Delirium Prediction Research Articles

Prediction of Postoperative Delirium in Older Adults from Preoperative Cognition and Occipital Alpha Power from Resting-State Electroencephalogram.

Postoperative delirium is the most common complication following surgery among older adults, and has been consistently associated with increased mortality and morbidity, cognitive decline, and loss of independence, as well as markedly increased health-care costs. Electroencephalography (EEG) spectral slowing has frequently been observed during episodes of delirium, whereas intraoperative frontal alpha power is associated with postoperative delirium. We sought to identify preoperative predictors that could identify individuals at high risk for postoperative delirium, which could guide clinical decision-making and enable targeted interventions to potentially decrease delirium incidence and postoperative delirium-related complications. In this prospective observational study, we used machine learning to evaluate whether baseline (preoperative) cognitive function and resting-state EEG could be used to identify patients at risk for postoperative delirium. Preoperative resting-state EEGs and the Montreal Cognitive Assessment were collected from 85 patients (age = 73 +- 6.4 years, 12 cases of delirium) undergoing elective surgery. The model with the highest f1-score was subsequently validated in an independent, prospective cohort of 51 older adults (age = 68 +- 5.2 years, 6 cases of delirium) undergoing elective surgery. Occipital alpha powers have higher f1-score than frontal alpha powers and EEG spectral slowing in the training cohort. Occipital alpha powers were able to predict postoperative delirium with AUC, specificity and accuracy all >90%, and sensitivity >80%, in the validation cohort. Notably, models incorporating transformed alpha powers and cognitive scores outperformed models incorporating occipital alpha powers alone or cognitive scores alone. While requiring prospective validation in larger cohorts, these results suggest that strong prediction of postoperative delirium may be feasible in clinical settings using simple and widely available clinical tools. Additionally, our results suggested that the thalamocortical circuit exhibits different EEG patterns under different stressors, with occipital alpha powers potentially reflecting baseline vulnerabilities.

Data-driven Machine Learning Models for Risk Stratification and Prediction of Emergence Delirium in Pediatric Patients Underwent Tonsillectomy/Adenotonsillectomy.

In the pediatric surgical population, Emergence Delirium (ED) poses a significant challenge. This study aims to develop and validate machine learning (ML) models to identify key features associated with ED and predict its occurrence in children undergoing tonsillectomy or adenotonsillectomy. The analysis involved data cleaning, exploratory data analysis (EDA), supervised predictive modeling, and unsupervised learning on a medical dataset (n = 423). After preliminary data cleaning, EDA encompassed plotting histograms, boxplots, pairplots, and correlation heatmaps to understand variable distributions and relationships. Four predictive models were trained including logistic regression (LR), random forest (RF), Support Vector Machine (SVM), and Gradient Boosting (XGBoost). The models were evaluated and compared using Receiver Operating Characteristic (ROC) Area Under the Curve (AUC), precision, recall, and feature importance. The RF model showed better performance and was used for the test (AUC-ROC 0.96, precision 1.00, and recall 0.92 on the validation set). K-means clustering was applied to find groups within the data. Elbow method and silhouette scores were used to determine the optimal number of clusters. The formed clusters were analyzed by aggregating features to understand the characteristics of each cluster. EDA revealed significant positive correlations between age, weight, American Society of Anesthesiologists (ASA) health score, and surgery duration with the risk of developing ED. Among the ML models, RF achieved the highest performance. Key predictive variables, based on the model's feature importance, included delirium screening scales, extubation time, and time to regain consciousness. Unsupervised K-means clustering identified 2-3 optimal clusters, which represented distinct patient subgroups: younger, healthier, low-risk individuals (cluster 0), and older patients with increasing chronic disease burden, higher delirium screening scores, and consequently higher post-operative delirium risk (clusters 1 and 2). ML techniques are valuable tools for extracting insights and making accurate predictions from healthcare data. High-performing algorithm-based models can be implemented for clinical decision support systems, facilitating early identification and intervention for ED in pediatric patients. By investigating various variables, it is possible to assess risk and implement preventive measures effectively. Furthermore, unsupervised clustering reveals distinct patient subgroups, enabling personalized perioperative management strategies and enhancing overall patient care.

