, the evidence of the role of depression in spine surgery outcomes remains inconclusive.

Objective

To investigate the association between preoperative depression and patient-reported outcome measures (PROMs) after lumbar spine surgery.

Data Sources

A systematic search of PubMed, Cochrane Database of Systematic Reviews, Embase, Scopus, PsychInfo, Web of Science, and ClinicalTrials.gov was performed from database inception to September 14, 2023.

Study Selection

Included studies involved adults undergoing lumbar spine surgery and compared PROMs in patients with vs those without depression. Studies evaluating the correlation between preoperative depression and disease severity were also included.

Data Extraction and Synthesis

All data were independently extracted by 2 authors and independently verified by a third author. Study quality was assessed using Newcastle-Ottawa Scale. Random-effects meta-analysis was used to synthesize data, and I2 was used to assess heterogeneity. Metaregression was performed to identify factors explaining the heterogeneity.

Main Outcomes and Measures

The primary outcome was the standardized mean difference (SMD) of change from preoperative baseline to postoperative follow-up in PROMs of disability, pain, and physical function for patients with vs without depression. Secondary outcomes were preoperative and postoperative differences in absolute disease severity for these 2 patient populations.

Results

Of the 8459 articles identified, 44 were included in the analysis. These studies involved 21 452 patients with a mean (SD) age of 57 (8) years and included 11 747 females (55%). Among these studies, the median (range) follow-up duration was 12 (6-120) months. The pooled estimates of disability, pain, and physical function showed that patients with depression experienced a greater magnitude of improvement compared with patients without depression, but this difference was not significant (SMD, 0.04 [95% CI, -0.02 to 0.10]; I2 = 75%; P = .21). Nonetheless, patients with depression presented with worse preoperative disease severity in disability, pain, and physical function (SMD, -0.52 [95% CI, -0.62 to -0.41]; I2 = 89%; P < .001), which remained worse postoperatively (SMD, -0.52 [95% CI, -0.75 to -0.28]; I2 = 98%; P < .001). There was no significant correlation between depression severity and the primary outcome. A multivariable metaregression analysis suggested that age, sex (male to female ratio), percentage of comorbidities, and follow-up attrition were significant sources of variance.

Conclusions and Relevance

Results of this systematic review and meta-analysis suggested that, although patients with depression had worse disease severity both before and after surgery compared with patients without depression, they had significant potential for recovery in disability, pain, and physical function. Further investigations are needed to examine the association between spine-related disability and depression as well as the role of perioperative mental health treatments.

Association Between Patient Reported Outcomes Measurement Information System Physical Function With Postoperative Pain, Narcotics Consumption, and Patient-Reported Outcome Measures Following Lumbar Microdiscectomy

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

To determine association between preoperative Patient-Reported Outcomes Measurement Information System Physical Function (PROMIS-PF) scores with postoperative pain, narcotics consumption, and patient-reported outcome measures (PROMs) following single-level lumbar microdiscectomy.

METHODS

Consecutive patients who underwent single-level lumbar microdiscectomy were identified from May 2017-May 2020. Patients were grouped by their preoperative PROMIS-PF scores: mild disability (score≥40), moderate disability (score 30-39.9), and severe disability (score<30). Preoperative PROMIS-PF subgroups were tested for association with inpatient postoperative pain, total inpatient narcotics consumption, time to narcotic use cessation as well as improvements in postoperative PROMIS-PF, ODI, VAS-Leg Pain, VAS-Back Pain, SF-12 Physical Component Score (PCS), SF-12 Mental Component Score (MCS) at 2-, 6-, 12-weeks, 6-month, 1-year, 2-year follow-up.

RESULTS

A total of 127 patients were included. Patients with greater disability reported higher inpatient maximum Visual Analog Scale (VAS) pain scores (P = .023) and total inpatient narcotics consumption (P = .008) but no difference in time to narcotic cessation after surgery (P = .373). However, patients with greater preoperative disability also demonstrated greater improvement from baseline in PROMIS-PF, ODI, SF-12 PCS, and SF-12 MCS at 2-week follow-up (P < .05). These higher improvements from baseline for patients with greater preoperative disability were sustained for PROMIS-PF, ODI, and VAS-Leg Pain at 2-year follow-up (P < .05).

CONCLUSIONS

Patients with greater preoperative disability, as measured by PROMIS-PF, had increased inpatient postoperative pain and narcotics consumption, but also higher improvement from baseline in long-term PROMs. This data can be utilized for patient counseling and setting expectations.

Development and temporal validation of clinical prediction models for 1-year disability and pain after lumbar decompressive surgery. The Norwich Lumbar Surgery Predictor (development version)

PURPOSE

To identify clinical predictors and build prediction models for 1-year patient-reported outcomes measures (PROMs) after lumbar decompressive surgery for disc herniation or spinal stenosis.

METHODS

The study included 1835 cases, with or without additional single-level fusion, from a single centre from 2008 through 2020. General linear models imputed with 37 clinical variables identified 18 significant 1-year PROM predictors for retention in development models. Interaction of surgical indication with each predictor was tested. Temporal validation was conducted at the same centre on cases through 2021. R2 was used to measure goodness-of-fit, and area under curve (AUC) used to measure classification to a satisfactory symptom state (Oswestry Disability Index (ODI) ≤ 22; back or leg pain ≤ 30 out of 100).

RESULTS

A total 1228 (67%) had complete data for inclusion in model development. Predictors of ODI were baseline PROMs (ODI, back pain, leg pain), work status, condition duration, previous lumbar operation, multiple-joint osteoarthritis, female, diabetes, current smoker, rheumatic disorder, lower limb arthroplasty, mobility aided, provider status, facet cyst, scoliosis, and age, with BMI significantly associated with stenosis. Temporal validation (n = 188) found the ODI model R2 was 0.29 (95% confidence intervals (CI) 0.18-0.40) and AUC was 0.74 (95% CI 0.67-0.81). Back and leg pain models had lower R2 (0.12-0.14) and AUC (0.68-0.69) values.

CONCLUSION

Important PROM predictors are baseline PROMs, specific co-morbidities, work status, condition duration, previous lumbar operation, female, and smoking status. The ODI model predicted the likelihood of achieving a satisfactory state of both disability and pain.

Relationship Between Comorbidity Burden and Short-Term Outcomes Across 4680 Consecutive Spinal Fusions

OBJECTIVE

Preoperative management requires the identification and optimization of modifiable medical comorbidities, though few studies isolate comorbid status from related patient-level variables. This study evaluates Charlson Comorbidity Index (CCI)-an easily derived measure of aggregate medical comorbidity-to predict outcomes from spinal fusion surgery. Coarsened exact matching is employed to control for key patient characteristics and isolate CCI.

METHODS

We retrospectively assessed 4680 consecutive patients undergoing single-level, posterior-only lumbar fusion at a single academic center. Logistic regression evaluated the univariate relationship between CCI and patient outcomes. Coarsened exact matching generated exact demographic matches between patients with high comorbid status (CCI >6) or no medical comorbidities (matched n = 524). Patients were matched 1:1 on factors associated with surgical outcomes, and outcomes were compared between matched cohorts. Primary outcomes included surgical complications, discharge status, 30- and 90-day risk of readmission, emergency department (ED) visits, reoperation, and mortality.

RESULTS

Univariate regression of increasing CCI was significantly associated with non-home discharge, as well as 30- and 90-day readmission, ED visits, and mortality (all P < 0.05). Subsequent isolation of comorbidity between otherwise exact-matched cohorts found comorbid status did not affect readmissions, reoperations, or mortality; high CCI score was significantly associated with non-home discharge (OR = 2.50, P < 0.001) and 30-day (OR = 2.44, P = 0.02) and 90-day (OR = 2.29, P = 0.008) ED evaluation.

CONCLUSIONS

Comorbidity, measured by CCI, did not increase the risk of readmission, reoperation, or mortality. Single-level, posterior lumbar fusions may be safe in appropriately selected patients regardless of comorbid status. Future studies should determine whether CCI can guide discharge planning and postoperative optimization.

