Purpose
Surgical treatment of herniated lumbar intervertebral disks is a common procedure worldwide. However, recurrent herniated nucleus pulposus (re-HNP) may develop, complicating outcomes and ...patient management. The purpose of this study was to utilize machine-learning (ML) analytics to predict lumbar re-HNP, whereby a personalized risk prediction can be developed as a clinical tool.
Methods
A retrospective, single center study was conducted of 2630 consecutive patients that underwent lumbar microdiscectomy (mean follow-up: 22-months). Various preoperative patient pain/disability/functional profiles, imaging parameters, and anthropomorphic/demographic metrics were noted. An Extreme Gradient Boost (XGBoost) classifier was implemented to develop a predictive model identifying patients at risk for re-HNP. The model was exported to a web application software for clinical utility.
Results
There were 1608 males and 1022 females, 114 of whom experienced re-HNP. Primary herniations were central (65.8%), paracentral (17.6%), and far lateral (17.1%). The XGBoost algorithm identified multiple re-HNP predictors and was incorporated into an open-access web application software, identifying patients at low or high risk for re-HNP. Preoperative VAS leg, disability, alignment parameters, elevated body mass index, symptom duration, and age were the strongest predictors.
Conclusions
Our predictive modeling via an ML approach of our large-scale cohort is the first study, to our knowledge, that has identified significant risk factors for the development of re-HNP after initial lumbar decompression. We developed the re-herniation after decompression (RAD) profile index that has been translated into an online screening tool to identify low–high risk patients for re-HNP. Additional validation is needed for potential global implementation.
Purpose
Few studies examine the clinical outcomes in patients undergoing minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF) versus lateral lumbar interbody fusion (LLIF) for ...adjacent segment disease (ASD). We aim to compare the postoperative clinical trajectory through patient-reported outcome measures (PROMs) and minimum clinically important difference (MCID) in patients undergoing MIS-TLIF versus LLIF for ASD.
Methods
Patients were stratified into two cohorts based on surgical technique for ASD: MIS-TLIF versus LLIF. PROMs of 12-Item Short Form Physical Component Score (SF-12 PCS), visual analog scale (VAS) back, VAS leg, and Oswestry Disability Index (ODI) were collected at preoperative and postoperative 6-week/12-week/6-month/1-year time points. MCID attainment was calculated through comparison to established thresholds. Cohorts were compared through nonparametric inferential statistics.
Results
Fifty-four patients were identified, with 22 patients undergoing MIS-TLIF after propensity score matching. Patients undergoing MIS-TLIF for ASD demonstrated significant postoperative improvement up to 1-year VAS back, up to 1-year VAS leg, and 6-month through 1-year ODI (
p
≤ 0.035, all). Patients undergoing LLIF demonstrated significant postoperative improvement in 6-month SF-12 PCS, 6-month through 1-year VAS back, 12-week through 6-month VAS leg, and 6-month to 1-year ODI (
p
≤ 0.035, all). No significant differences were calculated between surgical techniques for PROMs or MCID achievement rates.
Conclusion
Patients undergoing either MIS-TLIF or LLIF for adjacent segment disease demonstrated significant postoperative improvement in pain and disability outcomes. Additionally, patients undergoing LLIF reported significant improvement in physical function. Both MIS-TLIF and LLIF are effective for the treatment of adjacent segment disease.
Objectives
Glioblastoma multiforme (GBM) is the most aggressive brain tumour type in humans. Its poor prognosis is largely attributed to its invasiveness and high rate of recurrence. Recurring GBM is ...commonly resistant to chemotherapeutic drugs, making it specially difficult to treat. Recent studies have revealed that matricellular glycoprotein SPOCK1 to be upregulated in several cancer types and to be specifically expressed in invasive GBM, but not in other types of non‐invasive brain tumour, which prompted us to study the mechanism of action of SPOCK1 in invasion, recurrence and drug resistance of GBM cells.
Materials and methods
SPOCK1 expression in GBM tissues was evaluated using qPCR, Western blotting and immunohistochemical staining. Cell migration was tested by the wound healing method and cell invasion was assessed using transwell plates with Matrigel coating. Western blotting was performed for E‐cadherin, vimentin, N‐cadherin, p‐Akt and Akt. Cell viability was examined using the MTT assay.
