Delirium Prediction Research Articles

Could neutrophil-to-lymphocyte ratio predict mortality in community-dwelling older people with delirium superimposed on dementia?

Delirium superimposed on dementia (DSD) is associated with adverse outcomes in older adults. Nonetheless, little is known about the association between inflammatory markers and clinical outcomes of DSD. This research investigated the predictive value of the neutrophil-to-lymphocyte ratio (NLR) for short- and long-term mortality among community-dwelling older adults with DSD. This retrospective cohort study included 9755 older outpatients who were referred to a tertiary hospital between January 2010 and June 2021. All patients underwent a comprehensive geriatric assessment and routine laboratory tests. Delirium and dementia was diagnosed with the DSM-4 or DSM-5 criteria. We recorded information on mortality during 1year following the delirium episode. Among 615 patients with dementia, 170 (26.3%) had delirium. Patients with delirium were predominantly older, with higher Deyo-Charlson comorbidity index scores, lower general cognitive performance, lower functional capability, and higher anticholinergic burden compared to those without delirium. At the 1-year follow-up, the mortality rate of DSD was 29.3%. Multivariate analysis showed that NLR at admission was an independent predictor of 1-month mortality (HR = 1.03; 95% CI 1.00-1.05; p = 0.04) and 1-year mortality (HR = 1.02; 95% CI 1.01-1.05; p = 0.01) of DSD patients. NLR can predict prognosis in various diseases including cardiovascular disease, malignancies, and cerebrovascular disease, but as yet there is no similar prognostic measure in delirium. Moreover, recent previous studies demonstrated NLR is a potential marker for the prediction of delirium in older adults with different clinical settings. In the current study, we demonstrated that NLR is also a prognostic marker for DSD. NLR could be useful marker for predicting short- and long-term mortality in patients with DSD. However, further studies are needed to validate these findings.

A Novel Radiomics-Based Machine Learning Framework for Prediction of Acute Kidney Injury-Related Delirium in Patients Who Underwent Cardiovascular Surgery.

Acute kidney injury (AKI) can be caused by multiple etiologies and is characterized by a sudden and severe decrease in kidney function. Understanding the independent risk factors associated with the development of AKI and its early detection can refine the risk management and clinical decision-making of high-risk patients after cardiovascular surgery. A retrospective analysis was performed in a single teaching hospital between December 1, 2019, and December 31, 2020. The diagnostic performance of novel biomarkers was assessed using random forest, support vector machine, and multivariate logistic regression. The nomogram from multivariate analysis of risk factors associated with AKI indicated that only LVEF, red blood cell input, and ICUmvat contribute to AKI differentiation and that the difference is statistically significant (P < 0.05). Seven radiomics biomarkers were found among 65 patients to be highly correlated with AKI-associated delirium. The importance of the variables was determined using the multilayer perceptron model; fivefold cross-validation was applied to determine the most important delirium risk factors in radiomics of the hippocampus. Finally, we established a radiomics-based machine learning framework to predict AKI-induced delirium in patients who underwent cardiovascular surgery.

Development and Validation of a Delirium Prediction Model for Elderly Patients (DEEP)

