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.

Using simulated family presence to decrease agitation in older hospitalized delirious patients: A randomized controlled trial.

BACKGROUND: Simulated family presence has been shown to be an effective nonpharmacological intervention to reduce agitation in persons with dementia in nursing homes. Hyperactive or mixed delirium is a common and serious complication experienced by hospitalized patients, a key feature of which is agitation. Effective nonpharmacological interventions to manage delirium are needed. OBJECTIVES: To examine the effect of simulated family presence through pre-recorded video messages on the agitation level of hospitalized, delirious, acutely agitated patients. DESIGN: Single site randomized control trial, 3 groups×4 time points mixed factorial design conducted from July 2015 to March 2016. SETTING: Acute care level one trauma center in an inner city of the state of Connecticut, USA. PARTICIPANTS: Hospitalized patients experiencing hyperactive or mixed delirium and receiving continuous observation were consecutively enrolled (n=126), with 111 participants completing the study. Most were older, male, Caucasian, spouseless, with a pre-existing dementia. METHODS: Participants were randomized to one of the following study arms: view a one minute family video message, view a one minute nature video, or usual care. Participants in experimental groups also received usual care. The Agitated Behavior Scale was used to measure the level of agitation prior to, during, immediately following, and 30min following the intervention. RESULTS: Both the family video and nature video groups displayed a significant change in median agitation scores over the four time periods (p<0.001), whereas the control group did not. The family video group had significantly lower median agitation scores during the intervention period (p<0.001) and a significantly greater proportion (94%) of participants experiencing a reduction in agitation from the pre-intervention to during intervention (p<0.001) than those viewing the nature video (70%) or those in usual care only (30%). The median agitation scores for the three groups were not significantly different at either of the post intervention time measurements. When comparing the proportion of participants experiencing a reduction in agitation from baseline to post intervention, there remained a statistically significant difference (p=0.001) between family video(60%) and usual care (35.1%) immediately following the intervention CONCLUSION: This work provides preliminary support for the use of family video messaging as a nonpharmacological intervention that may decrease agitation in selected hospitalized delirious patients. Further studies are necessary to determine the efficacy of the intervention as part of a multi-component intervention as well as among younger delirious patients without baseline dementia.

Intraoperative ketamine for prevention of postoperative delirium or pain after major surgery in older adults: an international, multicentre, double-blind, randomised clinical trial.

BACKGROUND: Delirium is a common and serious postoperative complication. Subanaesthetic ketamine is often administered intraoperatively for postoperative analgesia, and some evidence suggests that ketamine prevents delirium. The primary purpose of this trial was to assess the effectiveness of ketamine for prevention of postoperative delirium in older adults. METHODS: The Prevention of Delirium and Complications Associated with Surgical Treatments [PODCAST] study is a multicentre, international randomised trial that enrolled adults older than 60 years undergoing major cardiac and non-cardiac surgery under general anaesthesia. Using a computer-generated randomisation sequence we randomly assigned patients to one of three groups in blocks of 15 to receive placebo (normal saline), low-dose ketamine (0·5 mg/kg), or high dose ketamine (1·0 mg/kg) after induction of anaesthesia, before surgical incision. Participants, clinicians, and investigators were blinded to group assignment. Delirium was assessed twice daily in the first 3 postoperative days using the Confusion Assessment Method. We did analyses by intention-to-treat and assessed adverse events. This trial is registered with clinicaltrials.gov, number NCT01690988. FINDINGS: Between Feb 6, 2014, and June 26, 2016, 1360 patients were assessed, and 672 were randomly assigned, with 222 in the placebo group, 227 in the 0·5 mg/kg ketamine group, and 223 in the 1·0 mg/kg ketamine group. There was no difference in delirium incidence between patients in the combined ketamine groups and the placebo group (19·45% vs 19·82%, respectively; absolute difference 0·36%, 95% CI -6·07 to 7·38, p=0·92). There were more postoperative hallucinations (p=0·01) and nightmares (p=0·03) with increasing ketamine doses compared with placebo. Adverse events (cardiovascular, renal, infectious, gastrointestinal, and bleeding), whether viewed individually (p value for each >0·40) or collectively (36·9% in placebo, 39·6% in 0·5 mg/kg ketamine, and 40·8% in 1·0 mg/kg ketamine groups, p=0·69), did not differ significantly across groups. INTERPRETATION: A single subanaesthetic dose of ketamine did not decrease delirium in older adults after major surgery, and might cause harm by inducing negative experiences. FUNDING: National Institutes of Health and Cancer Center Support.

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.

Nurses' evaluation of the Confusion Assessment Method: a pilot study.

Delirium is frequently overlooked in hospitalized adult patients of all ages. Because nurses spend significant amounts of time with patients, the nursing assessment is vital to the identification of delirium. This pilot study investigated nurses'evaluation of the Confusion Assessment Method related to ease of use and helpfulness in identifying delirium in adult patients on two hospital units. Delirium rates are reported for patients across all shifts for 1 month. The majority of nurses found the Confusion Assessment Method to be an effective, user-friendly instrument for the assessment of patients' cognitive status over time.

How to try this: detecting delirium.

For patients and their loved ones, delirium can be a frightening experience. A fluctuating mental status is important to identify because it often signals a need for additional treatment. The Confusion Assessment Method (CAM) diagnostic algorithm enables nurses to assess for delirium by identifying the four features of the disorder that distinguish it from other forms of cognitive impairment. It can be completed in five minutes and is easily incorporated into ongoing assessments of hospitalized patients. (This screening tool is included in the series Try This: Best Practices in Nursing Care to Older Adults, from the Hartford Institute for Geriatric Nursing at New York University's College of Nursing.) For a free online video demonstrating the use of this tool, go to http://links.lww.com/A209.