Results
We found that the expression of SPOCK1 was significantly upregulated in recurrent GBM. We also demonstrated that SPOCK1 positively regulated migration, invasion and EMT process of GBM cells. Furthermore, SPOCK1 mediated TMZ resistance in GBM, as knockdown of SPOCK1 expression in TMZ‐resistant GBM cells substantially sensitized these cells to TMZ.
Conclusion
SPOCK1 results were positive and it mediated TMZ resistance in GBM. In addition, SPOCK1 regulated invasion and TMZ resistance in GBM cells via the Akt signalling pathway.
Lateral lumbar fusion is a commonly used spinal fusion technique that allows for indirect neural decompression while correcting sagittal malalignment. The lateral position has evolved to include ...placement of percutaneous pedicle screw fixation, anterior longitudinal ligament release, and approach the L5-S1 segment. This review article focuses on the anatomy and technique of the single-position anterior column spinal fusion and highlights the recent trends, outcomes, and future directions for the approach.
Purpose
We aim to examine the preoperative factors associated with increased postoperative length of stay in patients undergoing LLIF in the hospital setting.
Methods
Patient demographics, ...perioperative characteristics, and patient-reported outcome measures (PROMs) were collected from a single-surgeon database. Patients undergoing LLIF in the hospital setting were separated into postoperative LOS <48 h (H) and LOS ≥ 48H. Univariate analysis for preoperative characteristics was utilized to determine covariates for multivariable logistic regression. Multivariable logistic regression was then utilized to determine significant predictors of extended postoperative length of stay. Secondary univariate analysis of inpatient complications, operative, and postoperative characteristics were calculated to determine postoperative factors associated with prolonged hospitalization.
Results
Two-hundred and forty patients were identified with 115 patients’ LOS ≥ 48H. Univariate analysis identified age/Charlson Comorbidity Index (CCI) score/gender/insurance type/number of contiguous fused levels/preoperative PROMs of Visual Analog Scale (VAS) back/VAS leg/Patient-Reported Outcomes Measurement Information System (PROMIS-PF)/Oswestry Disability Index (ODI)/degenerative spondylolisthesis diagnoses/foraminal stenosis/central stenosis for multivariable logistic regression. Multivariable logistic regression calculated significant positive predictors of LOS ≥ 48H to be age/3-level fusion/preoperative ODI scores. Negative predictors of LOS ≥ 48H were the diagnosis of foraminal stenosis/preoperative PROMIS-PF/male gender. The secondary analysis determined that patients with longer operative time/estimated blood loss/transfusion/postoperative day 0 and 1 pain and narcotic consumption/complications of altered mental status/postoperative anemia/fever/ileus/urinary retention were associated with prolonged hospitalization.
Conclusion
Older patients undergoing LLIF with greater preoperative disability and 3-level fusion were more likely to require prolonged hospitalization. Male patients with higher preoperative physical function and who were diagnosed with foraminal stenosis were less likely to require prolonged hospitalization.
Purpose
Anterior cervical discectomy and fusion (ACDF) is a common surgical treatment for degenerative disease in the cervical spine. However, resultant biomechanical alterations may predispose to ...early-onset adjacent segment degeneration (EO-ASD), which may become symptomatic and require reoperation. This study aimed to develop and validate a machine learning (ML) model to predict EO-ASD following ACDF.
Methods
Retrospective review of prospectively collected data of patients undergoing ACDF at a quaternary referral medical center was performed. Patients > 18 years of age with > 6 months of follow-up and complete pre- and postoperative X-ray and MRI imaging were included. An ML-based algorithm was developed to predict EO-ASD based on preoperative demographic, clinical, and radiographic parameters, and model performance was evaluated according to discrimination and overall performance.