Background: Delirium is common among hospitalized elderly patients. It is associated with complications and mortality. Objective: To develop and validate a predictive model for delirium among hospitalized elderly patients. Materials and Methods: The present study was a single-center, retrospective cohort study performed in 589 patients aged 60 years or older admitted to medical or surgical units at a tertiary hospital in Bangkok, Thailand between 2011 and 2017. Results: A sample was randomly split (70:30) into the derivation set (n=412; 120 with delirium) and validation set (n=177; 56 with delirium). In the derivation set, multiple logistic regression reveled six potential risk factors, which were older than 75 years, dementia, infection, liver cirrhosis, hypokalemia, and hyponatremia. Hosmer-Lemeshow goodness-of-fit test showed that the model had a good calibration (p=0.27). The model also had a good discrimination ability based on high area under receiver operating characteristic (AUROC) curve of 0.821 (95% CI 0.784 to 0.858). Regression coefficients were used to get a risk score which varied from 0 to 15. The optimal cutoff point of 4.5 or with a higher risk of delirium, gave a sensitivity of 65.8% (95% CI 56.6 to 74.2), a specificity of 82.2% (95% CI 77.3 to 86.4), a positive predictive value of 60.3% (95% CI 53.5 to 66.7), a negative predictive value of 85.4% (95% CI 82.0 to 88.3), and an accuracy of 77.4% (95% CI 73.1 to 81.4). The risk score was then applied to the derivation set resulting in a higher AUROC of 0.855 (95% CI 0.797 to 0.914). Conclusion: The present study was a simple predictive model that demonstrated good discrimination ability, high specificity, and an excellent negative predictive value. It may permit the use of early preventive intervention to reduce the incidence, severity, and complications of delirium. Keywords: Delirium; Elderly; Hypokalemia; Hyponatremia; Predictive model

Postoperative delirium is an independent factor influencing the length of stay of elderly patients in the intensive care unit and in hospital

PurposePostoperative delirium (POD) is an often unrecognized adverse event in older people after surgery. The aim of this subgroup analysis of the PRe-Operative Prediction of postoperative DElirium by appropriate SCreening (PROPDESC) trial in patients aged 70 years and older was to identify preoperative risk factors and the impact of POD on length of stay (LOS) in intensive care unit (ICU) and hospital.MethodsOf the total 1097 patients recruited at a German university hospital (from September 2018 to October 2019) in the PROPDESC prospective observational study, 588 patients aged 70 years and older (mean age 77.2 ± 4.7 years) were included for subgroup analysis. The primary endpoint POD was considered positive if one of the following tests were positive on any of the five postoperative visit days: Confusion Assessment Method for ICU (CAM-ICU), Confusion Assessment Method (CAM), 4'A's (4AT) and Delirium Observation Scale (DOS). Trained doctoral students carried out these visitations and additionally the nursing staff were interviewed for completion of the DOS. To evaluate the independent effect of POD on LOS in ICU and in hospital, a multi-variable linear regression analysis was performed.ResultsThe POD incidence was 25.9%. The results of our model showed POD as an independent predictor for a prolonged LOS in ICU (36%; 95% CI 4–78%; < 0.001) and in hospital (22%; 95% CI 4–43%; < 0.001).ConclusionPOD has an independent impact on LOS in ICU and in hospital. Based on the effect of POD for the elderly, a standardized risk screening is required.Trail registrationGerman Registry for Clinical Studies: DRKS00015715.

PRe-Operative Prediction of postoperative DElirium by appropriate SCreening (PROPDESC) development and validation of a pragmatic POD risk screening score based on routine preoperative data

Study objectiveTo develop and validate a pragmatic risk screening score for postoperative delirium (POD) based on routine preoperative data. DesignProspective observational monocentric trial. SettingPreoperative data and POD assessment were collected from cardiac and non-cardiac surgical patients at a German university hospital. Data-driven modelling approaches (step-wise vs. component-wise gradient boosting on complete and restricted predictor set) were compared to predictor selection by experts (investigators vs. external Delphi survey). PatientsInpatients (≥60 years) scheduled for elective surgery lasting more than 60 min. MeasurementsPOD was assessed daily during first five postoperative or post-sedation days with confusion assessment method for intensive and standard care unit (CAM-ICU/CAM), 4 ‘A's test (4AT) and Delirium Observation Screening (DOS) scale. Main resultsFrom 1023 enrolled patients, 978 completed observations were separated in development (n = 600; POD incidence 22.2%) and validation (n = 378; POD incidence 25.7%) cohorts. Data-driven approaches generated models containing laboratory values, surgical discipline and several items on cognitive and quality of life assessment, which are time consuming to collect. Boosting on complete predictor set yielded the highest bootstrapped prediction accuracy (AUC 0.767) by selecting 12 predictors, with substantial dependence on cardiac surgery. Investigators selected via univariate comparison age, ASA and NYHA classification, surgical risk as well as ´serial subtraction´ and ´sentence repetition´ of the Montreal Cognitive Assessment (MoCA) to enable rapid collection of their risk score for preoperative screening. This investigator model provided slightly lower bootstrapped prediction accuracy (AUC 0.746) but proved to have robust results on validation cohort (AUC 0.725) irrespective of surgical discipline. Simplification of the investigator model by scaling and rounding of regression coefficients into the PROPDESC score achieved a comparable precision on the validation cohort (AUC 0.729). ConclusionsThe PROPDESC score showed promising performance on a separate validation cohort in predicting POD based on routine preoperative data. Suitability for universal screening needs to be shown in a large external validation.

