Delirium In Intensive Care Unit Research Articles

Windows in the ICU and Postoperative Delirium: A Retrospective Cohort Study.

The ICU built environment-including the presence of windows-has long been thought to play a role in delirium. This study investigated the association between the presence or absence of windows in patient rooms and ICU delirium. Retrospective single institution cohort study. Delirium was assessed with the Confusion Assessment Method for the ICU. ICU patients between January 1, 2020, and September 1, 2023, were categorized into windowed or nonwindowed groups based on their ICU room design. The primary outcome was the presence or absence of delirium at any time during the patient's ICU stay. Secondary outcomes included the presence of delirium during the first 7 days of the ICU stay, hospital length of stay, ICU length of stay, in-hospital mortality, pain scores, and Richmond Agitation-Sedation Scale scores. None. A total of 3527 patient encounters were included in the final analysis, of which 1292 distinct patient encounters were admitted to a room without windows (37%). Delirium was observed in 21% of patients (460/2235) in windowed rooms and 16% of patients (206/1292) in nonwindowed rooms. In adjusted analyses, patients in windowed rooms were associated with an increase in the odds of the presence of delirium (odds ratio, 1.29; 95% CI, 1.07-1.56; p = 0.008). Patients in windowed rooms were found to have longer hospital (adjusted hazard ratio [aHR], 0.94; 95% CI, 0.87-1.00) and ICU length of stay (aHR, 0.93; 95% CI, 0.87-1.00) compared with patients in the nonwindowed rooms, although this was not statistically significant in adjusted analyses (p = 0.06 and 0.05, respectively). No statistically significant difference was observed in other secondary outcomes. The current study provides insightful information regarding associations between a component of the ICU built environment, specifically the presence or absence of windows, and the frequency of delirium.

A Critical Reappraisal of Haloperidol for Delirium Management in the Intensive Care Unit: Perspective from Psychiatry

Delirium is a complex neuropsychiatric syndrome with multifactorial pathophysiology, encompassing a wide range of neuropsychiatric symptoms, and its management remains a significant challenge in critical care. Although often managed with antipsychotics, like haloperidol, current research has predominantly focused on dopamine dysregulation as the primary driver of delirium, overlooking its broader neuroanatomical and neurochemical underpinnings. This has led to a majority of research focusing on haloperidol as a treatment for intensive care unit (ICU) delirium. Our review critically evaluates the role of haloperidol in ICU delirium management, particularly in light of recent large-scale randomized controlled trials (RCTs) that have primarily focused on delirium-free days and mortality as the primary endpoints. These studies highlight an limited understanding of the true nature of delirium treatment, which requires a broader, neuropsychiatric approach. We argue that future research should shift focus to neuropsychiatric symptoms such as agitation and psychosis and explore the clinical and functional benefits of reducing these distressing symptoms. Additionally, the stratification of delirium by subtypes and etiology, the enhancement of detection tools, and the adoption of multi-intervention and multi-disciplinary care approaches should be prioritized. Despite the methodological flaws in these studies, the findings support the safety of haloperidol in the ICU setting, with minimal risk of adverse events, particularly cardiac and neuropsychiatric. Moving forward, delirium research must integrate modern neuroscientific understanding and adopt more multi-disciplinary input and nuanced, patient-centered approaches to truly advance clinical care and outcomes.

Evaluating the effectiveness of a clinical decision support system (AI-Antidelirium) to improve Nurses' adherence to delirium guidelines in the intensive care unit.