Results
In total, 366 ACDF patients were included (50.8% male, mean age 51.4 ± 11.1 years). Over 18.7 ± 20.9 months of follow-up, 97 (26.5%) patients developed EO-ASD. The model demonstrated good discrimination and overall performance according to precision (EO-ASD: 0.70, non-ASD: 0.88), recall (EO-ASD: 0.73, non-ASD: 0.87), accuracy (0.82), F1-score (0.79), Brier score (0.203), and AUC (0.794), with C4/C5 posterior disc bulge, C4/C5 anterior disc bulge, C6 posterior superior osteophyte, presence of osteophytes, and C6/C7 anterior disc bulge identified as the most important predictive features.
Conclusions
Through an ML approach, the model identified risk factors and predicted development of EO-ASD following ACDF with good discrimination and overall performance. By addressing the shortcomings of traditional statistics, ML techniques can support discovery, clinical decision-making, and precision-based spine care.
Purpose
The field of artificial intelligence is ever growing and the applications of machine learning in spine care are continuously advancing. Given the advent of the intelligence-based spine care ...model, understanding the evolution of computation as it applies to diagnosis, treatment, and adverse event prediction is of great importance. Therefore, the current review sought to synthesize findings from the literature at the interface of artificial intelligence and spine research.
Methods
A narrative review was performed based on the literature of three databases (MEDLINE, CINAHL, and Scopus) from January 2015 to March 2021 that examined historical and recent advancements in the understanding of artificial intelligence and machine learning in spine research. Studies were appraised for their role in, or description of, advancements within image recognition and predictive modeling for spinal research. Only English articles that fulfilled inclusion criteria were ultimately incorporated in this review.
Results
This review briefly summarizes the history and applications of artificial intelligence and machine learning in spine. Three basic machine learning training paradigms: supervised learning, unsupervised learning, and reinforced learning are also discussed. Artificial intelligence and machine learning have been utilized in almost every facet of spine ranging from localization and segmentation techniques in spinal imaging to pathology specific algorithms which include but not limited to; preoperative risk assessment of postoperative complications, screening algorithms for patients at risk of osteoporosis and clustering analysis to identify subgroups within adolescent idiopathic scoliosis. The future of artificial intelligence and machine learning in spine surgery is also discussed with focusing on novel algorithms, data collection techniques and increased utilization of automated systems.
Conclusion
Improvements to modern-day computing and accessibility to various imaging modalities allow for innovative discoveries that may arise, for example, from management. Given the imminent future of AI in spine surgery, it is of great importance that practitioners continue to inform themselves regarding AI, its goals, use, and progression. In the future, it will be critical for the spine specialist to be able to discern the utility of novel AI research, particularly as it continues to pervade facets of everyday spine surgery.
Mental health disorders (MHDs) have been linked to worse postoperative outcomes after various surgical procedures. Past studies have also demonstrated a higher prevalence of dysphagia in both acute ...and community mental health settings. Dysphagia is among the most common complications following anterior cervical spine surgery (ACSS); however, current literature describing the association between an established diagnosis of an MHD and the rate of dysphagia after ACSS is sparse.
All patients who underwent ACSS between 2014 and 2020 with a minimum of 6 months of follow-up were retrospectively evaluated at a single institution. Patients were divided into cohorts depending on an established diagnosis of an MHD: the first had no established MHD (non-MHD); the second included patients with a diagnosed MHD. Outcomes were measured using pre- and postoperative patient-reported outcome scores, which included the Swallowing Quality of Life survey for dysphagia, as well as physical and mental health questionnaires. Postoperative dysphagia surveys were obtained at final follow-up for both patient cohorts.
A total of 68 and 124 patients with and without a diagnosis of a MHD were assessed. The MHD group reported significantly worse baseline Patient-Reported Outcomes Measurement Information System depression scale scores (p < 0.001), 12-Item Short-Form Health Survey (p < 0.001), and Veterans RAND 12-Item Health Survey (p = 0.001) mental health components compared to non-MHD group. This group continued to have worse mental health status in the postoperative period, as reported by Patient-Reported Outcomes Measurement Information System depression scale scores (p = 0.024), 12-Item Short-Form Health Survey (p = 0.019), and Veterans RAND 12-Item Health Survey (p = 0.027). Postoperative assessment of Swallowing Quality of Life scores (expressed as the mean ± SD) also showed worse dysphagia outcomes in the MHD cohort (80.1 ± 12.2) than in the non-MHD cohort (86.0 ± 12.1, p = 0.001).
