RESUMO
Background: Metastasis to the spinal column is a common complication of malignancy, potentially causing pain and neurologic injury. An automated system to identify and refer patients with spinal metastases can help overcome barriers to timely treatment. We describe the training, optimization and validation of a natural language processing algorithm to identify the presence of vertebral metastasis and metastatic epidural cord compression (MECC) from radiology reports of spinal MRIs. Methods: Reports from patients with spine MRI studies performed between January 1, 2008 and April 14, 2019 were reviewed by a team of radiologists to assess for the presence of cancer and generate a labeled dataset for model training. Using regular expression, impression sections were extracted from the reports and converted to all lower-case letters with all nonalphabetic characters removed. The reports were then tokenized and vectorized using the doc2vec algorithm. These were then used to train a neural network to predict the likelihood of spinal tumor or MECC. For each report, the model provided a number from 0 to 1 corresponding to its impression. We then obtained 111 MRI reports from outside the test set, 92 manually labeled negative and 19 with MECC to test the model's performance. Results: About 37,579 radiology reports were reviewed. About 36,676 were labeled negative, and 903 with MECC. We chose a cutoff of 0.02 as a positive result to optimize for a low false negative rate. At this threshold we found a 100% sensitivity rate with a low false positive rate of 2.2%. Conclusions: The NLP model described predicts the presence of spinal tumor and MECC in spine MRI reports with high accuracy. We plan to implement the algorithm into our EMR to allow for faster referral of these patients to appropriate specialists, allowing for reduced morbidity and increased survival.
RESUMO
Study Design: This was retrospective cohort study. Purpose: The current investigation uses a large, multi-institutional dataset to compare short-term morbidity and mortality rates between current smokers and nonsmokers undergoing thoracolumbar fusion surgery. Overview of Literature: The few studies that have addressed perioperative complications following thoracolumbar fusion surgeries are each derived from small cohorts from single institutions. Materials and Methods: A retrospective study was conducted on thoracolumbar fusion patients in the American College of Surgeons National Surgical Quality Improvement Program database (2006-2016). The primary outcome compared the rates of overall morbidity, severe postoperative morbidity, infections, pneumonia, deep venous thrombosis (DVT), pulmonary embolism (PE), transfusions, and mortality in smokers and nonsmokers. Results: A total of 57,677 patients were identified. 45,952 (78.8%) were nonsmokers and 12,352 (21.2%) smoked within 1 year of surgery. Smokers had fewer severe complications (1.6% vs. 2.0%, P = 0.014) and decreased discharge to skilled nursing facilities (6.3% vs. 11.5%, P < 0.001) compared to nonsmokers. They had lower incidences of transfusions (odds ratio [OR] = 0.9, confidence interval [CI] = 0.8-1.0, P = 0.009) and DVT (OR = 0.7, CI = 0.5-0.9, P = 0.039) as well as shorter length of stay (LOS) (OR = 0.9, CI = 0.9-0.99, P < 0.001). They had a higher incidence of postoperative pneumonia (OR = 1.4, CI = 1.1-1.8, P = 0.002). There was no difference in the remaining primary outcomes between smoking and nonsmoking cohorts. Conclusions: There is a positive correlation between smoking and postoperative pneumonia after thoracolumbar fusion. The incidence of blood transfusions, DVT, and LOS was decreased in smokers. Early postoperative mortality, severe complications, discharge to subacute rehabilitation facilities, extubation failure, PE, SSI, and return to OR were not associated with smoking.
RESUMO
STUDY DESIGN: Finite element analysis. OBJECTIVE: The aim of this study was to determine the role of biological fusion and anterior column support in a long lumbopelvic spinal fixation. SUMMARY OF BACKGROUND DATA: Retrospective studies have shown that adding anterior column support is not sensitive to construct failure, highlighting that posterior fusion quality may be a more important factor. METHODS: Finite element models were created to match the average spinal-pelvic parameters of two patient cohorts reported in the literature: major failure and nonfailure. A moment load was applied at the T10 superior endplate to simulate gravimetric loading in a standing position. Effects of three factors on the biomechanical behavior of a fused spine were evaluated: sagittal alignment; posterior fusion versus no fusion; and anterior support at L4-S1 versus no anterior support. RESULTS: Sagittal balance of the major failure group was positively correlated with 15% higher translation, 14% higher rotation, and 16% higher stress than in the nonfailure group. Simulated posterior fusion-only decreased motion by 32% and 29%, and alleviated rod stress by 15% and 5% and S1 screw stress by 26% and 35%, respectively, in major failure and non-failure groups. The addition of anterior fusion without posterior fusion did not help with rod stress alleviation but dramatically decreased S1 screw stress (by 57% and 41%), respectively. With both posterior fusion and anterior support, screw stress at the S1 was decreased by additional 30% and 6%, respectively. CONCLUSION: The spinopelvic parameters of the major failure group produced increased gravity load, resulting in increased stresses in comparison to the nonfailure group. Simulated posterior "solid" fusion in the lumbar region helped reduce stresses in both major failure and nonfailure patients. Anterior column support was an important factor in reducing S1 screw stress, with or without posterior fusion, and should be considered for patients with poor alignment.Level of Evidence: N/A.
