Search

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., (© 2021. The Author(s).)

Background: Postoperative delirium is a common and serious problem for older adults. To better align local practices with delirium prevention consensus guidelines, we implemented a 5-component intervention followed by a quality improvement (QI) project at our institution., Methods: This hybrid implementation-effectiveness study took place at 2 adult hospitals within a tertiary care academic health care system. We implemented a 5-component intervention: preoperative delirium risk stratification, multidisciplinary education, written memory aids, delirium prevention postanesthesia care unit (PACU) orderset, and electronic health record enhancements between December 1, 2017 and June 30, 2018. This was followed by a department-wide QI project to increase uptake of the intervention from July 1, 2018 to June 30, 2019. We tracked process outcomes during the QI period, including frequency of preoperative delirium risk screening, percentage of "high-risk" screens, and frequency of appropriate PACU orderset use. We measured practice change after the interventions using interrupted time series analysis of perioperative medication prescribing practices during baseline (December 1, 2016 to November 30, 2017), intervention (December 1, 2017 to June 30, 2018), and QI (July 1, 2018 to June 30, 2019) periods. Participants were consecutive older patients (≥65 years of age) who underwent surgery during the above timeframes and received care in the PACU, compared to a concurrent control group <65 years of age. The a priori primary outcome was a composite of perioperative American Geriatrics Society Beers Criteria for Potentially Inappropriate Medication Use (Beers PIM) medications. The secondary outcome, delirium incidence, was measured in the subset of older patients who were admitted to the hospital for at least 1 night., Results: During the 12-month QI period, preoperative delirium risk stratification improved from 67% (714 of 1068 patients) in month 1 to 83% in month 12 (776 of 931 patients). Forty percent of patients were stratified as "high risk" during the 12-month period (4246 of 10,494 patients). Appropriate PACU orderset use in high-risk patients increased from 19% in month 1 to 85% in month 12. We analyzed medication use in 7212, 4416, and 8311 PACU care episodes during the baseline, intervention, and QI periods, respectively. Beers PIM administration decreased from 33% to 27% to 23% during the 3 time periods, with adjusted odds ratio (aOR) 0.97 (95% confidence interval [CI], 0.95-0.998; P = .03) per month during the QI period in comparison to baseline. Delirium incidence was 7.5%, 9.2%, and 8.5% during the 3 time periods with aOR of delirium of 0.98 (95% CI, 0.91-1.05, P = .52) per month during the QI period in comparison to baseline., Conclusions: A perioperative delirium prevention intervention was associated with reduced administration of Beers PIMs to older adults.

Background: Postoperative delirium is an important problem for surgical inpatients and was the target of a multidisciplinary quality improvement project at our institution. We developed and tested a semiautomated delirium risk stratification instrument, Age, WORLD backwards, Orientation, iLlness severity, Surgery-specific risk (AWOL-S), in 3 independent cohorts from our tertiary care hospital and describe its performance characteristics and impact on clinical care., Methods: The risk stratification instrument was derived with elective surgical patients who were admitted at least overnight and received at least 1 postoperative delirium screen (Nursing Delirium Screening Scale [NuDESC] or Confusion Assessment Method for the Intensive Care Unit [CAM-ICU]) and preoperative cognitive screening tests (orientation to place and ability to spell WORLD backward). Using data pragmatically collected between December 7, 2016, and June 15, 2017, we derived a logistic regression model predicting probability of delirium in the first 7 postoperative hospital days. A priori predictors included age, cognitive screening, illness severity or American Society of Anesthesiologists physical status, and surgical delirium risk. We applied model odds ratios to 2 subsequent cohorts ("validation" and "sustained performance") and assessed performance using area under the receiver operator characteristic curves (AUC-ROC). A post hoc sensitivity analysis assessed performance in emergency and preadmitted patients. Finally, we retrospectively evaluated the use of benzodiazepines and anticholinergic medications in patients who screened at high risk for delirium., Results: The logistic regression model used to derive odds ratios for the risk prediction tool included 2091 patients. Model AUC-ROC was 0.71 (0.67-0.75), compared with 0.65 (0.58-0.72) in the validation (n = 908) and 0.75 (0.71-0.78) in the sustained performance (n = 3168) cohorts. Sensitivity was approximately 75% in the derivation and sustained performance cohorts; specificity was approximately 59%. The AUC-ROC for emergency and preadmitted patients was 0.71 (0.67-0.75; n = 1301). After AWOL-S was implemented clinically, patients at high risk for delirium (n = 3630) had 21% (3%-36%) lower relative risk of receiving an anticholinergic medication perioperatively after controlling for secular trends., Conclusions: The AWOL-S delirium risk stratification tool has moderate accuracy for delirium prediction in a cohort of elective surgical patients, and performance is largely unchanged in emergent/preadmitted surgical patients. Using AWOL-S risk stratification as a part of a multidisciplinary delirium reduction intervention was associated with significantly lower rates of perioperative anticholinergic but not benzodiazepine, medications in those at high risk for delirium. AWOL-S offers a feasible starting point for electronic medical record-based postoperative delirium risk stratification and may serve as a useful paradigm for other institutions.

Introduction: Among older adults undergoing surgery, postoperative delirium is the most common complication. Cognitive impairment and dementia are major risk factors for postoperative delirium, yet they are frequently under‐recognized. It is well established that applying delirium preventive interventions to at‐risk individuals can reduce the likelihood of delirium by up to 40%. The aim of this study was to evaluate how often delirium preventive interventions are missing in patients at risk for delirium due to baseline cognitive impairment. Methods: We conducted a retrospective study using data from the observational study Perioperative Anesthesia Neurocognitive Disorder Assessment‐Geriatric (PANDA‐G) and clinical data from the University of California San Francisco delirium prevention bundle. Patients age 65+ received preoperative multidomain cognitive assessment as part of a research protocol prior to undergoing inpatient spine surgery at a single major academic institution. Results of the cognitive testing were not available to clinical teams. Using electronic medical records, we evaluated if patients who were cognitively impaired at baseline received delirium prevention orders, sleep orders, and avoidance of AGS Beers Criteria® potentially inappropriate medications. Results: Of the 245 patients included in the study, 42% were women. The mean [SD] age was 72 [5.2] years. Preoperative cognitive impairment was identified in 40% of participants (N = 98), and of these, 34% had postoperative delirium. Of patients with preoperative cognitive impairment, 45% did not receive delirium preventive orders, 43% received PIMs, and 49% were missing sleep orders. At least one of the three delirium preventive interventions was missing in 70% of the patients. Discussion: Undiagnosed preoperative cognitive impairment among older adults undergoing spine surgery is common. When cognitive test results were not available to clinicians, patients with baseline cognitive impairment frequently did not receive evidence‐based delirium preventive interventions. These findings highlight an opportunity to improve perioperative brain health care via preoperative cognitive assessment and clinical communication. [ABSTRACT FROM AUTHOR]