Prediction of Incident Delirium Using a Random Forest classifier

Delirium is a serious medical complication associated with poor outcomes. Given the complexity of the syndrome, prevention and early detection are critical in mitigating its effects. We used Confusion Assessment Method (CAM) screening and Electronic Health Record (EHR) data for 64,038 inpatient visits to train and test a model predicting delirium arising in hospital. Incident delirium was defined as the first instance of a positive CAM occurring at least 48 h into a hospital stay. A Random Forest machine learning algorithm was used with demographic data, comorbidities, medications, procedures, and physiological measures. The data set was randomly partitioned 80% / 20% for training and validating the predictive model, respectively. Of the 51,240 patients in the training set, 2774 (5.4%) experienced delirium during their hospital stay; and of the 12,798 patients in the validation set, 701 (5.5%) experienced delirium. Under-sampling of the delirium negative population was used to address the class imbalance. The Random Forest predictive model yielded an area under the receiver operating characteristic curve (ROC AUC) of 0.909 (95% CI 0.898 to 0.921). Important variables in the model included previously identified predisposing and precipitating risk factors. This machine learning approach displayed a high degree of accuracy and has the potential to provide a clinically useful predictive model for earlier intervention in those patients at greatest risk of developing delirium.

Assessment of Delirium in Intensive Care Unit Patients: Educational Strategies

BACKGROUND

Delirium is an acute brain dysfunction associated with poor outcomes in intensive care unit (ICU) patients. Critical care nurses play an important role in the prevention, detection, and management of delirium, but they must be able to accurately assess for it. The Confusion Assessment Method for the Intensive Care Unit (CAM-ICU) instrument is a reliable and valid method to assess for delirium, but research reveals most nurses need practice to use it proficiently.

METHOD

A pretest-posttest design was used to evaluate the success of a multimodal educational strategy (i.e., online learning module coupled with standardized patient simulation experience) on critical care nurses' knowledge and confidence to assess and manage delirium using the CAM-ICU.

RESULTS

Participants (N = 34) showed a significant increase (p < .001) in confidence in their ability to assess and manage delirium following the multimodal education. No statistical change in knowledge of delirium existed following the education.

CONCLUSION

A multimodal educational strategy, which included simulation, significantly added confidence in critical care nurses' performance using the CAM-ICU. J Contin Nurs Educ. 2017;48(5):239-244.

Analysis of multi-dimensional contemporaneous EHR data to refine delirium assessments

Delirium is a potentially lethal condition of altered mental status, attention, and level of consciousness with an acute onset and fluctuating course. Its causes are multi-factorial, and its pathophysiology is not well understood; therefore clinical focus has been on prevention strategies and early detection. One patient evaluation technique in routine use is the Confusion Assessment Method (CAM): a relatively simple test resulting in 'positive', 'negative' or 'unable-to-assess' (UTA) ratings. Hartford Hospital nursing staff use the CAM regularly on all non-critical care units, and a high frequency of UTA was observed after reviewing several years of records. In addition, patients with UTA ratings displayed poor outcomes such as in-hospital mortality, longer lengths of stay, and discharge to acute and long term care facilities. We sought to better understand the use of UTA, especially outside of critical care environments, in order to improve delirium detection throughout the hospital. An unsupervised clustering approach was used with additional, concurrent assessment data available in the EHR to categorize patient visits with UTA CAMs. The results yielded insights into the most common situations in which the UTA rating was used (e.g. impaired verbal communication, dementia), suggesting potentially inappropriate ratings that could be refined with further evaluation and remedied with updated clinical training. Analysis of the patient clusters also suggested that unrecognized delirium may contribute to the poor outcomes associated with the use of UTA. This method of using temporally related high dimensional EHR data to illuminate a dynamic medical condition could have wider applicability.

Informal caregivers and detection of delirium in postacute care: a correlational study of the confusion assessment method (CAM), confusion assessment method-family assessment method (CAM-FAM) and DSM-IV criteria

OBJECTIVES

Delirium is a common, serious and potentially life-threatening syndrome affecting older adults. This syndrome continues to be under-recognised and under treated by healthcare professionals across all care settings. Older adults who develop delirium have poorer outcomes, higher mortality and higher care costs. The purposes of this study were to correlate the confusion assessment method-family assessment method and confusion assessment method in the detection of delirium in postacute care, to correlate the confusion assessment method-family assessment method and diagnostic and statistical manual of mental disorders text revision criteria in detection of delirium in postacute care, to determine the prevalence of delirium in postacute care elders and to describe the relationship of level of cognitive impairment and delirium in the postacute care setting. Implications for Practice Delirium is disturbing for patients and caregivers. Frequently . family members want to provide information about their loved one. The use of the CAM-FAM and CAM can give a more definitive determination of baseline status. Frequent observations using both instruments may lead to better recognition of delirium and implementation of interventions to prevent lasting sequelae.

METHODS

Descriptive studies determined the strengths of relationship between the confusion assessment method, confusion assessment method-family assessment method, Mini-Cog and diagnostic and statistical manual of mental disorders text revision criteria in detection of delirium in the postacute care setting.

RESULTS

Prevalence of delirium in this study was 35%. The confusion assessment method-family assessment method highly correlates with the confusion assessment method and diagnostic and statistical manual of mental disorders text revision criteria for detecting delirium in older adults in the postacute care setting. Persons with cognitive impairment are more likely to develop delirium. Family members recognise symptoms of delirium when asked.

DISCUSSION

The confusion assessment method-family assessment method is a valid tool for detection of delirium.

IMPLICATIONS FOR PRACTICE

Delirium is disturbing for patients and caregivers. Frequently. family members want to provide information about their loved one. The use of the CAM-FAM and CAM can give a more definitive determination of baseline status. Frequent observations using both instruments may lead to better recognition of delirium and implementation of interventions to prevent lasting sequelae.