Assuntos
Parafusos Ósseos , Simulação por Computador , Vértebras Lombares/cirurgia , Ossos Pélvicos/cirurgia , Fusão Vertebral/métodos , Suporte de Carga , Fenômenos Biomecânicos/fisiologia , Estudos de Coortes , Feminino , Análise de Elementos Finitos , Humanos , Vértebras Lombares/fisiologia , Masculino , Pessoa de Meia-Idade , Ossos Pélvicos/fisiologia , Estudos Retrospectivos , Rotação , Fusão Vertebral/instrumentação , Suporte de Carga/fisiologiaRESUMO
STUDY DESIGN: Retrospective single-institution study. OBJECTIVE: The aim of this study was to determine the relationship between patients' insurance status and the likelihood for them to be recommended various spine interventions upon evaluation in our neurosurgical clinics. SUMMARY OF BACKGROUND DATA: Socioeconomically disadvantaged populations have worse outcomes after spine surgery. No studies have looked at the differential rates of recommendation for surgery for patients presenting to spine surgeons based on socioeconomic status. METHODS: We studied patients initially seeking spine care from spine-fellowship trained neurosurgeons at our institution from July 1, 2018 to June 30, 2019. Multivariable logistic regression was used to assess the association between insurance status and the recommended patient treatment. RESULTS: Overall, 663 consecutive outpatients met inclusion criteria. Univariate analysis revealed a statistically significant association between insurance status and treatment recommendations for surgery (Pâ<â0.001). Multivariate logistic regression demonstrated that compared with private insurance, Medicare (odds ratio [OR] 3.54, 95% confidence interval [CI] 1.21-7.53, Pâ=â0.001) and Medicaid patients (OR 2.46, 95% CI 1.21-5.17, Pâ=â0.014) were more likely to be recommended for surgery. Uninsured patients did not receive recommendations for surgery at significantly different rates than patients with private insurance. CONCLUSION: Medicare and Medicaid patients are more likely to be recommended for spine surgery when initially seeking spine care from a neurosurgeon. These findings may stem from a number of factors, including differential severity of the patient's condition at presentation, disparities in access to care, and differences in shared decision making between surgeons and patients.Level of Evidence: 3.
Assuntos
Medicaid , Medicare , Idoso , Humanos , Cobertura do Seguro , Seguro Saúde , Estudos Retrospectivos , Estados UnidosRESUMO
STUDY DESIGN: Case series. OBJECTIVE: To evaluate the impact of a multidisciplinary spine surgery indications conference (MSSIC) on surgical planning for elective spine surgeries. SUMMARY OF BACKGROUND DATA: Identifying methods for pairing the proper patient with the optimal intervention is of the utmost importance for improving spine care and patient outcomes. Prior studies have evaluated the utility of multidisciplinary spine conferences for patient management, but none have evaluated the impact of a MSSIC on surgical planning and decision making. METHODS: We implemented a mandatory weekly MSSIC with all spine surgeons at our institution. Each elective spine surgery in the upcoming week is presented. Subsequently, a group consensus decision is achieved regarding the best treatment option based on the expertise and opinions of the participating surgeons. We reviewed cases presented at the MSSIC from September 2019 to December 2019. We compared the surgeon's initial proposed surgery for a patient with the conference attendees' consensus decision on the best treatment and measured compliance rates with the group's recommended treatment. RESULTS: The conference reviewed 100 patients scheduled for elective spine surgery at our indications conference during the study period. Surgical plans were recommended for alteration in 19 cases (19%) with the proportion statistically significant from zero indicated by a binomial test (Pâ<â0.001). The median absolute change in the invasiveness index of the altered procedures was 3 (interquartile range [IQR] 1-4). Participating surgeons complied with the group's recommendation in 96.5% of cases. CONCLUSION: In conjunction with other multidisciplinary methods, MSSICs can lead to surgical planning alterations in a significant number of cases. This could potentially result in better selection of surgical candidates and procedures for particular patients. Although long-term patient outcomes remain to be evaluated, this care model will likely play an integral role in optimizing the care spine surgeons provide patients. LEVEL OF EVIDENCE: 4.
Assuntos
Congressos como Assunto , Estudos Interdisciplinares , Coluna Vertebral/cirurgia , Procedimentos Cirúrgicos Operatórios/normas , Adulto , Idoso , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Pesquisa , CirurgiõesRESUMO
BACKGROUND: Acquired lumbar spondylolisthesis is often treated with interbody fusion. However, few studies have evaluated predictors for prolonged length of stay (LOS) and disposition to rehabilitation facilities after posterior single-level lumbar interbody fusion for acquired spondylolisthesis. METHODS: The American College of Surgeons National Quality Improvement Program database was queried for adults with acquired spondylolisthesis who underwent single-level lumbar interbody fusion through a posterior approach (posterior lumbar interbody fusion (PLIF) or transforaminal lumbar interbody fusion [TLIF]). We utilized multivariate logistic regression analysis to identify predictors of prolonged LOS and disposition in this patient population. RESULTS: Among 2080 patients identified, 700 (33.7%) had a prolonged LOS (≥4 days), and 306 (14.7%) were discharged postoperatively to rehabilitation facilities. Predictors for prolonged LOS included: American Society of Anesthesiologist (ASA) class ≥3, anemia, prolonged operative time, perioperative blood transfusion, pneumonia, urinary tract infections, and return to the operating room. The following risk factors predicted discharge to postoperative rehabilitation facilities: age ≥65 years, male sex, ASA class ≥3, modified frailty score ≥2, perioperative blood transfusion, and prolonged LOS. CONCLUSION: Multiple partial-overlapping risk factors predicted prolonged LOS and discharge to rehabilitation facilities after single-level TLIF/PLIF performed for acquired spondylolisthesis.