Study Design.
A cross-sectional database study.
Objective.
The aim of this study was to train and validate machine learning models to identify risk factors for complications following posterior lumbar spine fusion.
Summary of Background Data.
Machine learning models such as artificial neural networks (ANNs) are valuable tools for analyzing and interpreting large and complex datasets. ANNs have yet to be used for risk factor analysis in orthopedic surgery.
Methods.
The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database was queried for patients who underwent posterior lumbar spine fusion. This query returned 22,629 patients, 70% of whom were used to train our models, and 30% were used to evaluate the models. The predictive variables used included sex, age, ethnicity, diabetes, smoking, steroid use, coagulopathy, functional status, American Society for Anesthesiology (ASA) class ≥3, body mass index (BMI), pulmonary comorbidities, and cardiac comorbidities. The models were used to predict cardiac complications, wound complications, venous thromboembolism (VTE), and mortality. Using ASA class as a benchmark for prediction, area under receiver operating curves (AUC) was used to determine the accuracy of our machine learning models.
Results.
On the basis of AUC values, ANN and LR both outperformed ASA class for predicting all four types of complications. ANN was the most accurate for predicting cardiac complications, and LR was most accurate for predicting wound complications, VTE, and mortality, though ANN and LR had comparable AUC values for predicting all types of complications. ANN had greater sensitivity than LR for detecting wound complications and mortality.
Conclusion.
Machine learning in the form of logistic regression and ANNs were more accurate than benchmark ASA scores for identifying risk factors of developing complications following posterior lumbar spine fusion, suggesting they are potentially great tools for risk factor analysis in spine surgery.
BACKGROUND
Asymptomatic blood pressure elevation is common in the inpatient setting. National guidelines recommend treating with oral agents to slowly decrease blood pressure; however, many clinicians use intravenous antihypertensive medications, which can lead to unpredictable changes in blood pressure.
OBJECTIVE
To decrease the number of inappropriate orders (without symptoms of hypertensive emergency or order for NPO) of intravenous antihypertensives and adverse events associated with intravenous orders.
DESIGN
Quasi‐experimental study with multidisciplinary intervention.
PARTICIPANTS
Inpatients with a one‐time order for an intravenous antihypertensive agent from January 2016 to February 2018.
MAIN MEASURES
The main outcomes were the total numbers of orders and inappropriate orders, adverse events, and alternate etiologies per 1,000 patient‐days. As a balancing measure, patients were monitored for adverse events when blood pressure was elevated and not treated.
KEY RESULTS
There were a total of 260 one‐time orders of intravenous antihypertensives on two medical units. Inappropriate orders decreased from 8.3 to 3.3 per 1,000 patient days (P = .0099). Adverse events associated with intravenous antihypertensives decreased from 3.7 to 0.8 per 1,000 patient days (P = .0072).
CONCLUSION
This initiative demonstrated a significant reduction in inappropriate use of IV antihypertensives and an associated reduction in adverse events.
Materials and Methods: A single-center retrospective review included 29 patients undergoing 41 LRTs-transarterial chemoembolization or yttrium-90 transarterial radioembolization-60 days before or concurrently with nivolumab. Demographic, clinical, and laboratory values and adverse events were reviewed before and after nivolumab initiation and after each LRT. Treatment response and time to progression were assessed using Modified Response Evaluation Criteria in Solid Tumors. Clinical events, including nivolumab termination, death, and time of last follow-up, were assessed.Results: Over a median nivolumab course of 8.1 months (range, 1.0-30) with a median of 14.2 2-week cycles (range, 1-53), predominantly Child-Pugh A (22/29) patients-12 Barcelona Clinic Liver Cancer (BCLC) B and 17 BCLC C-underwent 20 transarterial chemoembolization and 21 transarterial radioembolization LRTs at a median of 67 days (range, 48-609) after nivolumab initiation. Ten patients underwent multiple LRTs. During a median follow-up of 11.5 months (range, 1.8-35.1), no grade III/IV adverse events attributable to nivolumab were observed. There were five instances of grade III/IV hypoalbuminemia or hyperbilirubinemia within 3 months after LRT. There were no nivolumab-related deaths, and 30-day mortality after LRT was 0%.
Selective serotonin reuptake inhibitors (SSRIs) are widely prescribed to treat anxiety and depression, yet they paradoxically increase anxiety during initial treatment. Acute administration of these drugs prior to learning can also enhance Pavlovian cued fear conditioning. This potentiation has been previously reported to depend upon the bed nucleus of the stria terminalis (BNST). Here, using temporary inactivation, we confirmed that the BNST is not necessary for the acquisition of cued or contextual fear memory. Systemic administration of the SSRI citalopram prior to fear conditioning led to an upregulation of the immediate early gene Arc (activity-regulated cytoskeleton-associated protein) in the oval nucleus of the BNST, and a majority of these neurons expressed the 5-HT2C receptor. Finally, local infusions of a 5-HT2C receptor antagonist directly into the oval nucleus of the BNST prevented the fear memory-enhancing effects of citalopram. These findings highlight the ability of the BNST circuitry to be recruited into gating fear and anxiety-like behaviors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.