To evaluate the impact of Artificial Intelligence Assisted Prevention and Management for Delirium (AI-AntiDelirium) on improving adherence to delirium guidelines among nurses in the intensive care unit (ICU). Between November 2022 and June 2023, A cluster randomized controlled trial was undertaken. A total of 38 nurses were enrolled in the interventional arm, whereas 42 nurses were recruited for the control arm in six ICUs across two hospitals in Beijing, comparing nurses' adherence and cognitive load in units that use AI-AntiDelirium or the control group. The AI-AntiDelirium tailored delirium preventive or treated interventions to address patients' specific risk factors. The adherence rate of delirium interventions was the primary endpoint. The other endpoints were adherence to risk factors assessment, ICU delirium assessment, and nurses' cognitive load. The repeated measures analysis of variance was utilized to explore the influence of time, group, and time×group interaction on the repeated measurement variable (e.g., adherence, cognitive load). A cumulative total of 1040 nurse days were analyzed for this study. The adherence to delirium intervention of nurses in AI-AntiDelirium groups was higher than control units (75% vs. 58%, P<0.01). When compared to control groups, AI-AntiDelirium was found to be significantly effective in both decreasing extraneous cognitive load (P<0.01) and improving germane cognitive load (P<0.01). This study supports the effectiveness of AI-AntiDelirium in enhancing nurses' adherence to evidence-based, individualized delirium intervention and also reducing extraneous cognitive load. A nurse-led systemshould be applied by nursing administrators to improve compliance with nursing interventions among ICU nurses.

Effectiveness of a virtual reality-based sensory stimulation intervention in preventing delirium in intensive care units: a randomised-controlled trial protocol

IntroductionDelirium is a common acute cognitive impairment characterised by confusion, disorientation and attention deficits, particularly prevalent in intensive care unit (ICU) settings. Given its significant impact on patients, caregivers and...

Evaluation of Delirium Risk Factors in Intensive Care Patients.

The negative effects of delirium in intensive care unit (ICU) patients necessitate the identification and management of risk factors. This study aimed to determine the incidence of delirium and its associated modifiable and non-modifiable factors in the ICU setting to provide valuable insights for better patient care and outcomes. Patients admitted to the ICU underwent delirium screening twice daily. Comprehensive records of modifiable and non-modifiable risk factors were maintained throughout the ICU stay. The incidence of delirium was 32.5%. Age [odds ratio (OR) 1.04, confidence interval (CI) 1.02-1.06, P < 0.001)]. Illiteracy (OR 4, CI 1.19-13.35, P=0.02), hearing impairment (OR 3.37, CI 1.71-7.01, P=0.001), visual impairment (OR 3.90, CI 2.13-7.15, P < 0.001), hypertension (OR 2.56, CI 1.42-4.62, P=0.002), Sequential Organ Failure Assessment score (OR 1.21, CI 1.08-1.36, P=0.001), Acute Physiology and Chronic Health Evaluation II score (OR 1.20, CI 1.12-1.28, P < 0.001), presence of a nasogastric catheter/drain (OR 2.15, CI 1.18-3. 90, P=0.01), tracheal aspiration (OR 3.63, CI 1.91-6.90, P < 0.001), enteral nutrition (OR 2.54, CI 1.12-5.76, P=0.02), constipation (OR 1.65, Cl 1.11-2.45, P=0.02), oliguria (OR 1.56, Cl 1.06-2.28, P=0.02), midazolam infusion (OR 3. 4, Cl 1.16-10.05, P=0.02), propofol infusion (OR 2.91 Cl 1.03-8.19, P=0.04), albumin use (OR 2.39, Cl 1.11-5.14 P=0.02) and steroid use (OR 2.17, Cl 1.06-4.40, P=0.03) were found to be independent risk factors for delirium. This study highlights several risk factors contributing to delirium, such as age, sensory impairment, educational level, procedural interventions, and medications. Oral nutrition and mobilization are effective strategies for reducing delirium incidence in the ICU.