Factors that contribute to underrecognition of delirium by registered nurses in acute care settings: a scoping review of the literature to explain this phenomenon

AIMS AND OBJECTIVES

In order to obtain more information regarding this phenomenon, a scoping review of the literature was undertaken to analyse current research on the recognition of delirium by registered nurses in acute care settings.

BACKGROUND

Delirium is often manifested as a sign of an underlying undiagnosed condition that requires immediate intervention and is frequently manifested in acute care settings. Unfortunately, registered nurses often do not recognise delirium and its occurrence goes under-reported.

DESIGN/METHODS

Based on six inclusion criteria, a search in numerous databases using terms such as delirium detection, recognition and diagnosis by registered nurses was undertaken. Eight quantitative studies were deemed relevant and analysed for this scoping review.

RESULTS

Seven major categories emerged: the fluctuating nature of delirium, the impact of delirium education on its recognition, communication barriers, inadequate use of delirium assessment tools, lack of conceptual understanding of delirium, delirium as a burden and the likeness of delirium and dementia. A brief summary of the findings in each category is reported here.

CONCLUSIONS

The scoping review revealed that delirium remains underrecognised by registered nurses, which potentially contributes to reduced quality of nursing care for clients experiencing this condition. Further research on delirium and the processes that registered nurses use to recognise it is timely and will facilitate the development of evidence-based interventions to manage it.

RELEVANCE TO CLINICAL PRACTICE

While acute care registered nurses have historically reported dramatic changes in cognitive and neuro-biological functions in ill older adults, the literature highlighted in this scoping review revealed the following: (1) the need for further research to validate delirium assessment tools and, (2) the need for education and training for registered nurses on the use of these assessment tools to promote early recognition and thereby decrease the incidence of delirium in older adults.

Analysis of a health team's records and nurses' perceptions concerning signs and symptoms of delirium

This study investigates the extent of under-diagnosis of acute confusion/delirium by analyzing the records of a health team and the perception of nurses concerning this phenomenon. This quantitative study was developed in a central university hospital in Portugal and used the documentary and interview techniques. The sample obtained through the application of the NeeCham's scale was composed of 111 patients with the diagnosis of acute confusion/delirium hospitalized in the medical and surgical acute care units. A rate of 12.6% of under-diagnosis was identified in the records and a rate of 30.6% was found taking into account the perception of nurses. No indicators of acute confusion/delirium were found in 8.1% of the 111 cases and only 4.5% of the patients were diagnosed with acute confusion/delirium. The results indicate there is difficulty in identifying acute confusion/delirium, with implications for the quality of care, suggesting the need to implement training measures directed to health teams.

A discursive exploration of the practices that shape and discipline nurses' responses to postoperative delirium

A discursive exploration of the practices that shape and discipline nurses' responses to postoperative delirium Although delirium is classified as a medical emergency, it is often not treated as such by health care providers. The aim of this study was to critically examine, through a poststructural, Foucauldian concept of discourse, the language practices and discourses that shape and discipline nurses' care of older adults with postoperative delirium (POD) with a purpose to question accepted nursing practice. The study was based on data collected from face-to-face, in-depth, personal interviews with six nurses who work on an acute postoperative patient care unit. Five analytic readings of the data identified two prominent discourses at work in nursing practice which influenced the care of patients with POD. These were identified as discourses of legitimacy/illegitimacy and discourses of nursing work. Through the process of poststructural analysis it became evident that one overriding discourse - the biomedical/scientific discourse - served to direct, legitimize and govern all other discourses. The findings of this study have implications for nursing knowledge and practice, length of hospital stay and improved patient outcomes. This study builds on previous work and is the first study to conduct a discourse analysis illuminating nurses' responses to POD through comparison with other acute medical emergencies from a poststructural perspective.

Nursing care, delirium, and pain management for the hospitalized older adult

Delirium is a reversible cognitive disorder that has a rapid onset. Delirium risk factors include older age, severity of illness, poorer baseline functional status, comorbid medical conditions, and dementia. There are adverse consequences of delirium, including increased length of stay and increased mortality. Therefore, it is important for nurses to identify clients at risk and prevent and manage delirium in the hospitalized older client. Once high-risk clients are identified, prevention strategies may be used to reduce the incidence. Examples of prevention strategies include providing glasses and working hearing aids and effective pain management. This article discusses various assessment instruments that detect the presence of delirium. With this information, nurses are better equipped to evaluate the best assessment options for their work setting. Early detection is crucial to reduce the adverse consequences of delirium. Once a client is found to be experiencing delirium, a treatment plan can be established using both nonpharmacologic and pharmacologic interventions. In addition, the identification and the correction of etiologies of delirium can shorten the course of delirium.

Caring for hospitalized older adults at risk for delirium: the silent, unspoken piece of nursing practice

More than half of hospitalized older adults will experience delirium, which--if left untreated--can lead to detrimental outcomes. Despite the prevalence and severity of delirium, nurses recognize less than one third of cases. Because little is known about how nurses manage this problem, a qualitative study was conducted to explore how nurses care for hospitalized older adults at risk for delirium. The data revealed that nurses care for older adults byTaking a Quick Look, Keeping an Eye on Them, and Controlling the Situation. The context in which nurses choose their priorities and interventions was reflected in the themes of the Care Environment and Negative Beliefs and Attitudes about older adults. Nurses are caring for an older population whose care requirements are different than those of younger people and in a context where this challenging work is rarely addressed. To improve care, the older population must be acknowledged, and nurses must possess the knowledge and resources needed to meet this population's unique needs.