Postoperative delirium prediction using machine learning models and preoperative electronic health record data

Background Accurate, pragmatic risk stratification for postoperative delirium (POD) is necessary to target preventative resources toward high-risk patients. Machine learning (ML) offers a novel approach to leveraging electronic health record (EHR) data for POD prediction. We sought to develop and internally validate a ML-derived POD risk prediction model using preoperative risk features, and to compare its performance to models developed with traditional logistic regression. Methods This was a retrospective analysis of preoperative EHR data from 24,885 adults undergoing a procedure requiring anesthesia care, recovering in the main post-anesthesia care unit, and staying in the hospital at least overnight between December 2016 and December 2019 at either of two hospitals in a tertiary care health system. One hundred fifteen preoperative risk features including demographics, comorbidities, nursing assessments, surgery type, and other preoperative EHR data were used to predict postoperative delirium (POD), defined as any instance of Nursing Delirium Screening Scale ≥2 or positive Confusion Assessment Method for the Intensive Care Unit within the first 7 postoperative days. Two ML models (Neural Network and XGBoost), two traditional logistic regression models (“clinician-guided” and “ML hybrid”), and a previously described delirium risk stratification tool (AWOL-S) were evaluated using the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, positive likelihood ratio, and positive predictive value. Model calibration was assessed with a calibration curve. Patients with no POD assessments charted or at least 20% of input variables missing were excluded. Results POD incidence was 5.3%. The AUC-ROC for Neural Net was 0.841 [95% CI 0. 816–0.863] and for XGBoost was 0.851 [95% CI 0.827–0.874], which was significantly better than the clinician-guided (AUC-ROC 0.763 [0.734–0.793], p < 0.001) and ML hybrid (AUC-ROC 0.824 [0.800–0.849], p < 0.001) regression models and AWOL-S (AUC-ROC 0.762 [95% CI 0.713–0.812], p < 0.001). Neural Net, XGBoost, and ML hybrid models demonstrated excellent calibration, while calibration of the clinician-guided and AWOL-S models was moderate; they tended to overestimate delirium risk in those already at highest risk. Conclusion Using pragmatically collected EHR data, two ML models predicted POD in a broad perioperative population with high discrimination. Optimal application of the models would provide automated, real-time delirium risk stratification to improve perioperative management of surgical patients at risk for POD.

Clinical Use of Tailored Computed Tomography to Prevent Poststernotomy Dehiscence

Background Morphological and tissue density analysis of the sternum can be performed in the preoperative computed tomography (CT). The purpose of this study was to analyze morphology and tissue density of sternum in CT and effect for comparison sternal instability. Methods Patients with sternal instability (n = 61) and sternal stability (n = 66) were enrolled in this study. All of the patients were studied using same thorax CT procedure. All the measurements were performed by one specific cardiovascular radiologist. The Hounsfield units (HUs) were measured in axial sections of the sternum trabecular bone. Results Sternal instability group mean HU was 75.36 ± 13.19 and sternal stability group HU was 90.24 ± 12.16 (p < 0.000). HU is the statically significant predictor of sternal instability. Conclusion Our study showed a significant correlation between the mean HU value of sternum and sternal instability. We think that it is important to evaluate the existing thorax CT while performing preoperative risk analysis for sternal dehiscence.

Risk Factors and Prevention Measures for Postoperative Sternomediastinitis (Literature Review)

Median sternotomy remains the most common access in cardiac surgery, while postoperative sternomediastinitis is one of the most severe complications of the transsternal approach. The article analyzes the preoperative risk factors for the development of this complication, including concomitant pathology, constitutional features, bad habits, length of hospital stay, and the urgency of the operation. It was also noted that intraoperative risk factors consist of technical errors in the performance of the operation, intraoperative features of the course of surgery, the nature of the choice of the shunt during myocardial vascularization and the final stage of the operation. Postoperative risk factors include the specific management of the postoperative period in cardiac surgery patients, which can lead to the development of sternomediastinitis. The analysis of measures taken by cardiac surgeons to prevent the development of this complication was carried out