Authors' response to “Comment on Gao and Gan (2024) ‘A novel nomogram for the prediction of subsyndromal delirium in patients in intensive care units: A prospective, nested case-controlled study’”

Authors' response to “Comment on Gao and Gan (2024) ‘A novel nomogram for the prediction of subsyndromal delirium in patients in intensive care units: A prospective, nested case-controlled study’”

Nomogram-based prediction of emergence delirium in elderly patients undergoing laparoscopic surgery

BackgroundA nomogram model has been developed to forecast the incidence of emergence delirium (ED) in elderly patients undergoing laparoscopic surgery. MethodsA secondary analysis was performed on the eMODIPOD trial, which involved elective laparoscopic surgery patients at Xiangya Hospital between October 2017 and October 2019. To assess ED, the Richmond Agitation Sedation Scale (RASS) was combined with the Intensive Care Unit (CAM-ICU) scale, and patients were categorized as ED or non-ED based on the results. The two groups were compared in terms of perioperative information and test results. Logistic regression was utilized to investigate factors contributing to ED occurrence in elderly patients following laparoscopic surgery, and a nomogram was constructed to depict this. The diagnostic performance was evaluated through the utilization of the area under the receiver operating characteristic curve (AUROC) and a calibration plot. Simultaneously, to appraise the clinical value, decision curve analysis (DCA) was employed to assess the clinical value. ResultsOf the 565 patients subject to laparoscopic surgery, 94 were subsequently diagnosed with emergence delirium (ED), yielding a positive rate of 16.6 %. The developed Nomogram model was an amalgamation of several variables, which included preoperative cognitive function, educational level, dezocine, penehyclidine, ASA grading, blood loss, fluid infusion, and Post Anesthesia Care Unit-numerical rating scale (PACU-NRS). The model’s performance was commendable in terms of its discrimination power, as signified by an area under the curve of 0.713(95 % CI = 0.655–0.772). Furthermore, it exhibited adequate calibration, as affirmed by the Hosmer-Lemeshow test (χ2 = 2.243, p = 0.326). Internal validation of the model further emphasized its superior discrimination and calibration capabilities. The decision curve analysis pointed out that when the threshold probability exceeded 0.1, the Nomogram model delivered more substantial benefits compared to the treat-all and treat-none approaches. ConclusionsThis scoring system represents the pioneering Nomogram model utilized for predicting emergence delirium (ED) in geriatric patients undergoing laparoscopic surgery. It exhibits robust efficacy in forecasting the risk of ED, thereby furnishing valuable insights for the prevention, management, and treatment of ED.

Effectiveness of a delirium risk assessment and multidisciplinary care approach in reducing delirium incidence among surgical intensive care unit patients: A retrospective pre-post intervention study

BackgroundDelirium is a common complication in intensive care unit (ICU) patients. It can lead to various adverse events. In this study, we investigated the effectiveness of combining the use of the PREdiction of DELIRium (PRE-DELIRIC) model for delirium risk assessment and the use of a multicomponent care bundle for delirium assessment, prevention, and care in terms of reductions in the incidence of delirium among surgical ICU patients. MethodsThis retrospective study included surgical ICU patients who had received PRE-DELIRIC-guided SMART/SmART care (SMART care: SmART bundle plus multidisciplinary team; SmART care: Sleep/sweet sense of home (creating a comforting and restful environment for patients), Assessment (regular and thorough evaluation of patient needs and conditions), Release (revised endotracheal tube care/removal, restraint device care, and immobility reduction for patient comfort), and Time (reorientation of time to optimize patient care schedules) in our hospital between May 2022 and March 2023 (intervention group) and individuals who had received usual care between January 2021 and April 2022 (historical control group). The SmART intervention involves providing care in the following domains: sleep/sweet sense of home, assessment, release, and time. Patients with a PRE-DELIRIC score of >30% received SMART care, which includes multidisciplinary (physicians, pharmacists, respiratory therapists, and physiotherapists) care in addition to SmART care. For the control group, usual care was provided following the guidelines for the prevention and management of pain, agitation, delirium, immobility, and sleep disruption. The primary outcome was delirium incidence during ICU stay, which was assessed using the Intensive Care Delirium Screening Checklist. The secondary outcomes were the duration of ICU stay, rate of unplanned self-extubation, and status of ICU discharge. ResultsThe intervention and control groups comprised 184 and 197 patients, respectively; their mean ages were 63.7 ± 18.4 years and 62.4 ± 19.5 years, respectively. The incidence of delirium was significantly lower (p = 0.001) in the intervention group (22.3%) than in the control group (47.7%). ConclusionOur findings suggest that the PRE-DELIRIC-guided SMART/SmART care intervention is effective in preventing and managing delirium among surgical ICU patients.