ACSS is associated with significantly higher postoperative dysphagia in patients diagnosed with an MHD when compared to patients without an established mental health diagnosis. Given the high prevalence of MHDs in patients with spinal pathology, it is important for spine surgeons to take note of the increased incidence of dysphagia faced by this patient population.
STUDY DESIGN.Retrospective cohort.
OBJECTIVE.We evaluate the correlation of the Patient-Reported Outcomes Measurement Information System for physical function (PROMIS-PF) with legacy patient-reported ...outcome measures (PROMs) in patients undergoing minimally invasive transforaminal lumbar interbody fusion (MIS TLIF) up to 2 years postoperatively.
SUMMARY OF BACKGROUND DATA.PROMIS-PF has not been validated past 6 months following MIS TLIF.
METHODS.A surgical registry was retrospectively reviewed for eligible MIS TLIFs between May 2015 and September 2017. Inclusion criteria were primary, one- or two-level MIS TLIFs for degenerative spinal pathology. Patients without preoperative or 2-year follow up PROMIS-PF surveys were excluded. Demographic, perioperative, and PROMs including Visual Analog Scale (VAS) back, VAS leg, Oswestry Disability Index (ODI), 12-Item Short Form (SF-12) physical component summary (PCS) scores, and PROMIS-PF at preoperative and postoperative timepoint (e.g., 6 weeks, 12 weeks, 6 months, 1 year, and 2 years). A paired t test evaluated PROM improvement from baseline. The relationship of PROMIS-PF with VAS back, VAS leg, SF-12 PCS, and ODI was evaluated with a Pearson correlation coefficient.
RESULTS.The 68-subject cohort was 41.2% female, with an average age of 52.9 years; 44.1% were obese, and the majority underwent one-level fusions (95.6%). Pain (VAS back, VAS leg) and disability metrics (ODI) demonstrated significant improvement at all timepoints following MIS TLIF when compared to baseline (all P < 0.001). Physical function (SF-12 PCS, PROMIS-PF) demonstrated significant postoperative improvement at 12 weeks, 6 months, 1 year, and 2 years (all P < 0.001). All evaluated timepoints, with the exception of preoperative VAS back scores, revealed strong PROMIS-PF correlations with VAS back, VAS leg, ODI, and SF-12 PCS.
CONCLUSION.PROMIS-PF demonstrated a strong correlation with pain (VAS back, VAS leg), disability (ODI) and physical function (SF-12) at all postoperative follow-ups through 2 years. Our study provides longitudinal evidence for utilizing PROMIS-PF as a valid physical function measure among patients undergoing MIS TLIF.Level of Evidence4.
The aim of this study was to characterize the educational quality and reliability of YouTube videos related to low back pain (LBP) as well as to identify factors associated with the overall video ...quality. A review of YouTube was performed using two separate search strings. Video‐specific characteristics were analyzed for the first 50 videos of each string. Seventy‐seven eligible videos were identified as a result. The mean Journal of the American Medical Association score was 2.25 ± 1.09 (range: 0–4) out of 4. The mean Global Quality Score (GQS) score was 2.29 ± 1.37 (range: 1–4) out of 5. The mean LBP score (LPS) score was 3.83 ± 2.23 (range: 0–11) out of 15. Video power index was a predictor of GQS score (β = 55.78, p = 0.048), whereas the number of likes (β = −2.49, p = 0.047) and view ratio (β = −55.62, p = 0.049) were associated with lower quality scores. Days since initial upload (β = 0.32, p = 0.042) as well as like ratio (β = 0.37, p = 0.019) were independent predictors of higher LPS scores. The results of this study suggest that the overall reliability and educational quality of videos uploaded to YouTube concerning LBP are unsatisfactory. More popular videos demonstrated poorer educational quality than their less popular counterparts. As the prevalence of LBP rises, more accurate and thorough educational videos are necessary to ensure accurate information is available to patients.