Early Identification of Delirium in Intensive Care Unit Patients: Improving the Quality of Care

Enhanced machine learning predictive modeling for delirium in elderly ICU patients with COPD and respiratory failure: A retrospective study based on MIMIC-IV

BACKGROUND AND OBJECTIVE

Elderly patients with Chronic obstructive pulmonary disease (COPD) and respiratory failure admitted to the intensive care unit (ICU) have a poor prognosis, and the occurrence of delirium further worsens outcomes and increases hospitalization costs. This study aimed to develop a predictive model for delirium in this patient population and identify associated risk factors.

METHODS

Data for the machine learning model were obtained from the MIMIC-IV database. Feature variable screening was conducted using Lasso regression and the best subset method. Four models-K-nearest neighbor, random forest, logistic regression, and extreme gradient boosting (XGBoost)-were trained and optimized to predict delirium risk. The stability of the model is evaluated using ten-fold cross validation and the effectiveness of the model on the validation set is evaluated using accuracy, F1 score, precision and recall. The SHapley Additive exPlanations (SHAP) method was used to explain the importance of each variable in the model.

RESULTS

A total of 1,155 patients admitted to the intensive care unit between 2008 and 2019 were included in the study, with a delirium incidence of 12.9% (149/1,155). Among the four ML models evaluated, the XGBoost model demonstrated the best discriminative ability. In the validation set, it achieved an AUC of 0.932, indicating superior performance with high accuracy, precision, recall, and F1 scores of 0.891, 0.839, 0.795, and 0.810, respectively. Key features identified through SHAP analysis included the Glasgow Coma Scale (GCS) verbal score, length of hospital stay, mean SpO₂ on the first day of ICU admission, Modification of Diet in Renal Disease (MDRD) equation score, mean diastolic blood pressure, GCS motor score, gender, and duration of noninvasive ventilation. These findings provide valuable insights for individualized risk management.

CONCLUSIONS

The developed prediction model effectively predicts the occurrence of delirium in elderly COPD patients with respiratory failure in the ICU. This model can assist clinical decision-making, potentially improving patient outcomes and reducing healthcare costs.

Improving the Recognition and Assessment of ICU Delirium

BACKGROUND

Delirium is acute neurological failure that alters cognition and results in a state of confusion and lack of self-awareness. It commonly affects critically ill patients within intensive care units (ICUs), and the wide array of fluctuating symptoms frequently leads to underdiagnosis. Delirium results in cognitive impairment and increased rates of fatality, and accurate assessments are essential for improving patient outcomes. Barriers to delirium assessment stem from a lack of knowledge and assessment training among ICU nurses.

METHOD

Using the Cumulative Index to Nursing and Allied Health Literature electronic database, a literature synthesis was conducted, analyzing journal articles addressing delirium education and training among ICU nurses and barriers associated with assessment.

RESULTS

Current literature identifies methods to overcome barriers through training, education, and continuous reinforcement of delirium assessment. The goals of this review are to identify the barriers to delirium assessment and make recommendations for education methods to increase the confidence of ICU nurses in the recognition of delirium to improve patient outcomes.

CONCLUSION

Early identification of delirium is crucial to improving patient outcomes. A standardized delirium educational program should be developed and implemented throughout the U.S. health care system. [J Contin Educ Nurs. 2024;55(11):530-534.].

Practices of the ABCDEF care bundle in intensive care units as reported by nurses: A cross-sectional study from Turkey

BACKGROUND

Recent critical care guidelines recommended the evidence-based ABCDEF care bundle for intensive care unit (ICU) patients. However, limited information is available on the implementation of the bundle in Turkish ICUs.

AIM

To assess the current practices of the ABCDEF care bundle as reported by ICU nurses.

STUDY DESIGN

A cross-sectional study using a web-based survey was conducted. Researchers invited nurses with at least 1 year of ICU experience to participate by sending the link to the research questionnaires they created in Google Forms to the one ICU nurse association and one communication group of which they are members.

RESULTS

A total of 342 ICU nurses completed the survey. Although 92% of the participants performed pain assessments in their ICUs, 52.7% reported not using protocols. Based on the responses of the nurses, spontaneous awakening and breathing trials are performed in 88.8% and 92.4%, respectively, of ICUs. Fewer than half of the participants reported following a sedation protocol in their ICUs. Only 54.7% of ICU nurses surveyed reported routinely monitoring patients for delirium. It was reported that early mobilization was practised in 68.7% of ICUs, but non-ventilated patients were mobilized more frequently (70.2%), and 9.7% of ICUs had mobilization teams. Family members were actively involved in 95% of ICUs; however, 9.7% used dedicated staff to support families and 3.5% reported that their unit was open 24 h/day for visits.

CONCLUSIONS

While the implementation of most pain and sedation evaluations in ICUs were reported by nurses, many of them did not use structured delirium assessments. There is a need to encourage early mobilization programs and family participation.

