Accuracy of delirium risk factors in adult intensive care unit patients

Background: Intensive care units (ICUs) are crucial in healthcare, but internal factors, like patient agitation due to delirium, treatment discomfort, and the ICU environment, can compromise care and lead to safety issues. In Taiwan, the Richmond Agitation–Sedation Scale (RASS) is used for agitation assessment, but it has limitations, including subjectivity and infrequent assessments. Methods: To enhance ICU care, we developed a machine learning-based patient agitation and sedation assessment tool. We used an ensemble learning model, combining two machine learning models to classify patients into three categories: oversedation, optimal sedation, and agitation. Results: The RandomForest model achieved the highest average accuracy for sedation (ACC = 0.92, AUC = 0.97), while addressing class imbalance increased agitation classification accuracy (ACC = 0.77, AUC = 0.88). The model's results, based on key features identified, can guide sedative dosage adjustments, enabling more precise patient care. Conclusions: Our study demonstrated the effectiveness of machine learning in classifying patient agitation and sedation. We recommend incorporating image-based features in patient agitation assessment. Our classification system can assist medical professionals in RASS assessments, mitigating safety risks related to patient agitation in ICUs and improving overall ICU capacity. Trial Registration: We obtained access to the critical care database (AI-111010) of the AI Center of Taichung Veterans General Hospital (TCVGH) from the Institutional Review Board (approval number: CE22484A), retrospectively registered.

show abstract

Inflammatory and nutritional markers predict the risk of post-operative delirium in elderly patients following total hip arthroplasty

Hu,

Song,

Shang

et al. 2023

Front. Nutr.

View full text Add to dashboard Cite

ObjectivesThis study intended to explore whether albumin-associated inflammatory and nutritional markers could predict post-operative delirium (POD) in older patients after total hip arthroplasty (THA). In addition, we established a nomogram model for POD prediction.MethodsTotally, 254 elderly cases who received THA were included. Clinical and laboratory data of these patients were retrospectively collected. Albumin-associated inflammatory and nutritional markers included neutrophil-to-albumin ratio (NAR), CRP-to-albumin ratio (CAR), prognostic nutritional index (PNI), and systemic inflammation score (SIS). The LASSO, univariate and multivariate logistic regression analyses were utilized to screen risk factors. A nomogram model was developed according to the results of multivariate regression analyses.ResultsAmong 254 patients, 49 cases had POD with an incidence of 19.3%. LASSO regression and multivariate logistic analyses suggested that preoperative NAR, preoperative PNI, preoperative SIS, and age >75 years were risk factors for POD. A nomogram model was developed according to the results of multivariate logistic analyses. The calibration curve suggested that the predicted probability of this nomogram model was in good line with the actual probability. The DCA showed that this nomogram model had net benefits for the prediction of POD for elderly patients following THA.ConclusionAlbumin-associated inflammatory and nutritional markers including NAR, PNI, and SIS could predict POD in elderly patients following THA.

show abstract

Accuracy of delirium risk factors in adult intensive care unit patients

Cited by 3 publications

References 27 publications

Clinical characteristics and outcomes of antibiotic-associated encephalopathy in patients with end-stage kidney disease

Clinical characteristics and outcomes of antibiotic-associated encephalopathy in patients with end-stage kidney disease

An Agitation Sedation Level Prediction Model for ICU Patients

Inflammatory and nutritional markers predict the risk of post-operative delirium in elderly patients following total hip arthroplasty

Contact Info

Product

Resources

About