Delirium in Adult Critical Care Unit: Prevalence and Outcomes at Regional Hospital

Background: Delirium is an acute confusional state that affects 30-80% of admitted patients to intensive care units. According to the literature, delirium may worsen patients’ and hospital outcomes. No research studies regarding delirium prevalence and outcomes were found in Oman. Objective: This study aims to determine the prevalence and outcomes of delirium in Adult patients admitted to the Intensive Care Unit (ICU) at a regional hospital. Methodology: This study followed an observational longitudinal design. A consecutive sampling method for six months was used for selecting Adult Intensive Care Unit (AICU) patients after 48 hours of ICU admission and a total of 76 patients aged 18 years and older were included. Confusion Assessment Method in Intensive Care Unit (CAM-ICU) instrument (CAM-ICU worksheet and Daily Assessment Checklist) was used for assessing patients’ prevalence and outcomes of delirium. A training program was provided for adult intensive care doctors and nurses regarding using the CAM-ICU tool one month before the study. Social Packages for the Social Sciences Program (SPSS) version 20 was used for data analysis. Results: More than half of the participants were male (63%), while the age group above 65 years (42%) had more positive cases. Results indicated a high prevalence of delirium in AICU (77%) of admitted patients. Outcomes of delirium in AICU indicated two outcomes, duration in AICU and ventilation days. Duration in ICU (M= 15.53, SD= 21.27) while ventilation days indicated a (M=13.30, SD=20.69). The result indicated a significant positive relationship between age, duration days in ICU, and ventilation days to delirium (p=0.001). Conclusion: The results from this study indicated a high prevalence of delirium in AICU and delirium is associated with longer duration in AICU and longer ventilation days. Identifying delirium prevalence and outcomes can enhance the early management of delirium and improve patients’ and hospital outcomes. In addition, results from this study can improve the knowledge and skills of healthcare providers in using the CAM-ICU assessment as a valid tool for assessing delirium in Intensive care unit (ICU) patients.

High level of systemic immune inflammation index elevates delirium risk among patients in intensive care unit

Evidence regarding the effect of systemic immune-inflammation index on delirium occurrence is limited. This study aimed to investigate the association between SII and delirium in intensive care unit (ICU) patients. Methods: Information was extracted from Medical Information Mart for Intensive Care-IV. Four logistic regression model was established and incorporated with subgroup analysis and restricted cubic spline (RCS). The cutoff value of SII was acquired from receiver operator characteristic curve (ROC), and propensity score matching (PSM) was utilized to attenuate the confounding effect. Survival analysis was utilized to evaluate the relationship between SII and 30-day or 90-day all-cause mortality. Results: Among the 7,518 participants, 1,685 cases of delirium occurred. Individuals in the highest quartile of SII exhibited a heightened delirium risk, with a significant multivariable-adjusted odds ratio (OR) of 3.12(2.24,4.33). Tendency analysis, subgroup analysis and PSM together confirmed the positive relationship. Results of Cox regression displayed the risk of both 30-day and 90-day mortality increased about 50% in the higher-SII group. Conclusion: Higher levels of SII is positively associated with the occurrence of delirium and increased all-cause mortality risk.

Using Compressed Virtual Reality Exposure Therapy for an Adult Critical Illness Survivor: A Case Report.

Nearly one-quarter of adult critical illness survivors develop posttraumatic stress disorder symptoms triggered by sensory stimuli after intensive care unit discharge. Intensive care unit delirium is a risk factor for posttraumatic stress disorder. Compressed virtual reality exposure therapy (C-VRET) incorporates sensory stimuli to reduce posttraumatic stress disorder symptoms through habituation. A critical illness survivor developed intensive care unit delirium and enrolled in a C-VRET trial to treat posttraumatic stress disorder. She reported self-isolation because of infection fears and posttraumatic stress disorder symptoms triggered by medical commercials and lawn equipment sounds. She repetitively checked her heart rate at night for fear of missing illness signs and waking up intubated. The participant completed therapy. Screening tests were administered before, 2 weeks after, and 3 months after therapy to measure posttraumatic stress disorder symptoms (Clinician-Administered PTSD Scale for DSM-5; range, 0-60), depression (Center for Epidemiologic Studies Depression Scale; range, 0-60), physical activity (International Physical Activity Questionnaire), and resiliency (Connor-Davidson Resilience Scale; range, 0-100). The participant's posttraumatic stress disorder symptom scores declined from 36 to 11 to 5; depression scores declined from 19 to 5 to 1; physical activity scores increased from 499 to 2013 to 4599; and resiliency scores increased from 70 to 76 to 83. This report highlights the severity of posttraumatic stress disorder symptoms in critical illness survivors and the importance of strategies to limit delirium and posttraumatic stress disorder. Compressed virtual reality exposure therapy may reduce posttraumatic stress disorder symptoms in critical illness survivors.