Emergence delirium: an overview with an emphasis on the use of electroencephalography in its management.

Emergence delirium remains a clinically significant issue, which often leads to distress among pediatric patients, parents, and staff in the short term; and may also result in postoperative maladaptive behaviors persisting for weeks to months. Although several diagnostic tools are available, the Pediatric Anesthesia Emergence Delirium Scale is most often utilized. Many risk factors contributing to the likelihood of a pediatric patient developing emergence delirium have been identified; however, its accurate prediction remains challenging. Recently, intraoperative electroencephalographic monitoring has been used to improve the prediction of emergence delirium. Similarly, it may also prevent emergence delirium if the anesthesiologist ensures that the at-risk patient rouses only after the onset of appropriate electroencephalogram patterns, thus indicating a change to natural sleep. Prediction of at-risk patients is crucial; preventing emergence delirium may begin early during patient preparation by using non-pharmacological methods (i.e., the ADVANCE program). Intraoperative electroencephalographic monitoring can predict emergence delirium. This review also discusses a range of pharmacological treatment options which may assist the anesthesiologist in preventing emergence delirium among at-risk patients.

Machine learning-based delirium prediction in surgical in-patients: a prospective validation study.

Delirium is a syndrome that leads to severe complications in hospitalized patients, but is considered preventable in many cases. One of the biggest challenges is to identify patients at risk in a hectic clinical routine, as most screening tools cause additional workload. The aim of this study was to validate a machine learning (ML)-based delirium prediction tool on surgical in-patients undergoing a systematic assessment of delirium. 738 in-patients of a vascular surgery, a trauma surgery and an orthopedic surgery department were screened for delirium using the DOS scale twice a day over their hospital stay. Concurrently, delirium risk was predicted by the ML algorithm in real-time for all patients at admission and evening of admission. The prediction was performed automatically based on existing EHR data and without any additional documentation needed. 103 patients (14.0%) were screened positive for delirium using the DOS scale. Out of them, 85 (82.5%) were correctly identified by the ML algorithm. Specificity was slightly lower, detecting 463 (72.9%) out of 635 patients without delirium. The AUROC of the algorithm was 0.883 (95% CI, 0.8523-0.9147). In this prospective validation study, the implemented machine-learning algorithm was able to detect patients with delirium in surgical departments with high discriminative performance. In future, this tool or similar decision support systems may help to replace time-intensive screening tools and enable efficient prevention of delirium.

Predictiveness of preoperative laboratory values for postoperative delirium.

Postoperative delirium (POD) is a common postoperative complication, especially in patients over 60 years, with an incidence ranging from 15% to 50%. In most cases, POD manifests in the first 5 days after surgery. Multiple contributing risk factors for POD have been detected. Besides the predisposing factors such as higher age, cognitive impairment, high blood pressure, atrial fibrillation, and past stroke, pathophysiological mechanisms like neuroinflammation are also considered as contributing factors. In a subanalysis of the "PRe- Operative Prediction of postoperative DElirium by appropriate SCreening" (PROPDESC) study, the preoperative laboratory values of sodium, potassium, total protein, hemoglobin concentration (Hgb), and white blood cells as well as the biomarkers creatinine, HbA1c, NT-pro-BNP, high sensitive Troponin T (hsTnT), and C-reactive protein (CRP) were assessed to investigate a possible relationship to the occurrence of POD. After correction for age, physical status classification, surgery risk after Johns Hopkins, and operative discipline (cardiac surgery vs. noncardiac surgery), male patients with a Hgb <13 g/dL had significantly higher odds for POD (p = 0.025). Furthermore, patients with CRP ≥ 10 mg/L, HbA1c value ≥ 8.5% as well as patients with hypernatraemia (>145 mmol/L) presented significantly higher odds to develop POD (p = 0.011, p < 0.001, and p = 0.021, respectively). A raised (>14-52 ng/L) or high (>52 ng/L) hsTnT value was also associated with a significantly higher chance for POD compared to the patient group with hsTnT <14 ng/L (p < 0.001 and p = 0.016, respectively). Preoperative Hgb, CRP, HbA1c, sodium, and hsTnT could be used to complement and refine the preoperative screening for patients at risk for POD. Further studies should track these correlations to investigate the potential of targeted POD protection and enabling hospital staff to initiate POD-preventing measures in time.