Clinical and radiomics feature-based outcome analysis in lumbar disc herniation surgery

BACKGROUND

Low back pain is a widely prevalent symptom and the foremost cause of disability on a global scale. Although various degenerative imaging findings observed on magnetic resonance imaging (MRI) have been linked to low back pain and disc herniation, none of them can be considered pathognomonic for this condition, given the high prevalence of abnormal findings in asymptomatic individuals. Nevertheless, there is a lack of knowledge regarding whether radiomics features in MRI images combined with clinical features can be useful for prediction modeling of treatment success. The objective of this study was to explore the potential of radiomics feature analysis combined with clinical features and artificial intelligence-based techniques (machine learning/deep learning) in identifying MRI predictors for the prediction of outcomes after lumbar disc herniation surgery.

METHODS

We included n = 172 patients who underwent discectomy due to disc herniation with preoperative T2-weighted MRI examinations. Extracted clinical features included sex, age, alcohol and nicotine consumption, insurance type, hospital length of stay (LOS), complications, operation time, ASA score, preoperative CRP, surgical technique (microsurgical versus full-endoscopic), and information regarding the experience of the performing surgeon (years of experience with the surgical technique and the number of surgeries performed at the time of surgery). The present study employed a semiautomatic region-growing volumetric segmentation algorithm to segment herniated discs. In addition, 3D-radiomics features, which characterize phenotypic differences based on intensity, shape, and texture, were extracted from the computed magnetic resonance imaging (MRI) images. Selected features identified by feature importance analyses were utilized for both machine learning and deep learning models (n = 17 models).

RESULTS

The mean accuracy over all models for training and testing in the combined feature set was 93.31 ± 4.96 and 88.17 ± 2.58. The mean accuracy for training and testing in the clinical feature set was 91.28 ± 4.56 and 87.69 ± 3.62.

CONCLUSIONS

Our results suggest a minimal but detectable improvement in predictive tasks when radiomics features are included. However, the extent of this advantage should be considered with caution, emphasizing the potential of exploring multimodal data inputs in future predictive modeling.

Machine Learning Applications in Spine Surgery

This literature review sought to identify and evaluate the current applications of artificial intelligence (AI)/machine learning (ML) in spine surgery that can effectively guide clinical decision-making and surgical planning. By using specific keywords to maximize search sensitivity, a thorough literature research was conducted in several online databases: Scopus, PubMed, and Google Scholar, and the findings were filtered according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 46 studies met the requirements and were included in this review. According to this study, AI/ML models were sufficiently accurate with a mean overall value of 74.9%, and performed best at preoperative patient selection, cost prediction, and length of stay. Performance was also good at predicting functional outcomes and postoperative mortality. Regression analysis was the most frequently utilized application whereas deep learning/artificial neural networks had the highest sensitivity score (81.5%). Despite the relatively brief history of engagement with AI/ML, as evidenced by the fact that 77.5% of studies were published after 2018, the outcomes have been promising. In light of the Big Data era, the increasing prevalence of National Registries, and the wide-ranging applications of AI, such as exemplified by ChatGPT (OpenAI, San Francisco, California), it is highly likely that the field of spine surgery will gradually adopt and integrate AI/ML into its clinical practices. Consequently, it is of great significance for spine surgeons to acquaint themselves with the fundamental principles of AI/ML, as these technologies hold the potential for substantial improvements in overall patient care.

The Effectiveness of a Mindfulness-Based Intervention Integrated with Physical Therapy (MIND-PT) for Postsurgical Rehabilitation After Lumbar Surgery: A Protocol for a Randomized Controlled Trial as Part of the Back Pain Consortium (BACPAC) Research Program

BACKGROUND

Improving pain management for persons with chronic low back pain (LBP) undergoing surgery is an important consideration in improving patient-centered outcomes and reducing the risk of persistent opioid use after surgery. Nonpharmacological treatments, including physical therapy and mindfulness, are beneficial for nonsurgical LBP through complementary biopsychosocial mechanisms, but their integration and application for persons undergoing surgery for LBP have not been examined. This study (MIND-PT) is a multisite randomized trial that compares an enriched pain management (EPM) pathway that integrates physical therapy and mindfulness vs usual-care pain management (UC) for persons undergoing surgery for LBP.

DESIGN

Participants from military treatment facilities will be enrolled before surgery and individually randomized to the EPM or UC pain management pathways. Participants assigned to EPM will receive presurgical biopsychosocial education and mindfulness instruction. After surgery, the EPM group will receive 10 sessions of physical therapy with integrated mindfulness techniques. Participants assigned to the UC group will receive usual pain management care after surgery. The primary outcome will be the pain impact, assessed with the Pain, Enjoyment, and General Activity (PEG) scale. Time to opioid discontinuation is the main secondary outcome.

SUMMARY

This trial is part of the National Institutes of Health Helping to End Addiction Long-term (HEAL) initiative, which is focused on providing scientific solutions to the opioid crisis. The MIND-PT study will examine an innovative program combining nonpharmacological treatments designed to improve outcomes and reduce opioid overreliance in persons undergoing lumbar surgery.

Barriers and Facilitators to Implementing Patient-Reported Outcome Monitoring in Gastrointestinal Surgery

INTRODUCTION

More than 30% of patients experience complications after major gastrointestinal (GI) surgery, many of which occur after discharge when patients and families must assume responsibility for monitoring. Patient-reported outcomes (PROs) have been proposed as a tool for remote monitoring to identify deviations in recovery, and recognize and manage complications earlier. This study's objective was to characterize barriers and facilitators to the use of PROs as a patient monitoring tool following GI surgery.

METHODS

We conducted semistructured interviews with GI surgery patients and clinicians (surgeons, nurses, and advanced practitioners). Patients and clinicians were asked to describe their experience using a PRO monitoring system in three surgical oncology clinics. Using a phenomenological approach, research team dyads independently coded the transcripts using an inductively developed codebook and the constant comparative approach with differences reconciled by consensus.

RESULTS

Ten patients and five clinicians participated in the interviews. We identified four overarching themes related to functionality, workflow, meaningfulness, and actionability. Functionality refers to barriers faced by clinicians and patients in using the PRO technology. Workflow represents problematic integration of PROs into the clinical workflow and need for setting expectations with patients. Meaningfulness refers to lack of patient and clinician understanding of the impact of PROs on patient care. Finally, actionability reflects barriers to follow-up and practical use of PRO data.

CONCLUSIONS

While use of PRO systems for postoperative patient monitoring have expanded, significant barriers persist for both patients and clinicians. Implementation enhancements are needed to optimize functionality, workflow, meaningfulness, and actionability.

Perioperative Predictors in Patients Undergoing Lateral Lumbar Interbody Fusion for Minimum Clinically Important Difference Achievement

OBJECTIVE

To identify perioperative predictors of minimum clinically important difference (MCID) for patients undergoing lateral lumbar interbody fusion (LLIF) for the patient-reported outcome measures (PROMs) of Patient-Reported Outcomes Measurement Information System Physical Function (PROMIS-PF), visual analog scale (VAS) back, VAS leg, Oswestry Disability Index (ODI), and Patient Health Questionnaire-9 (PHQ-9).

METHODS

Patients undergoing LLIF were identified through retrospective review of a single-surgeon database. Overall MCID achievement was determined as the number of unique patients achieving ΔPROM thresholds of PROMIS-PF = 4.5, VAS back = 2.1, VAS leg = 2.8, ODI = 14.9, and PHQ-9 = 3.0 over a 2-year postoperative period. Univariate and multivariable logistic regression were used to determine perioperative predictors for MCID achievement.

RESULTS

Two-hundred and ninety patients were identified. For PROMIS-PF MCID achievement, increased preoperative PROMIS-PF and postoperative day (POD) 1 VAS pain were significant negative predictors. For VAS back, primary fusion with revision decompression was a negative predictor, whereas increased preoperative VAS back score was a positive predictor of MCID achievement. For VAS leg, increased preoperative VAS leg score was a positive predictor. For ODI, increased POD 0 VAS pain score was a negative predictor, whereas increased preoperative ODI was a positive predictor. For PHQ-9, increased preoperative PHQ-9 score was a positive predictor.

CONCLUSIONS

In patients undergoing LLIF, perioperative predictors for MCID achievement were highly dependent on PROM. Preoperative PROM was the most consistent perioperative predictor for achieving MCID. Increased acute postoperative pain and primary fusion after failed index decompression were significant predictors of failing to achieve MCID. Surgeons may use these findings in prognostication and management of postoperative expectations.