Prevalence of delirium in the postoperative period of cardiac surgery

In the Intensive Care Unit, delirium is a common yet underdiagnosed form of organ dysfunction, and its contribution to patient outcomes is unclear. Accurate prediction of delirium in the Intensive Care Unit may facilitate efficient use of early preventive strategies and stratification of Intensive Care Unit patients by delirium risk in clinical research, but the optimal delirium prediction model to use is unclear. In this paper the authors start the search for the predictive model by determining the occurrence of the major risk factors and conclude that all of them play a role with different grades of intensity but they all should be considered.

Postoperative delirium and its relationship with biomarkers for dementia: a meta-analysis.

This study seeks to identify Alzheimer's and related dementias (ADRD) biomarkers associated with postoperative delirium (POD) via meta-analysis. A comprehensive search was conducted. Studies met the following inclusion criteria: >18 years of age, identified POD with standardized assessment, and biomarker measured in the AT(N)-X (A = amyloid, T = tau, (N)=neurodegeneration, X-Other) framework. Exclusion criteria: focus on prediction of delirium, delirium superimposed on dementia, other neurologic or psychiatric disorders, or terminal delirium. Reviewers extracted and synthesized data for the meta-analysis. Meta-analysis. Patients with POD. Primary outcome: association between POD and ATN-X biomarkers. Secondary outcomes involved sample heterogeneity. 28 studies were included in this meta-analysis. Studies focused on inflammatory and neuronal injury biomarkers; there were an insufficient number of studies for amyloid and tau biomarker analysis. Two inflammatory biomarkers (IL-6, and CRP) showed a significant relationship with POD (IL-6 n = 10, standardized mean difference (SMD): 0.53, 95% CI: 0.36-0.70; CRP n = 14, SMD: 0.53, 95% CI: 0.33-0.74). Two neuronal injury biomarkers (blood-based S100B and NfL) were positively associated with POD (S100B n = 5, SMD: 0.40, 95% CI: 0.11-0.69; NFL n = 2, SMD: 0.93, 95% CI: 0.28-1.57). Of note, many analyses were impacted by significant study heterogeneity. This meta-analysis identified an association between certain inflammatory and neuronal injury biomarkers and POD. Future studies will need to corroborate these relationships and include amyloid and tau biomarkers in order to better understand the relationship between POD and ADRD.

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

BackgroundAccurate, 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.MethodsThis 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.ResultsPOD 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.ConclusionUsing 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.

Inter-Subject Prediction of Pediatric Emergence Delirium Using Feature Selection and Classification from Spontaneous EEG Signals

Inter-Subject Prediction of Pediatric Emergence Delirium Using Feature Selection and Classification from Spontaneous EEG Signals

Blood urea nitrogen to creatinine ratio as a potential biomarker for prediction of hypoactive delirium in critical illness patients

Blood urea nitrogen to creatinine ratio as a potential biomarker for prediction of hypoactive delirium in critical illness patients

Evidence-based strategies to reduce the incidence of postoperative delirium: a narrative review.