Machine learning for the prediction of delirium in elderly intensive care unit patients

Machine learning for the prediction of delirium in elderly intensive care unit patients

Machine learning-based model to predict delirium in patients with advanced cancer treated with palliative care: a multicenter, patient-based registry cohort

This study aimed to present a new approach to predict to delirium admitted to the acute palliative care unit. To achieve this, this study employed machine learning model to predict delirium in patients in palliative care and identified the significant features that influenced the model. A multicenter, patient-based registry cohort study in South Korea between January 1, 2019, and December 31, 2020. Delirium was identified by reviewing the medical records based on the criteria of the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. The study dataset included 165 patients with delirium among 2314 patients with advanced cancer admitted to the acute palliative care unit. Seven machine learning models, including extreme gradient boosting, adaptive boosting, gradient boosting, light gradient boosting, logistic regression, support vector machine, and random forest, were evaluated to predict delirium in patients with advanced cancer admitted to the acute palliative care unit. An ensemble approach was adopted to determine the optimal model. For k-fold cross-validation, the combination of extreme gradient boosting and random forest provided the best performance, achieving the following accuracy metrics: 68.83% sensitivity, 70.85% specificity, 69.84% balanced accuracy, and 74.55% area under the receiver operating characteristic curve. The performance of the isolated testing dataset was also validated, and the machine learning model was successfully deployed on a public website (http://ai-wm.khu.ac.kr/Delirium/) to provide public access to delirium prediction results in patients with advanced cancer. Furthermore, using feature importance analysis, sex was determined to be the top contributor in predicting delirium, followed by a history of delirium, chemotherapy, smoking status, alcohol consumption, and living with family. Based on a large-scale, multicenter, patient-based registry cohort, a machine learning prediction model for delirium in patients with advanced cancer was developed in South Korea. We believe that this model will assist healthcare providers in treating patients with delirium and advanced cancer.

Interpretable machine learning model for early prediction of delirium in elderly patients following intensive care unit admission: a derivation and validation study.

Delirium is the most common neuropsychological complication among older adults admitted to the intensive care unit (ICU) and is often associated with a poor prognosis. This study aimed to construct and validate an interpretable machine learning (ML) for early delirium prediction in older ICU patients. This was a retrospective observational cohort study and patient data were extracted from the Medical Information Mart for Intensive Care-IV database. Feature variables associated with delirium, including predisposing factors, disease-related factors, and iatrogenic and environmental factors, were selected using least absolute shrinkage and selection operator regression, and prediction models were built using logistic regression, decision trees, support vector machines, extreme gradient boosting (XGBoost), k-nearest neighbors and naive Bayes methods. Multiple metrics were used for evaluation of performance of the models, including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, recall, F1 score, calibration plot, and decision curve analysis. SHapley Additive exPlanations (SHAP) were used to improve the interpretability of the final model. Nine thousand seven hundred forty-eight adults aged 65 years or older were included for analysis. Twenty-six features were selected to construct ML prediction models. Among the models compared, the XGBoost model demonstrated the best performance including the highest AUC (0.836), accuracy (0.765), sensitivity (0.713), recall (0.713), and F1 score (0.725) in the training set. It also exhibited excellent discrimination with AUC of 0.810, good calibration, and had the highest net benefit in the validation cohort. The SHAP summary analysis showed that Glasgow Coma Scale, mechanical ventilation, and sedation were the top three risk features for outcome prediction. The SHAP dependency plot and SHAP force analysis interpreted the model at both the factor level and individual level, respectively. ML is a reliable tool for predicting the risk of critical delirium in elderly patients. By combining XGBoost and SHAP, it can provide clear explanations for personalized risk prediction and more intuitive understanding of the effect of key features in the model. The establishment of such a model would facilitate the early risk assessment and prompt intervention for delirium.