Predictors of poor outcome following lumbar spinal fusion surgery: a prospective observational study to derive two clinical prediction rules using British Spine Registry data

PURPOSE

Lumbar spinal fusion surgery (LSFS) is common for lumbar degenerative disorders. The objective was to develop clinical prediction rules to identify which patients are likely to have a favourable outcome to inform decisions regarding surgery and rehabilitation.

METHODS

A prospective observational study recruited 600 (derivation) and 600 (internal validation) consecutive adult patients undergoing LSFS for degenerative lumbar disorder through the British Spine Registry. Definition of good outcome (6 weeks, 12 months) was reduction in pain intensity (Numerical Rating Scale, 0-10) and disability (Oswestry Disability Index, ODI 0-50) > 1.7 and 14.3, respectively. Linear and logistic regression models were fitted and regression coefficients, Odds ratios and 95% CIs reported.

RESULTS

Lower BMI, higher ODI and higher leg pain pre-operatively were predictive of good disability outcome, higher back pain was predictive of good back pain outcome, and no previous surgery and higher leg pain were predictive of good leg pain outcome; all at 6 weeks. Working and higher leg pain were predictive of good ODI and leg pain outcomes, higher back pain was predictive of good back pain outcome, and higher leg pain was predictive of good leg pain outcome at 12 months. Model performance demonstrated reasonable to good calibration and adequate/very good discrimination.

CONCLUSIONS

BMI, ODI, leg and back pain and previous surgery are important considerations pre-operatively to inform decisions for surgery. Pre-operative leg and back pain and work status are important considerations to inform decisions for management following surgery. Findings may inform clinical decision making regarding LSFS and associated rehabilitation.

Nomogram for predicting the unfavourable outcomes of percutaneous endoscopic transforaminal discectomy for lumbar disc herniation: a retrospective study

Objective

To investigate and integrate multiple independent risk factors to establish a nomogram for predicting the unfavourable outcomes of percutaneous endoscopic transforaminal discectomy (PETD) for lumbar disc herniation (LDH).

Methods

From January 2018 to December 2019, a total of 425 patients with LDH undergoing PETD were included in this retrospective study. All patients were divided into the development and validation cohort at a ratio of 4:1. Univariate and multivariate logistic regression analyses were used to investigate the independent risk factors associated with the clinical outcomes of PETD for LDH in the development cohort, and a prediction model (nomogram) was established to predict the unfavourable outcomes of PETD for LDH. In the validation cohort, the nomogram was validated by the concordance index (C-index), calibration curve, and decision curve analysis (DCA).

Results

29 of 340 patients showed unfavourable outcomes in the development cohort, and 7 of 85 patients showed unfavourable outcomes in the validation cohort. Body mass index (BMI), course of disease (COD), protrusion calcification (PC), and preoperative lumbar epidural steroid injection (LI) were independent risk factors associated with the unfavourable outcomes of PETD for LDH and were identified as predictors for the nomogram. The nomogram was validated by the validation cohort and showed high consistency (C-index = 0.674), good calibration and high clinical value.

Conclusions

The nomogram based on patients' preoperative clinical characteristics, including BMI, COD, LI and PC, can be used to accurately predict the unfavourable outcomes of PETD for LDH.

Machine Learning Assisting the Prediction of Clinical Outcomes following Nucleoplasty for Lumbar Degenerative Disc Disease

BACKGROUND

Lumbar degenerative disc disease (LDDD) is a leading cause of chronic lower back pain; however, a lack of clear diagnostic criteria and solid LDDD interventional therapies have made predicting the benefits of therapeutic strategies challenging. Our goal is to develop machine learning (ML)-based radiomic models based on pre-treatment imaging for predicting the outcomes of lumbar nucleoplasty (LNP), which is one of the interventional therapies for LDDD.

METHODS

The input data included general patient characteristics, perioperative medical and surgical details, and pre-operative magnetic resonance imaging (MRI) results from 181 LDDD patients receiving lumbar nucleoplasty. Post-treatment pain improvements were categorized as clinically significant (defined as a ≥80% decrease in the visual analog scale) or non-significant. To develop the ML models, T2-weighted MRI images were subjected to radiomic feature extraction, which was combined with physiological clinical parameters. After data processing, we developed five ML models: support vector machine, light gradient boosting machine, extreme gradient boosting, extreme gradient boosting random forest, and improved random forest. Model performance was measured by evaluating indicators, such as the confusion matrix, accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC), which were acquired using an 8:2 allocation of training to testing sequences.

RESULTS

Among the five ML models, the improved random forest algorithm had the best performance, with an accuracy of 0.76, a sensitivity of 0.69, a specificity of 0.83, an F1 score of 0.73, and an AUC of 0.77. The most influential clinical features included in the ML models were pre-operative VAS and age. In contrast, the most influential radiomic features had the correlation coefficient and gray-scale co-occurrence matrix.

CONCLUSIONS

We developed an ML-based model for predicting pain improvement after LNP for patients with LDDD. We hope this tool will provide both doctors and patients with better information for therapeutic planning and decision-making.

Predicting patient-reported outcomes following lumbar spine surgery: development and external validation of multivariable prediction models

BACKGROUND

This study aimed to develop and externally validate prediction models of spinal surgery outcomes based on a retrospective review of a prospective clinical database, uniquely comparing multivariate regression and random forest (machine learning) approaches, and identifying the most important predictors.

METHODS

Outcomes were change in back and leg pain intensity and Core Outcome Measures Index (COMI) from baseline to the last available postoperative follow-up (3-24 months), defined as minimal clinically important change (MCID) and continuous change score. Eligible patients underwent lumbar spine surgery for degenerative pathology between 2011 and 2021. Data were split by surgery date into development (N = 2691) and validation (N = 1616) sets for temporal external validation. Multivariate logistic and linear regression, and random forest classification and regression models, were fit to the development data and validated on the external data.

RESULTS

All models demonstrated good calibration in the validation data. Discrimination ability (area under the curve) for MCID ranged from 0.63 (COMI) to 0.72 (back pain) in regression, and from 0.62 (COMI) to 0.68 (back pain) in random forests. The explained variation in continuous change scores spanned 16%-28% in linear, and 15%-25% in random forests regression. The most important predictors included age, baseline scores on the respective outcome measures, type of degenerative pathology, previous spinal surgeries, smoking status, morbidity, and duration of hospital stay.

CONCLUSIONS

The developed models appear robust and generalisable across different outcomes and modelling approaches but produced only borderline acceptable discrimination ability, suggesting the need to assess further prognostic factors. External validation showed no advantage of the random forest approach.

Early postoperative step count and walking time have greater impact on lower limb fracture outcomes than load-bearing metrics

INTRODUCTION

Weight-bearing protocols for rehabilitation of lower extremity fractures are the gold standard despite not being data-driven. Additionally, current protocols are focused on the amount of weight placed on the limb, negating other patient rehabilitation behaviors that may contribute to outcomes. Wearable sensors can provide insight into multiple aspects of patient behavior through longitudinal monitoring. This study aimed to understand the relationship between patient behavior and rehabilitation outcomes using wearable sensors to identify the metrics of patient rehabilitation behavior that have a positive effect on 1-year rehabilitation outcomes.

METHODS

Prospective observational study on 42 closed ankle and tibial fracture patients. Rehabilitation behavior was monitored continuously between 2 and 6 weeks post-operative using a gait monitoring insole. Metrics describing patient rehabilitation behavior, including step count, walking time, cadence, and body weight per step, were compared between patient groups of excellent and average rehabilitation outcomes, as defined by the 1-year Patient Reported Outcome Measure Physical Function t-score (PROMIS PF). A Fuzzy Inference System (FIS) was used to rank metrics based on their impact on patient outcomes. Additionally, correlation coefficients were calculated between patient characteristics and principal components of the behavior metrics.

RESULTS

Twenty-two patients had complete insole data sets, and 17 of which had 1-year PROMIS PF scores (33.7 ± 14.5 years of age, 13 female, 9 in Excellent group, 8 in Average group). Step count had the highest impact ranking (0.817), while body weight per step had a low impact ranking (0.309). No significant correlation coefficients were found between patient or injury characteristics and behavior principal components. General patient rehabilitation behavior was described through cadence (mean of 71.0 steps/min) and step count (logarithmic distribution with only ten days exceeding 5,000 steps/day).