RELEVANCE TO CLINICAL PRACTICE

Health institutions can improve patient care and outcomes by establishing and standardizing a protocol for each component of the ABCDEF care bundle in ICUs.

Bringing Delirium to Light: Impact of CAM-ICU Tool to Improve Care Coordination

BACKGROUND

Delirium is a serious complication in patients in the critical care unit (CCU) that may lead to prolonged hospitalization if left undetected. The CCU at our hospital does not have a framework for determining delirium that could affect patient outcomes and discharge planning.

PRIMARY PRACTICE SETTING

CCU in a community hospital.

METHOD

A posttest-only design was used for this study. We established a framework for the early assessment of delirium, educated and trained nurses to detect delirium, collaborated with the informatics department, intensivist, nursing, respiratory therapy and worked with case management to deploy the Confusion Assessment Method for the Intensive Care Unit (CAM-ICU). We used a one-tailed independent t test to determine the impact of CAM-ICU on length of stay (LOS). Cross-tabulation and chi-square tests were used to examine the impact of CAM-ICU tool on home care utilization between the intervention and comparison groups.

RESULTS

There was a 3.12% reduction in LOS after implementing the CAM-ICU tool. Also, a reduction in home care service utilization demonstrated statistical significance ( p = .001) between the intervention group (62.5%; n = 177) and the comparison group (37.5%; n = 106).

IMPLICATIONS FOR CASE MANAGEMENT PRACTICE

Case managers are essential in improving care transitions. Case managers need to become competent in understanding the implications of the CAM-ICU tool because of their relevant role in the multidisciplinary rounds as advocates to improve care transitions across the continuum of care. Case managers need to have an understanding on how to escalate when changes in the Richmond Agitation-Sedation Scale scores occur during the multidisciplinary rounds because it can affect care coordination throughout the hospital.

CONCLUSIONS

Implementing the CAM-ICU decreased LOS, and reduced health care utilization. The early identification of patients with delirium can affect the outcomes of critically ill patients and entails multidisciplinary collaboration.

Recognizing and Reducing Delirium in the Intensive Care Unit

This article discusses a quality improvement study conducted on intensive care unit (ICU) staff nurses that assessed their ability to utilize the CAM-ICU tool for delirium detection properly. Staff members' expertise in identifying and managing delirious patients directly correlates with reducing the long-term sequelae associated with ICU delirium. The cohort of ICU nurses participating in this research study took a questionnaire on 4 separate occasions. The survey ascertained quantitative and qualitative data, reflecting personal knowledge about the CAM-ICU tool and delirium. After each round of assessment, group and one-on-one educational sessions were provided by the researchers. The study culminated with providing each staff member a delirium reference card (badge buddy) containing relevant and easily accessible clinical information that supported the ICU staff nurses in correctly implementing the CAM-ICU tool.

Patient Safety: Cognitive Assessment at Intensive Care Unit Discharge

Topic

Assessing functional cognition is a critical need for intensive care unit survivors transitioning to another level of care.

Clinical Relevance

Up to 62% of patients discharged from an intensive care unit have significant cognitive impairment that is not associated with severity of illness, number of comorbidities, or length of hospital stay. For more than 20 years, researchers have published an array of potentially effective interventions, including case management, patient and informal caregiver education, and home health care services.

Purpose

To describe the impact of and potential interventions for cognitive decline at intensive care unit discharge and discharge readiness on 30-day readmission rates.

Content Covered

Assessing the patient’s functional cognition assessment and advocating for appropriate resources are needed to improve patient and clinical outcomes.

An exploration of the reliability and usability of two delirium screening tools in an Australian intensive care unit: A pilot study

OBJECTIVE

To compare the inter-rater reliability and usability of two delirium screening tools designed for use in ICU; the Confusion Assessment Method for ICU and the Intensive Care Delirium Screening Checklist.

RESEARCH METHODOLOGY/DESIGN

A multiple methods design was used. The intra and inter rater reliability of the tools were evaluated using Kappa statistics and intra class correlation coefficients. Focus groups were conducted to explore ICU staff perceptions of the usability of the tools and feasibility of delirium screening.

SETTING

Private hospital ICU, Melbourne Australia.

RESULTS

66 patients were assessed for delirium; median age of 71 (IQR 62-75) years. Seventeen patients (26%) scored positive for delirium using the screening tools and 11 (17%) had delirium confirmed on the medical ICU discharge summary. Ten nurse assessors performed 99 paired assessments using the two tools sequentially, demonstrating the intra and inter-rater agreement and reliability of the tools was moderate to high. Four focus groups were conducted with 16 participants. Content analysis identified three themes: (i) current recognition of delirium, (ii) benefits of delirium screening, and (iii) future directions for delirium management. Time and medical staff indifference were identified as barriers to screening, facilitators were education and having a follow-up plan.

CONCLUSION

This study found that the reliability and usability of the CAM-ICU and ICDSC were acceptable and that using structured delirium screening was feasible as part of a wider, multi-disciplinary delirium management plan.