149. Prediction of Postoperative Delirium by Blood Metabolome

149. Prediction of Postoperative Delirium by Blood Metabolome

Development and validation of a machine learning model to predict postoperative delirium using a nationwide database: A retrospective, observational study

Study objectivePostoperative delirium is a neuropsychological syndrome that typically occurs in surgical patients. Its onset can lead to prolonged hospitalization as well as increased morbidity and mortality. Therefore, it is important to promptly identify its signs. This study aimed to develop and validate a machine learning predictive model for postoperative delirium using extensive population data. DesignRetrospective observational study. SettingJapanese Diagnosis Procedure Combination inpatient data. Data were used for internal (2016.4–2018.12) and temporal validation (2019.01–2019.10). PatientsPatients aged ≥65 years who underwent general anesthesia for surgical procedure. MeasurementsThe primary outcome was postoperative delirium, which was defined as a condition requiring newly prescribed antipsychotic drugs or assignment of the corresponding insurance claim code after the date of surgery. We trained and tuned the optimal machine-learning model through 10-fold cross-validation using the selected optimal area under the receiver operating characteristic curve (AUC) value. In the temporal validation, we measured the performance of our model. Main resultsThe analysis included 557,990 patients. The light-gradient boosting machine models showed a higher AUC value (0.826 [95% confidence interval (CI): 0.822–0.829]) than the other models. Regarding performance, the model had a recall value of 0.124 (95% CI: 0.119–0.129) and precision value of 0.659 (95% CI: 0.641–0.677]). This performance was sustained in the temporal validation (AUC, 0.815 [95% CI: 0.811–0.818]). At a sensitivity of 0.80, the model achieved a specificity of 0.672 (95% CI: 0.670–0.674]), a negative predictive value of 0.975 (95% CI: 0.974–0.975), and a positive predictive value of 0.176 (95% CI: 0.176–0.179). ConclusionsUsing extensive Diagnostic Procedure Combination data, we successfully created and validated a machine learning model for predicting postoperative delirium. This model may facilitate prediction of postoperative delirium.

Brain functional magnetic resonance imaging in ICU patients who developed delirium

ObjectiveTo detect brain alterations in intensive care unit (ICU) patients who develop delirium using functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI) and to determine their predictive value.MethodsFifty-two patients who were admitted to the ICU of the Affiliated Hospital of Zunyi Medical University between June 2021 and June 2022 were enrolled. Fifteen patients who were diagnosed with delirium by the Intensive Care Delirium Screening Checklist (ICDSC) after MRI were selected as the delirium group, and 15 healthy volunteers who were examined during the same period served as the control group. Both groups underwent fMRI and DTI. Quantitative fMRI and DTI data were compared between the two groups to detect abnormal structural and functional brain damage. The relationships between MRI outliers and clinical indicators in the delirium group were also assessed.ResultsDemographic characteristics and imaging indicators before delirium were not correlated with ICDSC scores after delirium. Compared with the healthy control group, the delirium group had significantly lower regional homogeneity (ReHo) values in the left caudate nucleus and frontal lobe on fMRI. The amplitude of the low-frequency fluctuations (ALFF) values of the delirium group were significantly increased in the hippocampus but significantly decreased in the frontal lobe. Compared with the healthy control group, the delirium group showed reduced mean diffusivity (MD) values, mainly in the right cerebellum and right middle temporal gyrus; reduced radial diffusivity (RD) values, mainly in the anterior cerebellum and right middle temporal gyrus; reduced fractional anisotropy (FA) values, only in the corpus callosum; and reduced axial diffusivity (AD) values, mainly in the anterior cerebellar lobe, right middle temporal gyrus, and left middle frontal gyrus on DTI. The statistical thresholds for quantitative DTI measurements were p &amp;lt; 0.005 at the voxel level and a cluster size &amp;gt; 5.ConclusionAbnormal resting-state brain activity in the left superior frontal gyrus and structural changes in the frontal lobe, temporal lobe, corpus callosum, hippocampus, and cerebellum were observed in ICU patients who developed delirium during hospitalization. Early-brain fMRI and DTI examinations are recommended for the prediction of delirium according to unique quantitative indicators to facilitate early intervention for critically ill patients, reduce the length of hospital stay, and improve patient prognosis.