CONCLUSION

Step count and walking time had a greater impact on 1-year outcomes than body weight per step or cadence. The results suggest that increased activity may improve 1-year outcomes for patients with lower extremity fractures. The use of more accessible devices, such as smart watches with step counters combined with patient reported outcome measures may provide more valuable insights into patient rehabilitation behaviors and their effect on rehabilitation outcomes.

Magnetic resonance spectroscopy (MRS) identification of chemically painful lumbar discs leads to improved 6-, 12-, and 24-month outcomes for discogenic low back pain surgeries

PURPOSE

MRS was shown to reliably quantify relative levels of degenerative pain biomarkers, differentiating painful versus non-painful discs in patients with chronic discogenic low back pain (DLBP), and this correlates with surgical success rates. We now report results based on more patients and longer follow-up.

METHODS

Disc MRS was performed in DLBP patients who subsequently received lumbar surgery. Custom post-processing (NOCISCAN-LS®; Aclarion Inc.) calculated disc-specific NOCISCORES® that reflect relative differences in degenerative pain biomarkers for diagnosing chemically painful discs. Outcomes in 78 patients were evaluated using Oswestry Disability Index (ODI) scores. Surgical success (≥ 15-point ODI improvement) was compared between surgeries that were "Concordant" (Group C) versus "Discordant" (Group D) with NOCISCORE-based diagnosis for painful discs.

RESULTS

Success rates were higher for Group C versus Group D: 6 months (88% vs. 62%; p = 0.01), 12 months (91% vs. 56%; p < 0.001), and 24 months (85% vs. 63%; p = 0.07). Success rates for Group C surgeries were also higher than Group D surgeries in a variety of sub-group comparisons. Group C had a greater reduction in ODI from pre-operative to follow-up than Group D [absolute change (% change), (p)]: 6 months: - 35 (- 61%) versus - 23 (- 39%), (p < 0.05); 12 months: - 39 (- 69%) versus - 22 (- 39%), (p < 0.01); and 24 months:  - 38 (- 66%) versus - 26 (- 48%), (p < 0.05).

CONCLUSION

More successful, sustained outcomes were obtained when surgically treating chemically painful discs identified by NOCISCAN-LS post-processed disc MRS exams. Results suggest that NOCISCAN-LS provides a valuable new diagnostic tool to help clinicians better select treatment levels.

Patient-reported outcomes after posterior surgical stabilization for thoracolumbar junction fractures: A pilot study with combined patient-reported outcome measure methodology

Background

Thoracolumbar junction fractures (TLJFs) attract controversy for several parameters, including surgery versus conservative treatment, fusion versus stabilization, open versus percutaneous surgery, construct length, and downstream metalwork extraction.

Aims and Objectives

The aim of this pilot study was to assess the effectiveness of surgical treatment in patients with burst (AO Classification Type A4) TLJFs using patient-reported outcome measures (PROMs) and evaluate and compare different PROMs in this clinical scenario.

Materials and Methods

Patient records of consecutive patients who underwent posterior stabilization surgery for TLJFs were retrospectively reviewed. Data were collected on demographics, medical and social history, neurological examination, and postoperative complications. Telephone interviews and a combined PROM methodology (Numerical Rating Scale [NRS], EuroQol [EQ]-5D-5L, and Oswestry Disability Index [ODI]) were utilized to assess the effectiveness of intervention. Descriptive statistics were used to analyze exposure variables and outcome measures. Spearman's rank correlation was used for the outcome measures.

Results

Thirteen patients were included. The mean age was 42 ± 16 years; the male: female ratio was 8:5; the mean follow-up was 18.9 ± 6.4 months. The mean NRS score was 3.3 ± 2.5, in line with a median score of 2 (2) on EQ-5D-5L pain/discomfort scale. Statistically significant correlations were found between several PROMs: pain-EQ-5D-5L and NRS (rs = 0.8, P = 0.002), pain-EQ-5D-5L and ODI (rs = 0.8, P = 0.001), usual anxiety/depression-EQ-5D-5L, and ODI (rs = 0.7, P = 0.008).

Conclusion

A combined PROM methodology showed supportive evidence for safety and efficacy in the surgical stabilization of burst TLJFs. This alleviated significant pain and prevented neurological deficit and major disability. The preliminary widespread correlation between these PROMs supports further larger studies of their combined use in clinical practice, to measure the outcomes of spine trauma patients.

Let’s Get Physical! A Comprehensive Review of Pre- and Post-Surgical Interventions Targeting Physical Activity to Improve Pain and Functional Outcomes in Spine Surgery Patients

The goal of this comprehensive review was to synthesize the recent literature on the efficacy of perioperative interventions targeting physical activity to improve pain and functional outcomes in spine surgery patients. Overall, research in this area does not yet permit definitive conclusions. Some evidence suggests that post-surgical interventions may yield more robust long-term outcomes than preoperative interventions, including large effect sizes for disability reduction, although there are no studies directly comparing these surgical approaches. Integrated treatment approaches that include psychosocial intervention components may supplement exercise programs by addressing fear avoidance behaviors that interfere with engagement in activity, thereby maximizing the short- and long-term benefits of exercise. Efforts should be made to test brief, efficient programs that maximize accessibility for surgical patients. Future work in this area should include both subjective and objective indices of physical activity as well as investigating both acute postoperative outcomes and long-term outcomes.

Cost consequence analysis of waiting for lumbar disc herniation surgery

The economic repercussions of waiting for lumbar disc surgery have not been well studied. The primary goal of this study was to perform a cost-consequence analysis of patients receiving early vs late surgery for symptomatic disc herniation from a societal perspective. Secondarily, we compared patient factors and patient-reported outcomes. This is a retrospective analysis of prospectively collected data from the CSORN registry. A cost-consequence analysis was performed where direct and indirect costs were compared, and different outcomes were listed separately. Comparisons were made on an observational cohort of patients receiving surgery less than 60 days after consent (short wait) or 60 days or more after consent (long wait). This study included 493 patients with surgery between January 2015 and October 2021 with 272 patients (55.2%) in the short wait group and 221 patients (44.8%) classified as long wait. There was no difference in proportions of patients who returned to work at 3 and 12-months. Time from surgery to return to work was similar between both groups (34.0 vs 34.9 days, p = 0.804). Time from consent to return to work was longer in the longer wait group corresponding to an additional $11,753.10 mean indirect cost per patient. The short wait group showed increased healthcare usage at 3 months with more emergency department visits (52.6% vs 25.0%, p < 0.032), more physiotherapy (84.6% vs 72.0%, p < 0.001) and more MRI (65.2% vs 41.4%, p < 0.043). This corresponded to an additional direct cost of $518.21 per patient. Secondarily, the short wait group had higher baseline NRS leg, ODI, and lower EQ5D and PCS. The long wait group had more patients with symptoms over 2 years duration (57.6% vs 34.1%, p < 0.001). A higher proportion of patients reached MCID in terms of NRS leg pain at 3-month follow up in the short wait group (84.0% vs 75.9%, p < 0.040). This cost-consequence analysis of an observational cohort showed decreased costs associated with early surgery of $11,234.89 per patient when compared to late surgery for lumbar disc herniation. The early surgery group had more severe symptoms with higher healthcare utilization. This is counterbalanced by the additional productivity loss in the long wait group, which likely have a more chronic disease. From a societal economic perspective, early surgery seems beneficial and should be promoted.

Disparities in Elective Spine Surgery for Medicaid Beneficiaries: A Systematic Review

STUDY DESIGN

Systematic review.

OBJECTIVES

We sought to synthesize the literature investigating the disparities that Medicaid patients sustain with regards to 2 types of elective spine surgery, lumbar fusion (LF) and anterior cervical discectomy and fusion (ACDF).

METHODS

Our review was constructed in accordance with Preferred Reporting Items and Meta-analyses (PRISMA) guidelines and protocol. We systematically searched PubMed, Embase, Scopus, CINAHL, and Web of Science databases. We included studies comparing Medicaid beneficiaries to other payer categories with regards to rates of LF and ACDF, costs/reimbursement, and health outcomes.

RESULTS

A total of 573 articles were assessed. Twenty-five articles were included in the analysis. We found that the literature is consistent with regards to Medicaid disparities. Medicaid was strongly associated with decreased access to LF and ACDF, lower reimbursement rates, and worse health outcomes (such as higher rates of readmission and emergency department utilization) compared to other insurance categories.

