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.

Alginate hydrogels: A potential tissue engineering intervention for intervertebral disc degeneration.

Intervertebral disc (IVD) degeneration is a major cause of low back pain and disability, affecting millions of people worldwide. Current treatments for IVD degeneration are limited to invasive surgery or pain management. Recently, there has been increasing interest in the use of biomaterials, such as alginate hydrogels, for the treatment of IVD degeneration. Alginate hydrogels are an example of such a biomaterial that is biocompatible and can be tailored to mimic the native extracellular matrix of the IVD. Derived from alginate, a naturally derived polysaccharide from brown seaweed that can be transformed into a gelatinous solution, alginate hydrogels are emerging in the field of tissue engineering. They can be used to deliver therapeutic agents, such as growth factors or cells, to the site of injury, providing a localized and sustained release that may enhance treatment outcomes. This paper provides an overview on the use of alginate hydrogels for the treatment of IVD degeneration. We discuss the properties of alginate hydrogels and their potential applications for IVD regeneration, including the mechanism against IVD degeneration. We also highlight the research outcomes to date along with the challenges and limitations of using alginate hydrogels for IVD regeneration, including their mechanical properties, biocompatibility, and surgical compatibility. Overall, this review paper aims to provide a comprehensive overview of the current research on alginate hydrogels for IVD degeneration and to identify future directions for research in this area.

Predictors of airway, respiratory, and pulmonary complications following elective anterior cervical discectomy and fusion.

INTRODUCTION: Anterior cervical discectomy and fusion (ACDF) is a commonly performed procedure on the cervical spine. While the procedure is generally well tolerated, respiratory and pulmonary complications (RPC) are an unlikely yet possible complication following ACDF. Few previous studies have specifically identified risk factors associated with RPC following ACDF. As the incidence of an RPC is rare at a single institution, a large national database is required for meaningful analysis. OBJECTIVE: The goal of this study is to characterize the predictors for RPC following an ACDF by utilizing a large national database. METHODS: The National Inpatient Sample (NIS) was queried from 2016 to 2018 for all patients who had received elective ACDF for degenerative cervical spine disease. We categorized several complications as airway complications including various abscess, angioedema, laryngeal edema, vocal cord paralysis, dysphonia, various etiologies of pneumonia, and acute respiratory distress syndrome. A Firth's logistic regression model was used to identify predictors of RPC. RESULTS: We identified a final cohort of 52,575 admissions in which an ACDF was performed of which 1454 admissions had an RPC. Older patients were 1.03 times more likely to have an RPC (OR = 1.03, 95%CI: 1.02-1.04). African American patients compared to Caucasian patients were 1.44 times more likely to have an RPC (OR = 1.44, 95%CI: 1.23-1.68). Obese patients were found to be 1.64 to have an RPC (OR = 1.64, 95%CI: 1.45-1.85). Diabetic patients are 2.07 times more likely to have an RPC (OR = 2.07, 95%CI: 1.76-2.44). Hypertensive patients are 1.91 times more likely to have an RPC (OR = 1.91, 95%CI: 1.59-2.27). Urban based hospitals were 1.11 and 1.46 times more likely to have an RPC (OR = 1.11, 95%CI: 0.79-1.59; OR = 1.46, 95%CI: 1.06-2.08; teaching and non-teaching respectively). Patients who underwent multilevel procedure were 1.32 times more likely to experience a follow-on RPC (OR = 1.32, 95%CI: 1.17-1.49) DISCUSSION: Our study identified modifiable predictors of RPC after elective ACDF (e.g. obesity, diabetes) which can be used to guide preoperative patient optimization.

Smartphone-Based Light Detection and Ranging for Remote Patient Evaluation and Monitoring.

LIDAR (from "light detection and ranging" or "laser imaging, detection, and ranging") is an evolving three-dimensional scanning technology with historical applications in various fields. However, the applicability of LIDAR in the field of medicine has mostly not been examined thus far. Here, we review the basic principles governing LIDAR and its potential to be used in three notable use cases in the context of remote patient monitoring: geriatric fall prevention, postoperative recovery monitoring, and home safety assessment. For assisting geriatric populations, LIDAR can create 3D renderings of their home environments and classify which objects may be associated with risk for falls. These risk factors can then be forwarded to both patients and providers in order for them to discuss how to make the patient's environment safer. LIDAR is also capable of mapping the range of extremity motion in patients undergoing postoperative recovery. Such LIDAR data is simple to acquire and record for these patients and could enable unique metrics to be developed to assess patient outcomes in postoperative recovery. Finally, LIDAR can also reproduce 3D home models to identify attributes of their environments that could be harmful to infants. Given the recent momentum in telehealth following the events of the coronavirus 2019 disease (COVID-19) pandemic, LIDAR may also be a powerful tool in driving new insights from quality improvement initiatives through remote patient monitoring.

The "Kickstand Rod" Technique for Coronal Imbalance in Patients With Spinal Deformity: A Case Report With Review of Literature.

Coronal imbalance is a type of spinal deformity with deviation from midline in the coronal plane. It is challenging to correct even in the hands of experienced spine surgeons. Many conventional techniques lead to unsuccessful results or complications. However, the incorporation of "kickstand rod" (KR) instrumentation is now understood to provide a more supported coronal correction and improve spinal deformities. Sometimes it can be used to provide additional spinal support in instances where spinal fusion has already occurred. The KR is placed from a posterior approach along the lateral spine from lumbar spine to ilium and exerts distraction forces that counteract misaligned spinal segments. Our objective is to present a clinical case example with a brief review of literature. Herein, we present a case of a 62-year-old male with the development of significant coronal imbalance following his posterior lumbosacral instrumentation and fusion 11 years prior to presentation. KR supplementation to his hardware improved his functional outcome significantly. Further, we provide a literature review of the surgical characteristics, indications, and functional outcomes of KR instrumentation. A term search of "kickstand rod" was performed in PubMed, and relevant English language publications were included. The literature search yielded only six publications. A total of 45 patients across three studies were assessed. A mean postoperative coronal balance magnitude of 26.83 mm was calculated compared to the preoperative coronal magnitude of 64.16 mm. Results also showed only four cases of intraoperative or postoperative complications. Moreover, the presented case reported successful KR implementation without any intraoperative complications. KR instrumentation is a safe and effective technique for coronal imbalance correction. The results show favorable outcomes in terms of coronal adjustment and low complication rates. Nevertheless, we caution the fact that further studies are warranted with long-term follow-ups.