Effectiveness of Consolidated National Institute for Health and Care Excellence Delirium Prediction Rule for Predicting the Risk of Delirium in Intensive Care Unit Patients with Stroke Managed by Pharmacist-led Interventions (P11-2.006)

Effectiveness of Consolidated National Institute for Health and Care Excellence Delirium Prediction Rule for Predicting the Risk of Delirium in Intensive Care Unit Patients with Stroke Managed by Pharmacist-led Interventions (P11-2.006)

A novel nomogram for the prediction of subsyndromal delirium in patients in intensive care units: A prospective, nested case-controlled study

BackgroundSubsyndromal delirium is a dynamic, recognizable condition commonly observed in intensive care unit (ICU) patients that can lead to poor patient prognosis, and its prompt recognition and management can prevent disease progression. However, no evidence-based predictive tool has been developed specifically to assess the occurrence of subsyndromal delirium in the ICU. ObjectiveTo develop and validate a novel, simple and effective tool for estimating the risk of subsyndromal delirium among ICU patients. DesignA prospective, nested case-controlled study. Data sourcesA total of 731 patients were recruited from the central ICU of a tertiary hospital in southwestern China from August 2021 to November 2022. MethodsThe least absolute shrinkage and selection operator was applied to screen potential features for univariate and multivariate logistic regression. A nomogram was constructed using the selected variables. The performance of the nomogram was evaluated by combining the area under the receiver operating characteristic curve (AUC), calibration curves and decision curve analysis (DCA). ResultsThe prevalence of subsyndromal delirium among ICU patients was 23.06 %. Multiple logistic regression analysis revealed that the independent predictive factors for subsyndromal delirium among ICU patients were vision impairment, a history of falls, the use of restraint, blood transfusion, the use of antibiotics, surgery, the Caprini score, and the Braden score, all of which were used to construct the nomogram. The AUCs for the model were 0.710 (95 % CI, 0.654–0.766, P < 0.001) and 0.825 (95 % CI, 0.732–0.917, P < 0.001) in the training and validation cohorts, respectively, indicating that the model had high accuracy in distinguishing patients with and without subsyndromal delirium. The calibration curve of the nomogram showed good consistency between the predicted and actual probabilities. The DCA indicated that the nomogram has clinical application for patients in the ICU. ConclusionsWe developed an easy-to-use nomogram for identifying subsyndromal delirium in ICU patients with satisfactory predictive ability based on simple and easily accessible clinical features. The nomogram can identify ICU patients at high-risk for subsyndromal delirium and may be a useful subsyndromal delirium tool for current ICU physicians.

Métodos de aprendizaje automático para el desarrollo de un modelo predictivo de delirio durante el ingreso en unidades de cuidados intensivos cardiacos

Introduction and objectivesDelirium, recognized as a crucial prognostic factor in the cardiac intensive care unit (CICU), has evolved in response to the changing demographics among critically ill cardiac patients. This study aimed to create a predictive model for delirium for patients in the CICU. MethodsThis study included consecutive patients admitted to the CICU of the Samsung Medical Center. To assess the candidate variables for the model: we applied the following machine learning methods: random forest, extreme gradient boosting, partial least squares, and Plmnet-elastic.net. After selecting relevant variables, we performed a logistic regression analysis to derive the model formula. Internal validation was conducted using 100-repeated hold-out validation. ResultsWe analyzed 2774 patients, 677 (24.4%) of whom developed delirium in the CICU. Machine learning-based models showed good predictive performance. Clinically significant and frequently important predictors were selected to construct a delirium prediction scoring model for CICU patients. The model included albumin level, international normalized ratio, blood urea nitrogen, white blood cell count, C-reactive protein level, age, heart rate, and mechanical ventilation. The model had an area under the receiver operating characteristics curve (AUROC) of 0.861 (95%CI, 0.843-0.879). Similar results were obtained in internal validation with 100-repeated cross-validation (AUROC, 0.854; 95%CI, 0.826-0.883). ConclusionsUsing variables frequently ranked as highly important in four machine learning methods, we created a novel delirium prediction model. This model could serve as a useful and simple tool for risk stratification for the occurrence of delirium at the patient's bedside in the CICU.

Identification of risk factors for the onset of delirium associated with COVID-19 by mining nursing records.