CONCLUSIONS

In adult patients undergoing elective spine surgery, Medicaid insurance is associated with wide disparities with regards to access to care and health outcomes. Efforts should focus on identifying causes and interventions for such disparities in this vulnerable population.

Developing a triage predictive model for access to a spinal surgeon using clinical variables and natural language processing of radiology reports

PURPOSE

To utilize natural language processing (NLP) of MRI reports and various clinical variables to develop a preliminary model predictive of the need for surgery in patients with low back and neck pain. Such a model would be beneficial for informing clinical practice decisions and help reduce the number of unnecessary surgical referrals, streamlining the surgical process.

METHODS

A historical cohort study was conducted using de-identified data from patients referred to a spine assessment clinic. Various demographic, clinical, and radiological variables were included as potential predictors. Full-text radiology reports of patients' MRI findings were vectorized using NLP before applying machine learning algorithms to develop models predicting who underwent surgery. Outputs from these models were then entered into a logistic regression model with clinical variables to develop a preliminary model predictive of surgical recommendations.

RESULTS

Of the 398 patients assessed, 71 underwent spine surgery. NLP variables were significant predictors in univariate analysis but did not remain in the final logistic regression model. An outcome of receiving surgery was predicted by a primary symptom of low back and leg pain (adjusted odds ratio 2.81), distal pain indicated by a pain diagram (adjusted odds ratio 2.49) and self-reported difficulties walking (adjusted odds ratio 2.73).

CONCLUSION

A logistic regression model was created to predict which patients may require spine surgery. Simple clinical variables appeared more predictive than variables created using NLP. However, additional research with more data samples is needed to validate this model and fully evaluate the usefulness of NLP for this task.

Development and Validation of a Risk-Prediction Nomogram for Chronic Low Back Pain Using a National Health Examination Survey: A Cross-Sectional Study

BACKGROUND

Several prognostic factors have been reported for chronic low back pain (CLBP). However, there are no studies on the prediction of CLBP development in the general population using a risk prediction model. This cross-sectional study aimed to develop and validate a risk prediction model for CLBP development in the general population, and to create a nomogram that can help a person at risk of developing CLBP to receive appropriate counseling on risk modification.

METHODS

Data on CLBP development, demographics, socioeconomic history, and comorbid health conditions of the participants were obtained through a nationally representative health examination and survey from 2007 to 2009. Prediction models for CLBP development were derived from a health survey on a random sample of 80% of the data and validated in the remaining 20%. After developing the risk prediction model for CLBP, the model was incorporated into a nomogram.

RESULTS

Data for 17,038 participants were analyzed, including 2693 with CLBP and 14,345 without CLBP. The selected risk factors included age, sex, occupation, education level, mid-intensity physical activity, depressive symptoms, and comorbidities. This model had good predictive performance in the validation dataset (concordance statistic = 0.7569, Hosmer-Lemeshow chi-square statistic = 12.10, p = 0.278). Based on our model, the findings indicated no significant differences between the observed and predicted probabilities.

CONCLUSIONS

The risk prediction model presented by a nomogram, which is a score-based prediction system, can be incorporated into the clinical setting. Thus, our prediction model can help individuals at risk of developing CLBP to receive appropriate counseling on risk modification from primary physicians.

Development and validation of a prediction model for outcomes after transaxillary first rib resection for neurogenic thoracic outlet syndrome following strict Society for Vascular Surgery diagnostic criteria

OBJECTIVE

Neurogenic thoracic outlet syndrome (NTOS) is the most common form of thoracic outlet syndrome. However, NTOS has remained difficult to diagnose and treat successfully. The purpose of the present study was to generate a predictive clinical calculator for postoperative outcomes after first rib resection (FRR) for NTOS.

METHODS

We performed a retrospective review of patients who had undergone FRR for NTOS at a single tertiary care institution between 2016 and 2020. A multivariate stepwise logistic regression analysis was performed to assess the association of the percentage of improvement after FRR with the patient baseline characteristics, pertinent clinical characteristics, and diagnostic criteria set by the Society for Vascular Surgery. The primary outcome was subjective patient improvement after FRR. A prediction risk calculator was developed using backward stepwise multivariate logistic regression coefficients. Bootstrapping was used for internal validation.

RESULTS

A total of 208 patients (22.2% male; mean age, 35.8 ± 12.8 years; median follow-up, 44.9 months) had undergone 243 FRRs. Of the 208 patients, 94.7% had had symptoms localized to the supraclavicular area, and 97.6% had had symptoms in the hand. All the patients had had positive symptoms reproduced by the elevated arm stress test and upper limb tension test. Another reasonably likely diagnosis was absent for all the patients. Of the 196 patients who had received a lidocaine injection, 180 (93.3%) had experienced improvement of NTOS symptoms. Of the 95 patients who had received a Botox injection, 82 (74.6%) had experienced improvement of NTOS symptoms. Receiver operating characteristic curve analysis was used to assess the model. The area under the curve for the backward stepwise multivariate logistic regression model was 0.8. The multivariate logistic regression analyses revealed that the significant predictors of worsened clinical outcomes included hand weakness (adjusted odds ratio [aOR], 4.28; 95% confidence interval [CI], 1.04-17.74), increasing age (aOR, 0.93; 95% CI, 0.88-0.99), workers' compensation or litigation case (aOR, 0.09; 95% CI, 0.01-0.82), and symptoms in the dominant hand (aOR, 0.20; 95% CI, 0.05-0.88).

CONCLUSIONS

Using retrospective data from a single-institution database, we have developed a prediction calculator with moderate to high predictive ability, as demonstrated by an area under the curve of 0.8. The tool (available at: https://jhhntosriskcalculator.shinyapps.io/NTOS_calc/) is an important adjunct to clinical decision-making that can offer patients and providers realistic and personalized expectations of the postoperative outcome after FRR for NTOS. The findings from the present study have reinforced the diagnostic criteria set by the Society for Vascular Surgery. The calculator could aid physicians in surgical planning, referrals, and counseling patients on whether to proceed with surgery.

The quality of life of 50-70 years old patients with orthopedic spinal stenosis surgery. A follow-up study (descriptive study)

Background

Background: Nowadays, surgical procedures are assessed based on the state of an individual. This study aimed to investigate the effect of lumbar spinal stenosis surgery on the patient's quality of life and motor functions in Kashani and Alzahra Hospital in Esfahan.

Methods

In the present cross-sectional study, 40 patients aged between 50-70 were respectively evaluated who underwent lumbar spine stenosis surgery in Al Zahra and Kashani Hospitals in Esfahan University of Medical Sciences, Esfahan, Iran, during 2020-2021. The SF-36 questionnaire was used as a research tool. The visual analog scale (VAS), and spine functional index (SFI), were measured initially before surgery and 6 months and 9 months after surgery.

Results

The mean scores of the SF-36, SFI, and VAS scores questionnaire were 87.95±4.94, 21.38±1.24, 6.07±0.69 (p<0.001) before surgery, 89.77±5.25, 19.73±1.40, 5.37±1.56 (p<0.001) six months after surgery, and 94.70±5.34, 18.63±1.56, 4.57±0.81 (p<0.001) nine months after surgery, and all were significant. Improvement in the domains of general health, role-physical, role disorder due to impaired physical health, social function, emotional role, and bodily pain was evident. Also, the overall quality of life was enhanced but energy levels and role disorder due to impaired mental health showed no improvement.

Conclusion

Not only does lumbar spinal stenosis surgery significantly improve the general health, role-physical, and the social function of the patients but also enhances their quality of life.

Validation of Adult Spinal Deformity Surgical Outcome Prediction Tools in Adult Symptomatic Lumbar Scoliosis

STUDY DESIGN

A post hoc analysis.

OBJECTIVE

Advances in machine learning (ML) have led to tools offering individualized outcome predictions for adult spinal deformity (ASD). Our objective is to examine the properties of these ASD models in a cohort of adult symptomatic lumbar scoliosis (ASLS) patients.

SUMMARY OF BACKGROUND DATA

ML algorithms produce patient-specific probabilities of outcomes, including major complication (MC), reoperation (RO), and readmission (RA) in ASD. External validation of these models is needed.