Delirium is one of the most commonly occurring postoperative complications in older adults. It occurs due to the vulnerability of cerebral functioning to pathophysiological stressors. Identification of those at increased risk of developing delirium early in the surgical pathway provides an opportunity for modification of predisposing and precipitating risk factors and effective shared decision-making. No single delirium prediction tool is used widely in surgical settings. Multi-component interventions to prevent delirium involve structured risk factor modification supported by geriatrician input; these are clinically efficacious and cost effective. Barriers to the widespread implementation of such complex interventions exist, resulting in an 'implementation gap'. There is a lack of evidence for pharmacological prophylaxis for the prevention of delirium. Current evidence suggests that avoidance of peri-operative benzodiazepines, careful titration of anaesthetic depth guided by processed electroencephalogram monitoring and treatment of pain are the most effective strategies to minimise the risk of delirium. Addressing postoperative delirium requires a collaborative, whole pathway approach, beginning with the early identification of those patients who are at risk. The research agenda should continue to examine the potential for pharmacological prophylaxis to prevent delirium while also addressing how successful models of delirium prevention can be translated from one setting to another, underpinned by implementation science methodology.

Inclusion of interleukin-6 improved performance of postoperative delirium prediction for patients undergoing coronary artery bypass graft (POD-CABG): A derivation and validation study

BackgroundPatients undergoing coronary artery bypass graft (CABG) are at high risk for developing postoperative delirium (POD). A simple prediction rule may benefit patients from early identification of POD followed by adequate preventive strategies. The purpose of the current study was to develop and validate a POD prediction rule for patients undergoing CABG (POD-CABG), by considering all possible perioperative factors. MethodsIn this prospective cohort study, patients who underwent first elective isolated CABG were continuously enrolled from May 2014 to November 2015 in a tertiary hospital. Delirium was assessed using the Confusion Assessment Method for Intensive Care Unit. Patients’ perioperative risk factors were collected through interviews and review of medical records. The area under receiver-operating characteristic curve (AUC) was used to assess the overall performance of the predictive rule. ResultsA total of 242 and 148 patients were enrolled in the derivation and validation cohorts, respectively. Multiple logistic regression analysis identified seven variables that were independently associated with POD: age (≥65 years), gender (female), history of myocardial infarction and diabetes mellitus, postoperative atrial fibrillation, the use of intra-aortic balloon pump, and serum interleukin-6 ≥478 pg/ml at 18 hours after surgery. The AUC of the POD-CABG was 0.84 (95% CI, 0.79-0.90) in the derivation cohort, and was 0.86 (95% CI, 0.80-0.91) after bootstrap resampling. The AUC was 0.81 (95% CI, 0.73-0.88) after the POD-CABG was applied to the validation cohort. ConclusionsThe POD-CABG with inclusion of interleukin-6 demonstrated good performance in predicting POD.

Hospital-induced Delirium among Medical Older Adults: Evaluating the Veracity of Prognostic Models

Several prognostic models have been developed and validated for delirium prediction among older adults. However, model development and validation studies need to be evaluated for risk of bias to establish the veracity of the prognostic models. This is a critical step before they can be implemented in clinical practice. Multiple systematic reviews have evaluated prognostic models of hospital-induced delirium. However, none of the existing systematic reviews evaluated the validity of models for non-surgical, medical hospitalized older adults. We conducted a scoping review to evaluate the validity of existing prognostic models of hospital-induced delirium in medical older adults. CINAHL, PsycINFO, PubMed, and Web of Science were searched for original studies. The database search yielded 4,312 records. Five studies were included in the qualitative synthesis. All the studies claimed to have developed valid prognostic models. However, the risk of bias assessment revealed that existing prognostic models of hospital-induced delirium in medical older adults are at a high risk of bias. Collectively, the statistical analysis was the greatest source of bias. Notably, while we have seen a proliferation of prognostic models for use in the surgical older adult population, efforts at developing prognostic models in the medical older adult population seem to have declined since the early 1990s. Newer methods of data collection, such as data mining of electronic health records, and statistical analysis, such as machine learning, have shown promise in accurate prediction of hospital-induced delirium while overcoming many challenges associated with manual data collection and traditional statistical analyses.