Research Progress in the Construction of Delirium Risk Warning Model for ICU Patients Based on Decision Tree: A Review of the Literature

Intensive Care Unit (ICU) delirium is a cerebral syndrome characterized by acute disturbance of consciousness, with an incidence of 38%-87%. The occurrence of delirium can lead to prolonged hospital stay, accidental extubation rate, mortality and other adverse consequences. Therefore, early identification of delirium and active correction of reversible causes appear to be particularly important. At present, the risk prediction models for delirium in ICU constructed at home and abroad mainly use logistic regression to build delirium risk prediction models for patients admitted to ICU≥24h. However, studies have found that as many as 25% of critically ill patients will develop delirium within 24h of admission to ICU. Therefore, it is particularly important to construct a delirium early warning model for patients entering ICU24h. Logistic regression model has low processing efficiency for non-linear and interactive data, and can not intuitively show the importance of each variable in the predicted result. As a non-parametric statistical method, decision tree can overcome the disadvantages of Logistic regression model and build a better prediction model. Therefore, this study used 24h after admission to ICU as the segmentation point to build a decision tree model for predicting early and late delirium in ICU patients, forming a corresponding risk level system, and compared it with similar delirium models to verify the predictive value of the decision tree model for early and late delirium in ICU patients, providing a basis for the formulation of further intervention and nursing plans. Thereby reducing the incidence of ICU delirium.

Bibliometric Analysis of Studies on Delirium in Critical Care

Background Delirium leads to prolongation in intensive care unit (ICU) and hospital length of stay and an increase in ICU costs and mortality. As a result of this, the number of studies on delirium in ICUs has recently increased significantly, and many articles have been published. Objectives The aim of this study was to evaluate the articles related to “delirium” in “critical care” field in the Web of Science database and the first hundred most cited articles on this subject. Methods The Web of Science database was searched for articles relevant to “delirium” in the critical care medicine field published between 1980 and 2024. Text analytics and network models used in bibliometric mapping were used for prolific authors, annual trend, citation, and countries. Results In our study, it was determined that a total of 1834 articles in the field of delirium in critical care medicine were included. It was determined that the annual citation average was 42.79 and the H-index value was 134. There is a general upward trend over the years, and it was observed that it has intensified in the last 5 to 6 years. With the Reference Spectroscopy analysis, it was determined that the most intensively cited studies on delirium were the studies of 2013 and 2010. The distribution of keywords in recent years has focused on analgosedation, acute brain injury, older patient, COVID-19, and fragility. When examined for the top 100 cited articles, it was seen that mobilization, guidelines, pain, activities of daily living, anesthesia, sedation, and haloperidol have become prominent in recent years. Conclusion In recent years, there has been a noticeable increase in the volume of research focusing on delirium studies within the field of critical care medicine. Staying current with trends, incorporating findings from frequently cited studies, and customizing interventions to suit modern difficulties can all improve the quality of care offered to critically ill patients and lead to better outcomes.

Implementing Screening for Neonatal Delirium in the Neonatal Intensive Care Unit: A Quality Improvement Initiative.