METHODS

Thirty-nine predictive factors (12 demographic, 9 radiographic, 4 health-related quality of life, 14 surgical) were retrieved and entered into web-based prediction models for MC, unplanned RO, and hospital RA. Calculated probabilities were compared with actual event rates. Discrimination and calibration were analyzed using receiver operative characteristic area under the curve (where 0.5=chance, 1=perfect) and calibration curves (Brier scores, where 0.25=chance, 0=perfect). Ninety-five percent confidence intervals are reported.

RESULTS

A total of 169 of 187 (90%) surgical patients completed 2-year follow up. The observed rate of MCs was 41.4% with model predictions ranging from 13% to 68% (mean: 38.7%). RO was 20.7% with model predictions ranging from 9% to 54% (mean: 30.1%). Hospital RA was 17.2% with model predictions ranging from 13% to 50% (mean: 28.5%). Model classification for all three outcome measures was better than chance for all [area under the curve=MC 0.6 (0.5-0.7), RA 0.6 (0.5-0.7), RO 0.6 (0.5-0.7)]. Calibration was better than chance for all, though best for RA and RO (Brier Score=MC 0.22, RA 0.16, RO 0.17).

CONCLUSIONS

ASD prediction models for MC, RA, and RO performed better than chance in a cohort of adult lumbar scoliosis patients, though the homogeneity of ASLS affected calibration and accuracy. Optimization of models require samples with the breadth of outcomes (0%-100%), supporting the need for continued data collection as personalized prediction models may improve decision-making for the patient and surgeon alike.

Development, validation, and visualization of a web-based nomogram to predict the effect of tubular microdiscectomy for lumbar disc herniation

Objective

The purpose of this study was to retrospectively collect the relevant clinical data of lumbar disc herniation (LDH) patients treated with the tubular microdiscectomy (TMD) technique, and to develop and validate a prediction model for predicting the treatment improvement rate of TMD in LDH patients at 1 year after surgery.

Methods

Relevant clinical data of LDH patients treated with the TMD technology were retrospectively collected. The follow-up period was 1 year after surgery. A total of 43 possible predictors were included, and the treatment improvement rate of the Japanese Orthopedic Association (JOA) score of the lumbar spine at 1 year after TMD was used as an outcome measure. The least absolute shrinkage and selection operator (LASSO) method was used to screen out the most important predictors affecting the outcome indicators. In addition, logistic regression was used to construct the model, and a nomogram of the prediction model was drawn.

Results

A total of 273 patients with LDH were included in this study. Age, occupational factors, osteoporosis, Pfirrmann classification of intervertebral disc degeneration, and preoperative Oswestry Disability Index (ODI) were screened out from the 43 possible predictors based on LASSO regression. A total of 5 predictors were included while drawing a nomogram of the model. The area under the ROC curve (AUC) value of the model was 0.795.

Conclusions

In this study, we successfully developed a good clinical prediction model that can predict the effect of TMD for LDH. A web calculator was designed on the basis of the model (https://fabinlin.shinyapps.io/DynNomapp/).

Does Age Younger Than 65 Affect Clinical Outcomes in Medicare Patients Undergoing Lumbar Fusion?

STUDY DESIGN

This was a retrospective cohort study.

OBJECTIVE

To determine if age (younger than 65) and Medicare status affect patient outcomes following lumbar fusion.

SUMMARY OF BACKGROUND DATA

Medicare is a common spine surgery insurance provider, but most qualifying patients are older than age 65. There is a paucity of literature investigating clinical outcomes for Medicare patients under the age of 65.

MATERIALS AND METHODS

Patients 40 years and older who underwent lumbar fusion surgery between 2014 and 2019 were queried from electronic medical records. Patients with >2 levels fused, >3 levels decompressed, incomplete patient-reported outcome measures (PROMs), revision procedures, and tumor/infection diagnosis were excluded. Patients were placed into 4 groups based on Medicare status and age: no Medicare under 65 years (NM<65), no Medicare 65 years or older (NM≥65), yes Medicare under 65 (YM<65), and yes Medicare 65 years or older (YM≥65). T tests and χ 2 tests analyzed univariate comparisons depending on continuous or categorical type. Multivariate regression for ∆PROMs controlled for confounders. Alpha was set at 0.05.

RESULTS

Of the 1097 patients, 567 were NM<65 (51.7%), 133 were NM≥65 (12.1%), 42 were YM<65 (3.8%), and 355 were YM≥65 (32.4%). The YM<65 group had significantly worse preoperative Visual Analog Scale back ( P =0.01) and preoperative and postoperative Oswestry Disability Index (ODI), Short-Form 12 Mental Component Score (MCS-12), and Physical Component Score (PCS-12). However, on regression analysis, there were no significant differences in ∆PROMs for YM <65 compared with YM≥65, and NM<65. NM<65 (compared with YM<65) was an independent predictor of decreased improvement in ∆ODI following surgery (β=12.61, P =0.007); however, overall the ODI was still lower in the NM<65 compared with the YM<65.

CONCLUSION

Medicare patients younger than 65 years undergoing lumbar fusion had significantly worse preoperative and postoperative PROMs. The perioperative improvement in outcomes was similar between groups with the exception of ∆ODI, which demonstrated greater improvement in Medicare patients younger than 65 compared with non-Medicare patients younger than 65.

LEVEL OF EVIDENCE

Level III (treatment).

Individual differences in postoperative recovery trajectories for adult symptomatic lumbar scoliosis

OBJECTIVE

The Adult Symptomatic Lumbar Scoliosis-1 (ASLS-1) trial demonstrated the benefit of adult symptomatic lumbar scoliosis (ASLS) surgery. However, the extent to which individuals differ in their postoperative recovery trajectories is unknown. This study's objective was to evaluate variability in and factors moderating recovery trajectories after ASLS surgery.

METHODS

The authors used longitudinal, multilevel models to analyze postoperative recovery trajectories following ASLS surgery. Study outcomes included the Oswestry Disability Index (ODI) score and Scoliosis Research Society-22 (SRS-22) subscore, which were measured every 3 months until 2 years postoperatively. The authors evaluated the influence of preoperative disability level, along with other potential trajectory moderators, including radiographic, comorbidity, pain/function, demographic, and surgical factors. The impact of different parameters was measured using the R2, which represented the amount of variability in ODI/SRS-22 explained by each model. The R2 ranged from 0 (no variability explained) to 1 (100% of variability explained).

RESULTS

Among 178 patients, there was substantial variability in recovery trajectories. Applying the average trajectory to each patient explained only 15% of the variability in ODI and 21% of the variability in SRS-22 subscore. Differences in preoperative disability (ODI/SRS-22) had the strongest influence on recovery trajectories, with patients having moderate disability experiencing the greatest and most rapid improvement after surgery. Reflecting this impact, accounting for the preoperative ODI/SRS-22 level explained an additional 56%-57% of variability in recovery trajectory, while differences in the rate of postoperative change explained another 7%-9%. Among the effect moderators tested, pain/function variables-such as visual analog scale back pain score-had the biggest impact, explaining 21%-25% of variability in trajectories. Radiographic parameters were the least influential, explaining only 3%-6% more variance than models with time alone. The authors identified several significant trajectory moderators in the final model, such as significant adverse events and the number of levels fused.

CONCLUSIONS

ASLS patients have highly variable postoperative recovery trajectories, although most reach steady state at 12 months. Preoperative disability was the most important influence, although other factors, such as number of levels fused, also impacted recovery.

Surgical outcomes of patients who fail to reach minimal clinically important differences: comparison of minimally invasive versus open transforaminal lumbar interbody fusion

OBJECTIVE

Treatment of degenerative lumbar diseases has been shown to be clinically effective with open transforaminal lumbar interbody fusion (O-TLIF) or minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF). Despite this, a substantial proportion of patients do not meet minimal clinically important differences (MCIDs) in patient-reported outcomes (PROs). The objectives of this study were to compare the proportions of patients who did not meet MCIDs after O-TLIF and MIS-TLIF and to determine potential clinical factors associated with failure to achieve MCID.

METHODS

The authors performed a retrospective analysis of consecutive patients who underwent O-TLIF or MIS-TLIF for lumbar degenerative disorders and had been prospectively enrolled in the Canadian Spine Outcomes and Research Network. The authors analyzed the Oswestry Disability Index (ODI) scores, physical and mental component summary scores of SF-12, numeric rating scale (NRS) scores for leg and back pain, and EQ-5D scores of the patients in each group who did not meet the MCID of ODI at 2 years postoperatively.

