An Integrated Voice Recognition and Natural Language Processing Platform to Automatically Extract Thoracolumbar Injury Classification Score Features From Radiology Reports

BACKGROUND

Many predictive models for estimating clinical outcomes after spine surgery have been reported in the literature. However, implementation of predictive scores in practice is limited by the time-intensive nature of manually abstracting relevant predictors. In this study, we designed natural language processing (NLP) algorithms to automate data abstraction for the thoracolumbar injury classification score (TLICS).

METHODS

We retrieved the radiology reports of all Mayo Clinic patients with an International Classification of Diseases, 9th or 10th revision, code corresponding to a fracture of the thoracolumbar spine between January 2005 and October 2020. Annotated data were used to train an N-gram NLP model using machine learning methods, including random forest, stepwise linear discriminant analysis, k-nearest neighbors, and penalized logistic regression models.

RESULTS

A total of 1085 spine radiology reports were included in our analysis. Our dataset included 483 compression, 401 burst, 103 translational/rotational, and 98 distraction fractures. A total of 103 reports had documented an injury of the posterior ligamentous complex. The overall accuracy of the random forest model for fracture morphology feature detection was 76.96% versus 65.90% in the stepwise linear discriminant analysis, 50.69% in the k-nearest neighbors, and 62.67% in the penalized logistic regression. The overall accuracy to detect posterior ligamentous complex integrity was highest in the random forest model at 83.41%. Our random forest model was implemented in the backend of a web application in which users can dictate reports and have TLICS features automatically extracted.

CONCLUSIONS

We have developed a machine learning NLP model for extracting TLICS features from radiology reports, which we deployed in a web application that can be integrated into clinical practice.

R2 advances in robotic-assisted spine surgery: comparative analysis of options, future directions, and bibliometric analysis of the literature

Spine surgery has undergone rapid advancements over the past several decades with the emergence of robotic and minimally invasive surgery (MIS). While conventional MIS spine surgery has had relative success, its complication profile has warranted continued efforts to improve clinical outcomes. We discuss the functional, clinical, and financial aspects of four robotic options for spinal pathologies, namely ROSA, Mazor X, Da Vinci, and ExcelsiusGPS, and conduct a bibliometric analysis to better understand current trends and applications of these robots as the field of robotic spine surgery continues to grow. An extensive search of English-language published literature on robotic-assisted spinal surgery was performed in Elsevier's Scopus database. A bibliometric analysis was then performed on the top 100 most cited papers. The search yielded articles regarding robotic-assisted spine surgery application, limitations, and functional outcomes secondary to spine pathology. Accuracy analyses of 1733 screw placements were reviewed. The top 100 papers were published between 1992 and 2020, with a significant increase from 2015 onwards. The top publishing institution was John Hopkins University (n = 8). The top contributing author was Dr. Isador H. Lieberman (n = 6). The USA (n = 34) had the most articles on robotic spinal surgery, followed by Germany (n = 12). This review examines robotic applications in spine surgery, including four available options: ROSA, Mazor X, Da Vinci, and ExcelsiusGPS. Publication output over time, surgical outcomes, screw accuracy, and cost-effectiveness of these technologies have been investigated here. Certain robots have functional, clinical, and financial differences worth noting. Given the dearth of existing literature reporting postoperative complications and long-term comparative outcomes, there is a clear need for further studies on this matter.

Rheumatoid Arthritis in Spine Surgery: A Systematic Review and Meta-Analysis

STUDY DESIGN

Systematic Review and Meta-analysis.

OBJECTIVE

The purpose of this study is to synthesize recommendations for perioperative medical management of RA patients and quantify outcomes after spine surgery when compared to patients without RA.

METHODS

A search of available literature on patients with RA and spine surgery was performed. Studies were included if they provided a direct comparison of outcomes between patients undergoing spine surgery with or without RA diagnosis. Meta-analysis was performed on operative time, estimated blood loss, hospital length of stay, overall complications, implant-related complications, reoperation, infection, pseudarthrosis, and adjacent segment disease.

RESULTS

Included in the analysis were 9 studies with 703 patients with RA undergoing spine surgery and 2569 patients without RA. In RA patients compared to non-RA patients undergoing spine surgery, the relative risk of infection was 2.29 times higher (P = .036), overall complications 1.61 times higher (P < .0001), implant-related complications 3.93 times higher (P = .009), and risk of reoperation 2.45 times higher (P < .0001). Hospital length of stay was 4.6 days longer in RA patients (P < .0001).

CONCLUSIONS

Treatment of spinal pathology in patients with RA carries an increased risk of infection and implant-related complications. Spine-specific guidelines for perioperative management of antirheumatic medication deserve further exploration. All RA patients should be perioperatively co-managed by a rheumatologist. This review helps identify risk profiles in RA specific to spine surgery and may guide future studies seeking to medically optimize RA patients perioperatively.

The Role of Alginate Hydrogels as a Potential Treatment Modality for Spinal Cord Injury: A Comprehensive Review of the Literature

Objective

To comprehensively characterize the utilization of alginate hydrogels as an alternative treatment modality for spinal cord injury (SCI).

Methods

An extensive review of the published literature on studies using alginate hydrogels to treat SCI was performed. The review of the literature was performed using electronic databases such as PubMed, EMBASE, and OVID MEDLINE electronic databases. The keywords used were “alginate,” “spinal cord injury,” “biomaterial,” and “hydrogel.”