Delirium is not commonly diagnosed in neonatal intensive care units and can adversely impact patient outcomes in the ICU setting. Recognition of delirium in the NICU is a necessary first step to address the potential impact on neonatal outcomes. We conducted a quality improvement initiative implementing screening for neonatal delirium. We aimed to increase screening in NICU patients from 0% to 85% by March 2022. Interdisciplinary meetings were held with key stakeholders to develop a clinical algorithm. We used standardized tools for delirium screening. Our process measures included weekly nursing compliance with Richmond Agitation Sedation Scale/Cornell Assessment of Pediatric Delirium/ scoring documentation (Fig. 1) and patients referred to psychiatry. Outcome measures included the percentage of patients screened for delirium before discharge. We conducted Plan-Do-Study Act cycles to optimize the screening process in the electronic medical record (EMR). This included creating an order set, documentation flowsheets, and prompts in the EMR for patients. After initial implementation, we achieved an average weekly screening compliance of 76% (Fig. 1). Inclusion criteria expansion resulted in a downward compliance shift to 59%. Subsequently, the addition of the EMR checklist resulted in a center-line shift to a sustained average weekly screening compliance of 77%. An average of 82% of all eligible NICU patients received delirium screening before discharge (Fig. 2). Using quality improvement methodology, there was increased screening and recognition of delirium in our NICU. Future research efforts could focus on assessing preventive measures and the impact of neonatal delirium on patient outcomes.

Self-efficacy of ICU nurses in delirium care: an analysis of the current status and influencing factors

ObjectiveThe aim of this study was to assess the current status of delirium care self-efficacy among nurses in the intensive care unit (ICU) and the level of their knowledge about delirium in the ICU, more importantly, to analyze factors influencing the delirium care self-efficacy of ICU nurses and to provide a theoretical basis for ICU nursing managers to develop strategies for effective delirium care and management.MethodsThe study was based on a sample of 283 ICU nurses from eight hospitals in Chongqing selected using a convenience sampling method between July 2023 and September 2023. The tools used included a general information questionnaire, the Chinese version of the Delirium Care Self-Efficacy of ICU Nurses Scale, and the Chinese version of the ICU Delirium Knowledge Level Questionnaire.ResultsThe self-efficacy score (47.84 ± 9.93) of ICU nurses was positively correlated with the delirium knowledge level score (12.32 ± 3.47, r = 0.591, P < 0.001). Multivariate linear regression analysis identified the gender of the nurse, hospital level (tier), duration of ICU work experience, whether the nurse was a specialized ICU nurse, whether the nurse received delirium-related training, and the level of knowledge about delirium (all P < 0.05) as the influencing factors for the delirium care self-efficacy of ICU nurses.ConclusionIt is recommended that ICU nursing managers offer targeted interventions based on the influencing factors to improve the delirium care self-efficacy of ICU nurses and their delirium knowledge levels, thereby reducing the incidence of delirium and improving the quality of care provided for patients with delirium in the ICU.

Assessment of ICU nurses' competency towards delirium among critically ill patients.

ICU nurses play a critical role in managing delirium in critically ill patients, yet their competency in this area remains under-explored. To assess ICU nurses' competency including their knowledge, practice, and attitudes toward delirium among critically ill patients. A correlational descriptive study was conducted with 67 nurses in the medical intensive care unit at Suez Canal University Hospitals. Data was collected using an online survey and analyzed using descriptive statistics, ANOVA, and Pearson's correlation. Nurses showed a moderate knowledge level (M = 8.55), a low practice level (M = 6.62), and positive attitudes (M = 21.65) toward ICU delirium. ANOVA results indicated significant differences in practice scores based on educational level, F (2, 64) = 3.361, p = .041, and in knowledge scores based on ICU experience, F(3, 63) = 6.455, p < .001. Nurses with Master of Science in Nursing (MSN) degrees had higher practice scores than those with diplomas or Bachelor of Science in Nursing (BSN) degrees. There were no significant differences in knowledge and attitude scores based on educational level or age. Gender differences were minimal, with male nurses slightly outperforming female nurses. Correlation analysis showed positive relationships between age, education, ICU experience, and ICU nurses' levels of knowledge and practice. ICU nurses demonstrate a knowledge-practice gap in delirium management. Targeted educational interventions, mentorship programs, and a focus on practical skills are essential to enhance delirium care. These findings highlight the urgent need for comprehensive delirium education and training programs for ICU nurses. By improving nurses' knowledge and practice, healthcare organizations can significantly enhance the early detection, prevention, and management of delirium, ultimately leading to improved patient outcomes and reduced length of stay in the ICU.