RESULTS

In this study, 38.8% (137 of 353) of patients in the O-TLIF cohort and 41.8% (51 of 122) of patients in the MIS-TLIF cohort did not meet the MCID of ODI at 2 years postoperatively (p = 0.59). Demographic variables and baseline PROs were similar between groups. There were improvements across the PROs of both groups through 2 years, and there were no differences in any PROs between the O-TLIF and MIS-TLIF cohorts. Multivariable logistic regression analysis demonstrated that higher baseline leg pain score (p = 0.017) and a diagnosis of spondylolisthesis (p = 0.0053) or degenerative disc disease (p = 0.022) were associated with achieving the MCID at 2 years after O-TLIF, whereas higher baseline leg pain score was associated with reaching the MCID after MIS-TLIF (p = 0.038).

CONCLUSIONS

Similar proportions of patients failed to reach the MCID of ODI at 2 years after O-TLIF or MIS-TLIF. Higher baseline leg pain score was predictive of achieving the MCID in both cohorts, whereas a diagnosis of spondylolisthesis or degenerative disc disease was predictive of reaching the MCID after O-TLIF. These data provide novel insights for patient counseling and suggest that either MIS-TLIF or O-TLIF does not overcome specific patient factors to mitigate clinical success or failure in terms of the intermediate-term PROs associated with 1- to 2-level lumbar fusion surgical procedures for degenerative pathologies.

Artificial Learning and Machine Learning Applications in Spine Surgery: A Systematic Review

OBJECTIVES

This current systematic review sought to identify and evaluate all current research-based spine surgery applications of AI/ML in optimizing preoperative patient selection, as well as predicting and managing postoperative outcomes and complications.

METHODS

A comprehensive search of publications was conducted through the EMBASE, Medline, and PubMed databases using relevant keywords to maximize the sensitivity of the search. No limits were placed on level of evidence or timing of the study. Findings were reported according to the PRISMA guidelines.

RESULTS

After application of inclusion and exclusion criteria, 41 studies were included in this review. Bayesian networks had the highest average AUC (.80), and neural networks had the best accuracy (83.0%), sensitivity (81.5%), and specificity (71.8%). Preoperative planning/cost prediction models (.89,82.2%) and discharge/length of stay models (.80,78.0%) each reported significantly higher average AUC and accuracy compared to readmissions/reoperation prediction models (.67,70.2%) (P < .001, P = .005, respectively). Model performance also significantly varied across postoperative management applications for average AUC and accuracy values (P < .001, P < .027, respectively).

CONCLUSIONS

Generally, authors of the reviewed studies concluded that AI/ML offers a potentially beneficial tool for providers to optimize patient care and improve cost-efficiency. More specifically, AI/ML models performed best, on average, when optimizing preoperative patient selection and planning and predicting costs, hospital discharge, and length of stay. However, models were not as accurate in predicting postoperative complications, adverse events, and readmissions and reoperations. An understanding of AI/ML-based applications is becoming increasingly important, particularly in spine surgery, as the volume of reported literature, technology accessibility, and clinical applications continue to rapidly expand.

Development of a machine-learning based model for predicting multidimensional outcome after surgery for degenerative disorders of the spine

BACKGROUND

It is clear that individual outcomes of spine surgery can be quite heterogeneous. When consenting a patient for surgery, it is important to be able to offer an individualized prediction regarding the likely outcome. This study used a comprehensive set of data collected over 12 years in an in-house registry to develop a parsimonious model to predict the multidimensional outcome of patients undergoing surgery for degenerative pathologies of the thoracic, lumbar or cervical spine.

METHODS

Data from 8374 patients (mean age 63.9 (14.9-96.3) y, 53.4% female) were used to develop a model to predict the 12-month scores for the Core Outcome Measures Index (COMI) and its subdomain scores. The data were split 80:20 into a training and test set. The top predictors were selected by applying recursive feature elimination based on LASSO cross validation models. Based on the 111 top predictors (contained within 20 variables), Ridge cross validation models were trained, validated, and tested for each of 9 outcome domains, for patients with either "Back" (thoracic/lumbar spine) or "Neck" (cervical spine) problems (total 18 models).

RESULTS

Among the strongest outcome predictors in most models were: preoperative scores for almost all COMI items (especially axial pain (back or neck) and peripheral pain (leg/buttock or arm/shoulder)), catastrophizing, fear avoidance beliefs, comorbidity, age, BMI, nationality, previous spine surgery, type and spinal level of intervention, number of affected levels, and surgeon seniority. The R² of the models on the validation/test sets averaged 0.16/0.13. A preliminary online tool was programmed to present the predicted outcomes for individual patients, based on their presenting characteristics. https://linkup.kws.ch/prognostictool .

CONCLUSION

The models provided estimates to enable a bespoke prediction of the outcome of surgery for individual patients with varying degenerative pathologies and baseline characteristics. The models form the basis of a simple, freely-available online prognostic tool developed to improve access to and usability of prognostic information in clinical practice. It is hoped that, following confirmation of its validity and practical utility, the tool will ultimately serve to facilitate decision-making and the management of patients' expectations.

Performance of hybrid artificial intelligence in determining candidacy for lumbar stenosis surgery

PURPOSE

Lumbar spinal stenosis (LSS) is a condition affecting several hundreds of thousands of adults in the United States each year and is associated with significant economic burden. The current decision-making practice to determine surgical candidacy for LSS is often subjective and clinician specific. In this study, we hypothesize that the performance of artificial intelligence (AI) methods could prove comparable in terms of prediction accuracy to that of a panel of spine experts.

METHODS

We propose a novel hybrid AI model which computes the probability of spinal surgical recommendations for LSS, based on patient demographic factors, clinical symptom manifestations, and MRI findings. The hybrid model combines a random forest model trained from medical vignette data reviewed by surgeons, with an expert Bayesian network model built from peer-reviewed literature and the expert opinions of a multidisciplinary team in spinal surgery, rehabilitation medicine, interventional and diagnostic radiology. Sets of 400 and 100 medical vignettes reviewed by surgeons were used for training and testing.

RESULTS

The model demonstrated high predictive accuracy, with a root mean square error (RMSE) between model predictions and ground truth of 0.0964, while the average RMSE between individual doctor's recommendations and ground truth was 0.1940. For dichotomous classification, the AUROC and Cohen's kappa were 0.9266 and 0.6298, while the corresponding average metrics based on individual doctor's recommendations were 0.8412 and 0.5659, respectively.

CONCLUSIONS

Our results suggest that AI can be used to automate the evaluation of surgical candidacy for LSS with performance comparable to a multidisciplinary panel of physicians.

Correlation between the degree of pain relief following discoblock and short-term surgical disability outcome among patients with suspected discogenic low back pain

OBJECTIVES

To evaluate how well the degree of pain relief after discoblock predicts the disability outcome of subsequent fusion or total disc replacement (TDR) surgery, based on short-term Oswestry Disability Index (ODI) scores.

METHODS

We retrospectively analyzed a set of patients who had undergone discoblock and subsequent fusion or TDR surgery of the same lumbar intervertebral disc due to suspected discogenic chronic LBP between 2011 and 2018. We calculated the degree of pain relief following discoblock (ΔNRS) and the changes in both absolute and percentual ODI scores (ΔODI and ΔODI%, respectively) following fusion or TDR surgery. We analyzed the statistical significance of ΔNRS and ΔODI and the correlation (Spearman's rho) between ΔNRS and ΔODI%. The fusion and TDR group were analyzed both in combination and separately.

RESULTS

Fifteen patients were eligible for the current study (fusion n=9, TDR n=6). ΔNRS was statistically significant in all groups, and ΔODI was statistically significant in the combined group and in the fusion group alone. The parameters of both decreased. We found a Spearman's rho of 0.57 (p=0.026) between ΔNRS and ΔODI% for the combined group. The individual Spearman's rho values were 0.85 (p=0.004) for the fusion group and 0.62 (p=0.191) for the TDR group.

CONCLUSIONS

We suggest that discoblock is a useful predictive criterion for disability outcome prior to surgery for discogenic LBP, especially when stabilizing spine surgery is under consideration.

ETHICAL COMMITTEE NUMBER

174/2019 (Oulu University Hospital Ethics Committee).