Longitudinal validation of an electronic health record delirium prediction model applied at admission in COVID-19 patients

ObjectiveTo validate a previously published machine learning model of delirium risk in hospitalized patients with coronavirus disease 2019 (COVID-19). MethodUsing data from six hospitals across two academic medical networks covering care occurring after initial model development, we calculated the predicted risk of delirium using a previously developed risk model applied to diagnostic, medication, laboratory, and other clinical features available in the electronic health record (EHR) at time of hospital admission. We evaluated the accuracy of these predictions against subsequent delirium diagnoses during that admission. ResultsOf the 5102 patients in this cohort, 716 (14%) developed delirium. The model's risk predictions produced a c-index of 0.75 (95% CI, 0.73–0.77) with 27.7% of cases occurring in the top decile of predicted risk scores. Model calibration was diminished compared to the initial COVID-19 wave. ConclusionThis EHR delirium risk prediction model, developed during the initial surge of COVID-19 patients, produced consistent discrimination over subsequent larger waves; however, with changing cohort composition and delirium occurrence rates, model calibration decreased. These results underscore the importance of calibration, and the challenge of developing risk models for clinical contexts where standard of care and clinical populations may shift.

Development of a delirium predictive model for adult trauma patients in an emergency and critical care center: a retrospective study

BackgroundDelirium has been shown to prolong the length of intensive care unit stay, hospitalization, and duration of ventilatory control, in addition to increasing the use of sedatives and increasing the...

Physiological Assessment of Delirium Severity: The Electroencephalographic Confusion Assessment Method Severity Score (E-CAM-S).

Delirium is a common and frequently underdiagnosed complication in acutely hospitalized patients, and its severity is associated with worse clinical outcomes. We propose a physiologically based method to quantify delirium severity as a tool that can help close this diagnostic gap: the Electroencephalographic Confusion Assessment Method Severity Score (E-CAM-S). Retrospective cohort study. Single-center tertiary academic medical center. Three-hundred seventy-three adult patients undergoing electroencephalography to evaluate altered mental status between August 2015 and December 2019. None. We developed the E-CAM-S based on a learning-to-rank machine learning model of forehead electroencephalography signals. Clinical delirium severity was assessed using the Confusion Assessment Method Severity (CAM-S). We compared associations of E-CAM-S and CAM-S with hospital length of stay and inhospital mortality. E-CAM-S correlated with clinical CAM-S (R = 0.67; p < 0.0001). For the overall cohort, E-CAM-S and CAM-S were similar in their strength of association with hospital length of stay (correlation = 0.31 vs 0.41, respectively; p = 0.082) and inhospital mortality (area under the curve = 0.77 vs 0.81; p = 0.310). Even when restricted to noncomatose patients, E-CAM-S remained statistically similar to CAM-S in its association with length of stay (correlation = 0.37 vs 0.42, respectively; p = 0.188) and inhospital mortality (area under the curve = 0.83 vs 0.74; p = 0.112). In addition to previously appreciated spectral features, the machine learning framework identified variability in multiple measures over time as important features in electroencephalography-based prediction of delirium severity. The E-CAM-S is an automated, physiologic measure of delirium severity that predicts clinical outcomes with a level of performance comparable to conventional interview-based clinical assessment.

A Machine Learning-Based Algorithm for the Prediction of Intensive Care Unit Delirium (PRIDE): Retrospective Study.