Results

In the literature, we identified a total of 555 rat models that were treated with alginate scaffolds for regenerative biomarkers. Alginate hydrogels were found to be efficient and promising substrates for tissue engineering, drug delivery, neural regeneration, and cellbased therapies for SCI repair. With its ability to act as a pro-regenerative and antidegenerative agent, the alginate hydrogel has the potential to improve clinical outcomes.

Conclusion

The emerging developments of alginate hydrogels as treatment modalities may support current and future tissue regenerative strategies for SCI.

Transradial versus Transfemoral Approaches in Diagnostic and Therapeutic Neuroendovascular Interventions: A Meta-Analysis of Current Literature

BACKGROUND

The adoption of the transradial approach (TRA) has been increasing in popularity as a primary method to conduct both diagnostic and therapeutic interventions. As this technique gains broader acceptance and use within the neuroendovascular community, comparing its complication profile with a better-established alternative technique, the transfemoral approach (TFA), becomes more important. This study aimed to evaluate the safety of TRA compared with TFA in patients undergoing diagnostic, therapeutic, and combined neuroendovascular procedures.

METHODS

A systematic review and meta-analysis was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. A literature search of PubMed and other databases was conducted for studies from all available dates. To compare TRA and TFA, we performed an indirect meta-analysis between studies that mentioned the complications of the procedures.

RESULTS

Our search yielded 532 studies, of which 108 met full inclusion criteria. A total of 54,083 patients (9137 undergoing TRA and 44,946 undergoing TFA) were included. Access site complication rate was lower in TRA (1.62%) compared with TFA (3.31%) (P < 0.01). Neurological complication rate was lower in TRA (1.64%) compared with TFA (3.82%) (P = 0.02 and P < 0.01, respectively). Vascular spasm rate was higher in TRA (3.65%) compared with TFA (0.88%) (P < 0.01). Wound infection complication rate was higher in TRA (0.32%) compared with TFA (0.2%) (P < 0.01).

CONCLUSIONS

Patients undergoing TFA are significantly more likely to experience access site complications and neurological complications compared with patients undergoing TRA. Patients undergoing TRA are more likely to experience complications such as wound infections and vascular spasm.

Comparison of Outcomes Between Cage Materials Used for Patients Undergoing Anterior Cervical Discectomy and Fusion with Standalone Cages: A Systematic Review and Meta-Analysis

INTRODUCTION

Interbody cages are currently being used to address diseases of the vertebra requiring surgical stabilization. Titanium cages were first introduced in 1988. Polyetheretherketone (PEEK) cages are used frequently as one of the alternatives to titanium cages in current practice. This study aimed to compare available cage materials by reviewing the surgical and radiographic outcomes following anterior cervical discectomy and fusion.

METHODS

A comprehensive search of several electronic databases was conducted following the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) guidelines. Baseline characteristics, operative outcomes, arthrodesis rates, subsidence rates, and complications were collected from included studies. Collected outcomes were further stratified according to the procedure type, the number of levels operated, and graft used to compare cage materials.

RESULTS

Following the screening for inclusion criteria, a total of 37 studies with 2363 patients were included. The median age was 49.5 years and the median follow-up was 26 months. Overall, no significant differences were found between PEEK and titanium cages regarding fusion, neurologic deficit, subsidence rates, or "good and excellent" outcome according to Odom criteria. However, the standalone comparison between PEEK, titanium, and poly-methyl-methacrylate (PMMA) cages showed a significantly lower fusion rate for PMMA (PEEK: 94%, PMMA: 56%, titanium: 95%, P < 0.01).

CONCLUSIONS

In the present systematic review and meta-analysis, a comparison of the long-term patient-reported and the radiographic outcomes associated with the use of titanium and PEEK, intervertebral body cages showed similar findings. However, there were significantly lower fusion rates for PMMA cages when using a standalone cage without graft material.

Neurocytological Advances in the Treatment of Glioblastoma Multiforme

Glioblastoma multiforme (GBM) is an aggressive neoplasm of the brain that has commonly led to disappointing patient outcomes. Despite medical advancements and increasing research efforts, GBM studies reveal a stagnant survival rate at the global level with only sluggish improvement over time. Modern neuro-oncology research places a heavy emphasis on pharmacological therapies. Through a broad database search, we accumulated and synthesized the GBM-related neuroimmunocytological literature to create a comprehensive and contemporary review. Based on our findings, we discuss the recent neurocytological treatment strategies for GMB and the results of the studies. Regorafenib, paxalisib, and dianhydrogalactitol (VAL-083) are showing initial promise to decrease disease progression. VAL-083 is an alkylating agent that creates N7 methylation on DNA and has the ability to cross the blood-brain barrier (BBB). Selinexor, recombinant nonpathogenic polio-rhinovirus, and GBM-vaccine of autologous fibroblasts retrovirally transfected with TFG-IL4-Neo-TK vector have all also shown initial clinical benefit in terms of prolonging survival. Most trials observe modest improvement in outcomes with a positive safety profile. Nevertheless, the need for further studies is warranted, along with the trending of post-therapeutic biomarkers in order to better access future patient outcomes.