Using a consensus acupoints regimen to explore the relationship between acupuncture sensation and lumbar spinal postoperative analgesia: A retrospective analysis of prospective clinical cooperation

OBJECTIVE

This study evaluated the effectiveness of acupuncture treatment on postoperative pain in patients with degenerative lumbar spine disease, and explored the relationship between the postoperative analgesic effect of acupuncture and the sensation of acupuncture experienced by the patients.

METHODS

This retrospective study analyzed the medical records of 97 patients who had undergone an operation by the same surgeon due to degenerative lumbar disease. These patients were divided into acupuncture group (n = 32), patient-controlled analgesia (PCA) group (n = 27), and oral analgesia group (n = 38) according to the different postoperative analgesic methods. During their hospitalization, patients completed daily evaluations of their pain using a visual analogue scale (VAS), and injection times of supplemental meperidine were recorded. Also, the Chinese version of the Massachusetts General Hospital Acupuncture Sensation Scale (C-MASS) was used in the acupuncture group.

RESULTS

Each of the three treatment groups showed significant reductions in postoperative pain, as shown by reduced VAS scores. The acupuncture group, however, had less rebound pain (P < 0.05) than the other two groups. Both the acupuncture and PCA groups experienced acute analgesic effects that were superior to those in the oral analgesia group. In addition, the higher the C-MASS index on the second day after surgery, the lower the VAS score on the fourth day after surgery. There was also a significant difference in the "dull pain" in the acupuncture sensation.

CONCLUSION

The results demonstrated that acupuncture was beneficial for postoperative pain and discomfort after simple surgery for degenerative spinal disease. It is worth noting that there was a disproportionate relevance between the patient's acupuncture sensation and the improvement of pain VAS score.

Is the Centers for Medicare and Medicaid Services Hierarchical Condition Category Risk Adjustment Model Satisfactory for Quantifying Risk After Spine Surgery?

BACKGROUND

The Centers for Medicare and Medicaid Services (CMS) hierarchical condition category (HCC) coding is a risk adjustment model that allows for the estimation of risk-and cost-associated with health care provision. Current models may not include key factors that fully delineate the risk associated with spine surgery.

OBJECTIVE

To augment CMS HCC risk adjustment methodology with socioeconomic data to improve its predictive capabilities for spine surgery.

METHODS

The National Inpatient Sample was queried for spinal fusion, and the data was merged with county-level coverage and socioeconomic status variables obtained from the Brookings Institute. We predicted outcomes (death, nonroutine discharge, length of stay [LOS], total charges, and perioperative complication) with pairs of hierarchical, mixed effects logistic regression models-one using CMS HCC score alone and another augmenting CMS HCC scores with demographic and socioeconomic status variables. Models were compared using receiver operating characteristic curves. Variable importance was assessed in conjunction with Wald testing for model optimization.

RESULTS

We analyzed 653 815 patients. Expanded models outperformed models using CMS HCC score alone for mortality, nonroutine discharge, LOS, total charges, and complications. For expanded models, variable importance analyses demonstrated that CMS HCC score was of chief importance for models of mortality, LOS, total charges, and complications. For the model of nonroutine discharge, age was the most important variable. For the model of total charges, unemployment rate was nearly as important as CMS HCC score.

CONCLUSION

The addition of key demographic and socioeconomic characteristics substantially improves the CMS HCC risk-adjustment models when modeling spinal fusion outcomes. This finding may have important implications for payers, hospitals, and policymakers.

Patient-reported outcome measure clustering after surgery for adult symptomatic lumbar scoliosis

OBJECTIVE

Adult symptomatic lumbar scoliosis (ASLS) is a widespread and debilitating subset of adult spinal deformity. Although many patients benefit from operative treatment, surgery entails substantial cost and risk for adverse events. Patient-reported outcome measures (PROMs) are patient-centered tools used to evaluate the appropriateness of surgery and to assist in the shared decision-making process. Framing realistic patient expectations should include the possible functional limitation to improvement inherent in surgical intervention, such as multilevel fusion to the sacrum. The authors' objective was to predict postoperative ASLS PROMs by using clustering analysis, generalized longitudinal regression models, percentile analysis, and clinical improvement analysis of preoperative health-related quality-of-life scores for use in surgical counseling.

METHODS

Operative results from the combined ASLS cohorts were examined. PROM score clustering after surgery investigated limits of surgical improvement. Patients were categorized by baseline disability (mild, moderate, moderate to severe, or severe) according to preoperative Scoliosis Research Society (SRS)-22 and Oswestry Disability Index (ODI) scores. Responder analysis for patients achieving improvement meeting the minimum clinically important difference (MCID) and substantial clinical benefit (SCB) standards was performed using both fixed-threshold and patient-specific values (MCID = 30% of remaining scale, SCB = 50%). Best (top 5%), worst (bottom 5%), and median scores were calculated across disability categories.

RESULTS

A total of 171/187 (91%) of patients with ASLS achieved 2-year follow-up. Patients rarely achieved a PROM ceiling for any measure, with 33%-43% of individuals clustering near 4.0 for SRS domains. Patients with severe baseline disability (< 2.0) SRS-pain and SRS-function scores were often left with moderate to severe disability (2.0-2.9), unlike patients with higher (≥ 3.0) initial PROM values. Patients with mild disability according to baseline SRS-function score were unlikely to improve. Crippling baseline ODI disability (> 60) commonly left patients with moderate disability (median ODI = 32). As baseline ODI disability increased, patients were more likely to achieve MCID and SCB (p < 0.001). Compared to fixed threshold values for MCID and SCB, patient-specific values were more sensitive to change for patients with minimal ODI baseline disability (p = 0.008) and less sensitive to change for patients with moderate to severe SRS subscore disability (p = 0.01).

CONCLUSIONS

These findings suggest that ASLS surgeries have a limit to possible improvement, probably due to both baseline disability and the effects of surgery. The most disabled patients often had moderate to severe disability (SRS < 3, ODI > 30) at 2 years, emphasizing the importance of patient counseling and expectation management.

Machine Learning Algorithms Predict Achievement of Clinically Significant Outcomes After Orthopaedic Surgery: A Systematic Review

PURPOSE

To determine what subspecialties have applied machine learning (ML) to predict clinically significant outcomes (CSOs) within orthopaedic surgery and to determine whether the performance of these models was acceptable through assessing discrimination and other ML metrics where reported.

METHODS

The PubMed, EMBASE, and Cochrane Central Register of Controlled Trials databases were queried for articles that used ML to predict achievement of the minimal clinically important difference (MCID), patient acceptable symptomatic state (PASS), or substantial clinical benefit (SCB) after orthopaedic surgical procedures. Data pertaining to demographic characteristics, subspecialty, specific ML algorithms, and algorithm performance were analyzed.

RESULTS

Eighteen articles met the inclusion criteria. Seventeen studies developed novel algorithms, whereas one study externally validated an established algorithm. All studies used ML to predict MCID achievement, whereas 3 (16.7%) predicted SCB achievement and none predicted PASS achievement. Of the studies, 7 (38.9%) concerned outcomes after spine surgery; 6 (33.3%), after sports medicine surgery; 3 (16.7%), after total joint arthroplasty (TJA); and 2 (11.1%), after shoulder arthroplasty. No studies were found regarding trauma, hand, elbow, pediatric, or foot and ankle surgery. In spine surgery, concordance statistics (C-statistics) ranged from 0.65 to 0.92; in hip arthroscopy, 0.51 to 0.94; in TJA, 0.63 to 0.89; and in shoulder arthroplasty, 0.70 to 0.95. Most studies reported C-statistics at the upper end of these ranges, although populations were heterogeneous.

CONCLUSIONS

Currently available ML algorithms can discriminate the propensity to achieve CSOs using the MCID after spine, TJA, sports medicine, and shoulder surgery with a fair to good performance as evidenced by C-statistics ranging from 0.6 to 0.95 in most analyses. Less evidence is available on the ability of ML to predict achievement of SCB, and no evidence is available for achievement of the PASS. Such algorithms may augment shared decision-making practices and allow clinicians to provide more appropriate patient expectations using individualized risk assessments. However, these studies remain limited by variable reporting of performance metrics, CSO quantification methods, and adherence to predictive modeling guidelines, as well as limited external validation.

LEVEL OF EVIDENCE

Level III, systematic review of Level III studies.