The Management and Prevention of Delirium in Elderly Patients Hospitalised in Intensive Care Units: A Systematic Review.

Delirium or an acute confusional state (ACS) is characterised as being a frequent and complex hospital complication in older adult patients, which can affect their level of independence and increase patient morbidity and mortality. Critically ill patients in the intensive care unit (ICU) frequently develop ICU delirium, leading to longer hospital and ICU stays, increased mortality and long-term impairment. This review aims to assess existing evidence of interventions that can be considered effective for the management and prevention of delirium in ICUs, reducing short-term morbidity and mortality, ICU and hospital admission times and the occurrence of other long-term complications. For this systematic review, we searched Medline, PubMed, Cochrane Library, CINHAL, LILACS, SciELO and Dialnet from January 2018 to August 2024, in English, Spanish and French. MeSH descriptors were adjusted to search the different databases. We also checked Prospero for ongoing systematic reviews. The electronic search yielded a total of 2656 studies, of which 14 trials met the eligibility criteria, with a total of 14,711 participants. We included eight randomised clinical trial (RCTs), four cohort analyses, one systematic review and one observational trial, including participants over 65 years admitted to the ICU. Ten of these studies were based on pharmacological interventions, three of them examined non-pharmacological interventions and the remaining study examined mixed (pharmacological and non-pharmacological) interventions. Six placebo RCTs were included, plus four reported comparisons between different drugs. Regarding non-pharmacological interventions, nursing programmes focused on optimising modifiable risk factors or the use of therapies such as bright light are emerging. Regarding mixed interventions, we found the combination of invasive techniques and with sedoanalgesia. Due to its satisfactory level of sedation, dexmedetomidine is presented as a viable option because, although olanzapine offers safer results, postoperative administration angiotensin inhibitor systems significantly reduced the incidence of delirium. As for propofol, no significant differences were found. Among the non-pharmacological and mixed therapies, bright light therapy was able to reduce the incidence of delirium, and the combination of epidural/general anaesthesia was effective in all subtypes of delirium. Concerning the remaining interventions, the scientific evidence is still insufficient to provide a definitive recommendation.

Clinician and Visitor Activity Patterns in an Intensive Care Unit Room: A Study to Examine How Ambient Monitoring Can Inform the Measurement of Delirium Severity and Escalation of Care.

The early detection of the acute deterioration of escalating illness severity is crucial for effective patient management and can significantly impact patient outcomes. Ambient sensing technology, such as computer vision, may provide real-time information that could impact early recognition and response. This study aimed to develop a computer vision model to quantify the number and type (clinician vs. visitor) of people in an intensive care unit (ICU) room, study the trajectory of their movement, and preliminarily explore its relationship with delirium as a marker of illness severity. To quantify the number of people present, we implemented a counting-by-detection supervised strategy using images from ICU rooms. This was accomplished through developing three methods: single-frame, multi-frame, and tracking-to-count. We then explored how the type of person and distribution in the room corresponded to the presence of delirium. Our designed pipeline was tested with a different set of detection models. We report model performance statistics and preliminary insights into the relationship between the number and type of persons in the ICU room and delirium. We evaluated our method and compared it with other approaches, including density estimation, counting by detection, regression methods, and their adaptability to ICU environments.