COVID-19 has a range of complications, from no symptoms to severe pneumonia. It can also affect multiple organs including the nervous system. COVID-19 affects the brain, leading to neurological symptoms such as delirium. Delirium, a sudden change in consciousness, can increase the risk of death and prolong the hospital stay. However, research on delirium prediction in patients with COVID-19 is insufficient. This study aimed to identify new risk factors that could predict the onset of delirium in patients with COVID-19 using machine learning (ML) applied to nursing records. This retrospective cohort study used natural language processing and ML to develop a model for classifying the nursing records of patients with delirium. We extracted the features of each word from the model and grouped similar words. To evaluate the usefulness of word groups in predicting the occurrence of delirium in patients with COVID-19, we analyzed the temporal changes in the frequency of occurrence of these word groups before and after the onset of delirium. Moreover, the sensitivity, specificity, and odds ratios were calculated. We identified (1) elimination-related behaviors and conditions and (2) abnormal patient behavior and conditions as risk factors for delirium. Group 1 had the highest sensitivity (0.603), whereas group 2 had the highest specificity and odds ratio (0.938 and 6.903, respectively). These results suggest that these parameters may be useful in predicting delirium in these patients. The risk factors for COVID-19-associated delirium identified in this study were more specific but less sensitive than the ICDSC (Intensive Care Delirium Screening Checklist) and CAM-ICU (Confusion Assessment Method for the Intensive Care Unit). However, they are superior to the ICDSC and CAM-ICU because they can predict delirium without medical staff and at no cost.

A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

BackgroundPrevious models for predicting delirium after cardiac surgery remained inadequate. This study aimed to develop and validate a machine learning-based prediction model for postoperative delirium (POD) in cardiac valve surgery patients.MethodsThe electronic medical information of the cardiac surgical intensive care unit (CSICU) was extracted from a tertiary and major referral hospital in southern China over 1 year, from June 2019 to June 2020. A total of 507 patients admitted to the CSICU after cardiac valve surgery were included in this study. Seven classical machine learning algorithms (Random Forest Classifier, Logistic Regression, Support Vector Machine Classifier, K-nearest Neighbors Classifier, Gaussian Naive Bayes, Gradient Boosting Decision Tree, and Perceptron.) were used to develop delirium prediction models under full (q = 31) and selected (q = 19) feature sets, respectively.ResultThe Random Forest classifier performs exceptionally well in both feature datasets, with an Area Under the Curve (AUC) of 0.92 for the full feature dataset and an AUC of 0.86 for the selected feature dataset. Additionally, it achieves a relatively lower Expected Calibration Error (ECE) and the highest Average Precision (AP), with an AP of 0.80 for the full feature dataset and an AP of 0.73 for the selected feature dataset. To further evaluate the best-performing Random Forest classifier, SHAP (Shapley Additive Explanations) was used, and the importance matrix plot, scatter plots, and summary plots were generated.ConclusionsWe established machine learning-based prediction models to predict POD in patients undergoing cardiac valve surgery. The random forest model has the best predictive performance in prediction and can help improve the prognosis of patients with POD.

Machine learning methods for developing a predictive model of the incidence of delirium in cardiac intensive care units

Introduction and objectivesDelirium, recognized as a crucial prognostic factor in the cardiac intensive care unit (CICU), has evolved in response to the changing demographics among critically ill cardiac patients. This study aimed to create a predictive model for delirium for patients in the CICU. MethodsThis study included consecutive patients admitted to the CICU of the Samsung Medical Center. To assess the candidate variables for the model: we applied the following machine learning methods: random forest, extreme gradient boosting, partial least squares, and Plmnet-elastic.net. After selecting relevant variables, we performed a logistic regression analysis to derive the model formula. Internal validation was conducted using 100-repeated hold-out validation. ResultsWe analyzed 2774 patients, 677 (24.4%) of whom developed delirium in the CICU. Machine learning-based models showed good predictive performance. Clinically significant and frequently important predictors were selected to construct a delirium prediction scoring model for CICU patients. The model included albumin level, international normalized ratio, blood urea nitrogen, white blood cell count, C-reactive protein level, age, heart rate, and mechanical ventilation. The model had an area under the receiver operating characteristics curve (AUROC) of 0.861 (95%CI, 0.843-0.879). Similar results were obtained in internal validation with 100-repeated cross-validation (AUROC, 0.854; 95%CI, 0.826-0.883). ConclusionsUsing variables frequently ranked as highly important in four machine learning methods, we created a novel delirium prediction model. This model could serve as a useful and simple tool for risk stratification for the occurrence of delirium at the patient's bedside in the CICU.