RESUMO
Background: Vertebral osteomyelitis and discitis (VOD), an infection of intervertebral discs, often requires spine surgical intervention and timely management to prevent adverse outcomes. Our study aims to develop a machine learning (ML) model to predict the indication for surgical intervention (during the same hospital stay) versus nonsurgical management in patients with VOD. Methods: This retrospective study included adult patients (≥18 years) with VOD (ICD-10 diagnosis codes M46.2,3,4,5) treated at a single institution between 01/01/2015 and 12/31/2019. The primary outcome studied was surgery. Candidate predictors were age, sex, race, Elixhauser comorbidity index, first-recorded lab values, first-recorded vital signs, and admit diagnosis. After splitting the dataset, XGBoost, logistic regression, and K-neighbor classifier algorithms were trained and tested for model development. Results: A total of 1,111 patients were included in this study, among which 30% (n=339) of patients underwent surgical intervention. Age and sex did not significantly differ between the two groups; however, race did significantly differ (P<0.0001), with the surgical group having a higher percentage of white patients. The top ten model features for the best-performing model (XGBoost) were as follows (in descending order of importance): admit diagnosis of fever, negative culture, Staphylococcus aureus culture, partial pressure of arterial oxygen to fractional inspired oxygen ratio (PaO2:FiO2), admit diagnosis of intraspinal abscess and granuloma, admit diagnosis of sepsis, race, troponin I, acid-fast bacillus culture, and alveolar-arterial gradient (A-a gradient). XGBoost model metrics were as follows: accuracy =0.7534, sensitivity =0.7436, specificity =0.7586, and area under the curve (AUC) =0.8210. Conclusions: The XGBoost model reliably predicts the indication for surgical intervention based on several readily available patient demographic information and clinical features. The interpretability of a supervised ML model provides robust insight into patient outcomes. Furthermore, it paves the way for the development of an efficient hospital resource allocation instrument, designed to guide clinical suggestions.
RESUMO
Calcifying pseudoneoplasms of the neuraxis (CAPNON) are rare, non-neoplastic, slow-growing tumors that can present anywhere throughout the central nervous system. While the etiology of these lesions remains unknown, the mainstay of treatment is surgical excision. We describe a case of CAPNON at our institution in a 66 year-old female patient who presented with 5 months of pain and burning sensation in her thigh. On MRI, an intradural extramedullary lesion was identified at the level of T11-T12. The mass was surgically excised and the patient reported resolution of her symptoms by her six week follow-up appointment. We reviewed 79 spinal CAPNON cases, covering all cases reported in the literature thus far. In summary, we find that spinal CAPNON are most commonly lumbar and extradural in location, with pain as the most common presenting symptom. Lesions are well-defined and hypointense on T1 and T2 MRI sequence. The majority of cases had favorable surgical outcomes with near complete resolution of pain and associated symptoms.
RESUMO
Background and Objectives: Augmented reality head-mounted display (AR-HMD) is a novel technology that provides surgeons with a real-time CT-guided 3-dimensional recapitulation of a patient's spinal anatomy. In this case series, we explore the use of AR-HMD alongside more traditional robotic assistance in surgical spine trauma cases to determine their effect on operative costs and perioperative outcomes. Materials and Methods: We retrospectively reviewed trauma patients who underwent pedicle screw placement surgery guided by AR-HMD or robotic-assisted platforms at an academic tertiary care center between 1 January 2021 and 31 December 2022. Outcome distributions were compared using the Mann-Whitney U test. Results: The AR cohort (n = 9) had a mean age of 66 years, BMI of 29.4 kg/m2, Charlson Comorbidity Index (CCI) of 4.1, and Surgical Invasiveness Index (SII) of 8.8. In total, 77 pedicle screws were placed in this cohort. Intra-operatively, there was a mean blood loss of 378 mL, 0.78 units transfused, 398 min spent in the operating room, and a 20-day LOS. The robotic cohort (n = 13) had a mean age of 56 years, BMI of 27.1 kg/m2, CCI of 3.8, and SII of 14.2. In total, 128 pedicle screws were placed in this cohort. Intra-operatively, there was a mean blood loss of 432 mL, 0.46 units transfused units used, 331 min spent in the operating room, and a 10.4-day LOS. No significant difference was found between the two cohorts in any outcome metrics. Conclusions: Although the need to address urgent spinal conditions poses a significant challenge to the implementation of innovative technologies in spine surgery, this study represents an initial effort to show that AR-HMD can yield comparable outcomes to traditional robotic surgical techniques. Moreover, it highlights the potential for AR-HMD to be readily integrated into Level 1 trauma centers without requiring extensive modifications or adjustments.
Assuntos
Realidade Aumentada , Fusão Vertebral , Cirurgia Assistida por Computador , Humanos , Idoso , Pessoa de Meia-Idade , Cirurgia Assistida por Computador/métodos , Estudos Retrospectivos , Fluoroscopia/métodos , Fusão Vertebral/métodosRESUMO
Tranexamic acid (TXA) has long been utilized in spine surgery and can be administered through intravenous (IV) and topical routes. Although, topical and IV administration of TXA are both effective in decreasing blood loss during spine surgery, complications like deep vein thrombosis (DVT) and pulmonary embolism have been reported with the use of intravenous TXA (ivTXA). These potential complications may be mitigated through the use of topical TXA (tTXA). To assess optimal dosing protocols and efficacy of topical TXA in spine surgery, Embase, Ovid-MEDLINE, Scopus, Cochrane, and clinicaltrials.gov were queried for original research on the use of tTXA in adult patients undergoing spine surgery. Data parameters analyzed included blood loss, transfusion rate, thromboembolic, and other complications. Data was synthesized and confidence evaluated according to the Grades of Recommendation, Assessment, Development, and Evaluation approach. Nineteen studies were included in the final analysis with 2197 patients. Of the 18 published studies, 9 (50%) displayed high levels of evidence. Topical TXA showed a trend towards a lower risk of transfusion and complications. Protocols that used 1g tTXA showed a significantly reduced risk for transfusion when compared to controls (risk ratio -1.05, 95% CI (-1.62, -0.48); P = 0.94, I2 = 0%). Complications associated with tTXA included DVTs and wound infections. Topical TXA was non-inferior to intravenous TXA with similar efficacy and complication profiles for bleeding control in spine surgery; however, more studies are needed to discern benefits and risks.