Impact of an enhanced recovery after surgery program integrating cardiopulmonary rehabilitation on post-operative prognosis of patients treated with CABG: protocol of the ERAS-CaRe randomized controlled trial

BackgroundCoronary artery bypass grafting is associated with a high occurrence of postoperative cardiopulmonary complications. Preliminary evidence suggested that enhanced recovery after surgery can effectively reduce the occurrence of postoperative cardiopulmonary complications. However, enhanced recovery after surgery with systematic integration of cardiopulmonary rehabilitation (ERAS-CaRe) into for Coronary artery bypass grafting has not been evaluated so far. We thus design the ERAS-CaRe randomized-controlled trial to evaluate possible superiority of embedding cardiopulmonary rehabilitation in ERAS over ERAS alone as well as to investigate effects of differential timing of cardiopulmonary rehabilitation within enhanced recovery after surgery (pre-, post-, perio-operative) on post-operative cardiopulmonary complications following Coronary artery bypass grafting surgery.MethodsERAS-CaRe is a pragmatic, randomized-controlled, parallel four-arm, clinical trial. Three hundred sixty patients scheduled for Coronary artery bypass grafting in two Chinese hospitals will be grouped randomly into (i) Standard enhanced recovery after surgery or (ii) pre-operative ERAS-CaRe or (iii) post-operative ERAS-CaRe or (iv) perio-operative ERAS-CaRe. Primary outcome is the occurrence of cardiopulmonary complications at 10 days after Coronary artery bypass grafting. Secondary outcomes include the occurrence of other individual complications including cardiac, pulmonary, stroke, acute kidney injury, gastrointestinal event, ICU delirium rate, reintubation rate, early drainage tube removal rate, unplanned revascularization rate, all-cause mortality, ICU readmission rate, plasma concentration of myocardial infarction-related key biomarkers etc.DiscussionThe trial is designed to evaluate the hypothesis that a cardiopulmonary rehabilitation based enhanced recovery after surgery program reduces the occurrence of cardiopulmonary complications following Coronary artery bypass grafting and to determine optimal timing of cardiopulmonary rehabilitation within enhanced recovery after surgery. The project will contribute to increasing the currently limited knowledge base in the field as well as devising clinical recommendations.Trial registrationThe trial was registered at the Chinese Clinical Trials Registry on 25 August 2023 (ChiCTR2300075125; date recorded: 25/8/2023, https://www.chictr.org.cn/).

Using Machine Learning and Electronic Health Records to Identify Neuropsychiatric Risk Scores for Delirium in ICU and General Hospital Settings.

Delirium is a common and acute neuropsychiatric syndrome that requires timely intervention to prevent its associated morbidity and mortality. Yet, its diagnosis and symptoms are often overlooked due to its variable clinical presentation and fluctuating nature. Thus, in this study, we address the barriers to delirium diagnosis by utilizing a machine learning-based predictive algorithm for incident delirium that relies on archived electronic health records (EHRs) data. We used the Medical Information Mart for Intensive Care (MIMIC) database to create a detailed dataset for identifying delirium in intensive care unit (ICU) patients. Our approach involved training machine learning models on this dataset to pinpoint critical clinical features for delirium detection. These features were then refined and applied to non-ICU patients using EHRs from the American University of Beirut Medical Center (AUBMC). Our study assessed machine learning models like Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Classification and Regression Trees (CART), Random Forest (RF), Neural Oblivious Decision Ensembles (NODE), and Logistic Regression (LR), highlighting superior delirium detection in diverse clinical settings. The CatBoost model excelled in ICU environments with an F1 Score of 89.2%, while XGBoost performed best in general hospital settings with a 75.4% F1 Score. Interpretations using Tabular Local Interpretable Model-agnostic Explanations (LIME) revealed critical indicators such as prothrombin time and hematocrit levels, enhancing model transparency and clinical applicability. These clinical insights help differentiate the delirium predictors between ICU patients, who are often sensitive to various factors. The proposed predictive algorithm improves delirium detection rates and streamlines efficiency in hospital electronic systems, thereby enabling prompt interventions to prevent delirium progression and associated complications. The clinical indicators for delirium that we identified in general hospital settings and ICU can greatly help healthcare professionals identify potential causes of delirium and reduce misdiagnosis.