BackgroundDelirium frequently occurs among patients admitted to the intensive care unit (ICU). There is limited evidence to support interventions to treat or resolve delirium in patients who have already developed delirium. Therefore, the early recognition and prevention of delirium are important in the management of critically ill patients.ObjectiveThis study aims to develop and validate a delirium prediction model within 24 hours of admission to the ICU using electronic health record data. The algorithm was named the Prediction of ICU Delirium (PRIDE).MethodsThis is a retrospective cohort study performed at a tertiary referral hospital with 120 ICU beds. We only included patients who were 18 years or older at the time of admission and who stayed in the medical or surgical ICU. Patients were excluded if they lacked a Confusion Assessment Method for the ICU record from the day of ICU admission or if they had a positive Confusion Assessment Method for the ICU record at the time of ICU admission. The algorithm to predict delirium was developed using patient data from the first 2 years of the study period and validated using patient data from the last 6 months. Random forest (RF), Extreme Gradient Boosting (XGBoost), deep neural network (DNN), and logistic regression (LR) were used. The algorithms were externally validated using MIMIC-III data, and the algorithm with the largest area under the receiver operating characteristics (AUROC) curve in the external data set was named the PRIDE algorithm.ResultsA total of 37,543 cases were collected. After patient exclusion, 12,409 remained as our study population, of which 3816 (30.8%) patients experienced delirium incidents during the study period. Based on the exclusion criteria, out of the 96,016 ICU admission cases in the MIMIC-III data set, 2061 cases were included, and 272 (13.2%) delirium incidents occurred. The average AUROCs and 95% CIs for internal validation were 0.916 (95% CI 0.916-0.916) for RF, 0.919 (95% CI 0.919-0.919) for XGBoost, 0.881 (95% CI 0.878-0.884) for DNN, and 0.875 (95% CI 0.875-0.875) for LR. Regarding the external validation, the best AUROC were 0.721 (95% CI 0.72-0.721) for RF, 0.697 (95% CI 0.695-0.699) for XGBoost, 0.655 (95% CI 0.654-0.657) for DNN, and 0.631 (95% CI 0.631-0.631) for LR. The Brier score of the RF model is 0.168, indicating that it is well-calibrated.ConclusionsA machine learning approach based on electronic health record data can be used to predict delirium within 24 hours of ICU admission. RF, XGBoost, DNN, and LR models were used, and they effectively predicted delirium. However, with the potential to advise ICU physicians and prevent ICU delirium, prospective studies are required to verify the algorithm’s performance.

Prediction of Postictal Delirium Following Status Epilepticus in the ICU: First Insights of an Observational Cohort Study.

To identify early predictors of postictal delirium in adult patients after termination of status epilepticus. Retrospective study. ICUs at a Swiss tertiary academic medical center. Status epilepticus patients treated on the ICUs for longer than 24 hours from 2012 to 2018. None. Primary outcome was postictal delirium during post-status epilepticus treatment defined as an Intensive Care Delirium Screening Checklist greater than or equal to 4. Associations with postictal delirium were secondary outcomes. A time-dependent multivariable Cox proportional hazards model was used to identify risks of postictal delirium. It included variables that differed between patients with and without delirium and established risk factors for delirium (age, sex, number of inserted catheters, illness severity [quantified by the Sequential Organ Failure Assessment and Status Epilepticus Severity Score], neurodegenerative disease, dementia, alcohol/drug consumption, infections, coma during status epilepticus, dose of benzodiazepines, anesthetics, and mechanical ventilation). Among 224 patients, post-status epilepticus Intensive Care Delirium Screening Checklist was increased in 83% with delirium emerging in 55% with a median duration of 2 days (interquartile range 1-3 d). Among all variables, only the history of alcohol and/or drug consumption was associated with increased hazards for delirium in multivariable analyses (hazard ratio = 3.35; 95% CI, 1.53-7.33). Our study provides first exploratory insights into the risks of postictal delirium in adult status epilepticus patients treated in the ICU. Delirium following status epilepticus is frequent, lasting mostly 2-3 days. Our findings that with the exception of a history of alcohol and/or drug consumption, other risk factors of delirium were not found to be associated with a risk of postictal delirium may be related to the limited sample size and the exploratory nature of our study. Further investigations are needed to investigate the role of established risk factors in other status epilepticus cohorts. In the meantime, our results indicate that the risk of delirium should be especially considered in patients with a history of alcohol and/or drug consumption.

Machine Learning Algorithm Using Electronic Chart-Derived Data to Predict Delirium After Elderly Hip Fracture Surgeries: A Retrospective Case-Control Study.