Dexmedetomidine: A Review of Its Use for the Treatment and Prevention of Hyperactive Delirium in Intensive Care Units (ICU)

Dexmedetomidine: A Review of Its Use for the Treatment and Prevention of Hyperactive Delirium in Intensive Care Units (ICU)

Gabapentin for Delirium in Infants in the Neonatal Intensive Care Unit

OBJECTIVE A protocol was developed for neonatal intensive care unit (NICU) delirium: Step 1, gabapentin for pain or melatonin for sleep; Step 2, add on other Step 1 agent; Step 3, antipsychotics. The purpose of this study was to describe the utility and dosing of gabapentin for NICU delirium. METHODS Retrospective evaluation of NICU patients from January 1, 2021–December 31, 2022 who received &amp;gt;1 dose of gabapentin based on the delirium protocol. Data collection included demographics, gabapentin regimen, and concomitant sedatives and analgesics. The primary objective was to identify the number of patients receiving gabapentin for Step 1 or Step 2. Secondary objectives included identifying the number of patients requiring antipsychotics (Step 3), the gabapentin regimen, comparison of Échelle de Douleur et d'Inconfort du Nouveau-né (EDIN), Cornell Assessment of Pediatric Delirium (CAPD), and Withdrawal Assessment Tool-1 (WAT-1) scores 72 hours pre- and post-gabapentin initiation, and comparison of opioids, clonidine, and melatonin 24 hours pre- and 72 hours post-gabapentin initiation. Wilcoxon signed rank tests were employed with significance defined at p &amp;lt; 0.05. RESULTS Twenty-nine patients were studied. The majority (n = 22; 75.9%) received gabapentin for Step 1; no patients required Step 3. The median initial dose was 14.4 mg/kg/day divided every 8 hours. Twelve (41.4%) required increase to a median of 16.9 mg/kg/day. A significant decrease in EDIN and WAT-1 scores was noted, but there was no change in CAPD scores or opioid, clonidine, or melatonin doses pre- versus post-gabapentin. CONCLUSION The majority received gabapentin at a median dose of 14 mg/kg/day as Step 1 for delirium. Gabapentin was associated with a significant decrease in pain and withdrawal scores.

Usefulness of the 4A's test for detecting delirium in critically ill patients: a multicenter prospective observation study.

The Confusion Assessment Method for the Intensive Care Unit (CAM-ICU) is a robust and reliable instrument for discerning delirium within the specific context of the intensive care unit (ICU). Nonetheless, the CAM-ICU is burdened by various limitations, including a protracted learning curve and the need for frequent daily administration. The 4 A's Test (4AT) was formulated to assess delirium in hospitalized patients and may have distinct advantages over the CAM-ICU, particularly regarding practical applicability within the ICU bundle. This study was performed to assess the utility of the 4AT in detecting delirium in critically ill patients. This multicenter prospective observational study involved critically ill patients at four academic tertiary care hospitals in South Korea from June 2021 to September 2022. In total, 274 patients (median age, 64years; 56.9% men) were included, and 75 (27.4%) developed delirium. The 4AT showed good performance in detecting ICU delirium (area under the curve, 0.879; P < 0.001). The 4AT showed a sensitivity of 74.0%, specificity of 95.4%, positive predictive value of 77.5%, negative predictive value of 94.6%, and accuracy of 91.7% for ICU detection of delirium. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the CAM-ICU for detecting ICU delirium were 71.3%, 97.1%, 83.8%, 94.1%, and 92.6%, respectively. The 4AT showed acceptable reliability and validity for detecting ICU delirium in critically ill patients. Because the 4AT is simpler and easier to learn, this scale could be a useful alternative to the CAM-ICU for detecting delirium in critically ill patients.