Background: Elderly patients undergoing hip fracture repair surgery are at increased risk of delirium due to aging, comorbidities, and frailty. But current methods for identifying the high risk of delirium among hospitalized patients have moderate accuracy and require extra questionnaires. Artificial intelligence makes it possible to establish machine learning models that predict incident delirium risk based on electronic health data.Methods: We conducted a retrospective case-control study on elderly patients (≥65 years of age) who received orthopedic repair with hip fracture under spinal or general anesthesia between June 1, 2018, and May 31, 2019. Anesthesia records and medical charts were reviewed to collect demographic, surgical, anesthetic features, and frailty index to explore potential risk factors for postoperative delirium. Delirium was assessed by trained nurses using the Confusion Assessment Method (CAM) every 12 h during the hospital stay. Four machine learning risk models were constructed to predict the incidence of postoperative delirium: random forest, eXtreme Gradient Boosting (XGBoosting), support vector machine (SVM), and multilayer perception (MLP). K-fold cross-validation was deployed to accomplish internal validation and performance evaluation.Results: About 245 patients were included and postoperative delirium affected 12.2% (30/245) of the patients. Multiple logistic regression revealed that dementia/history of stroke [OR 3.063, 95% CI (1.231, 7.624)], blood transfusion [OR 2.631, 95% CI (1.055, 6.559)], and preparation time [OR 1.476, 95% CI (1.170, 1.862)] were associated with postoperative delirium, achieving an area under receiver operating curve (AUC) of 0.779, 95% CI (0.703, 0.856).The accuracy of machine learning models for predicting the occurrence of postoperative delirium ranged from 83.67 to 87.75%. Machine learning methods detected 16 risk factors contributing to the development of delirium. Preparation time, frailty index uses of vasopressors during the surgery, dementia/history of stroke, duration of surgery, and anesthesia were the six most important risk factors of delirium.Conclusion: Electronic chart-derived machine learning models could generate hospital-specific delirium prediction models and calculate the contribution of risk factors to the occurrence of delirium. Further research is needed to evaluate the significance and applicability of electronic chart-derived machine learning models for the detection risk of delirium in elderly patients undergoing hip fracture repair surgeries.

Validation of E-PRE-DELIRIC in cardiac surgical ICU delirium: A retrospective cohort study.

The early prediction model for delirium in intensive care units (ICUs)-E-PRE-DELIRIC-has been created to predict delirium development during the length of stay in ICUs. However, there have been few early predictive models for delirium in the cardiac surgical ICU (CSICU), and the predictive ability of the E-PRE-DELIRIC among patients following cardiac surgeries is still unknown. To validate the performance of E-PRE-DELIRIC in CSICU. A retrospective cohort study. Data were retrospectively extracted from the electronic records for patients admitted in CSICU from January 2018 to December 2018 in a tertiary teaching hospital in China. Adult patients were included following the criteria of the E-PRE-DELIRIC model. Predictors, including age, history of cognitive impairment, history of alcohol abuse, urgent admission, use of corticosteroids, respiratory failure, blood urea nitrogen, and mean arterial pressure, at the time of ICU admission were retrieved, and delirium was assessed twice a day using the Confusion Assessment Method for the ICU. The performance of the E-PRE-DELIRIC model was evaluated by area under receiver operator characteristic curve, precision-recall curve (AUPRC), Hosmer-Lemeshow (HL) test, and calibration belt. Of the 725 patients included, 120 (16.6%) developed delirium. The AUROC was 0.54 (95% confidence interval [CI], 0.48-0.59), and the AUPRC was 0.18 (95% CI, 0.12-0.20). The HL test showed a significant difference between predicted probability and delirium occurrence (χ2 = 17.326, P = .027), and the overestimation chance of the E-PRE-DELIRIC score was 0.24 to 0.43. The E-PRE-DELIRIC model has poor-to-fair predictive value in this study; thus, its application among the CSICU patients is limited. Development of reliable and validated tools for early prediction of delirium in CSICU is required. Early prediction of delirium risk at CSICU admission is of vital importance and could provide timely information to caregivers. However, the E-PRE-DELIRIC model should be applied cautiously in the CSICU because of the significant probability of over-estimating the risk of developing delirium.