Background: delirium is a clinical syndrome associated with multiple short and long-term complications and therefore prevention is an essential part of its management. This study was designed to assess the efficacy of multicomponent intervention in delirium prevention. Methods: a total of 287 hospitalised patients at intermediate or high risk of developing delirium were randomised to receive a non-pharmacological intervention delivered by family members (144 patients) or standard management (143 patients). The primary efficacy outcome was the occurrence of delirium at any time during the course of hospitalisation. Three validated observers performed the event adjudication by using the confusion assessment method screening instrument. Results: there were no significant differences in the baseline characteristics between the two groups. The primary outcome occurred in 5.6% of the patients in the intervention group and in 13.3% of the patients in the control group (relative risk: 0.41; confidence interval: 0.19–0.92; P = 0.027). Conclusion: the results of this study show that there is a benefit in the non-pharmacological prevention of delirium using family members, when compared with standard management of patients at risk of developing this condition.

Background: delirium is a complex neuropsychiatric syndrome that is common among elderly inpatients. It has been associated with increased mortality, longer hospital stays, cognitive and functional decline and increased institutionalisation rates. Multicomponent interventions, a series of non-pharmacological strategies frequently handled by nursing staff, might be useful for prevention. Objectives: to assess the efficacy of multicomponent interventions in preventing incident delirium in the elderly. Methods: a systematic review of randomised trials was undertaken. Two independent reviewers performed iterative literature searches in seven databases without language restrictions. Grey literature repositories were considered as well. The quality of included trials was assessed by using the criteria established by the Cochrane Collaboration. When possible, data were synthesised into a meta-analysis. Heterogeneity was assessed using the χ² and I² tests. Findings: a total of 21,788 citations were screened, and seven studies of diverse quality were included in the review, comprising 1,691 participants. Multicomponent interventions significantly reduced incident delirium (relative risk [RR] 0.73, 95% confidence interval [CI] 0.63–0.85, P < 0.001) and accidental falls during the hospitalisation (RR 0.39, 95% CI 0.21, 0.72, P = 0.003), without evidence of differential effectiveness according to ward type or dementia rates. Non-significant reductions in delirium duration, hospital stay and mortality were found as well. Interpretation: multicomponent interventions are effective in preventing incident delirium among elderly inpatients. Effects seemed to be stable among different settings. Due to the limited amount of data, potential benefits in survival need to be confirmed in further studies. Future research should be aimed at contrasting different multicomponent programmes to select the most useful interventions.

Note From the Writing Group: Throughout this article, the reader will notice combinations of superscripted letters and numbers (eg, “Family Presence During ResuscitationPeds-003”). These callouts are hyperlinked to evidence-based worksheets, which were used in the development of this article. An appendix of worksheets, applicable to this article, is located at the end of the text. The worksheets are available in PDF format and are open access.

Each year, more than 30% of people over 65 years-old suffer some fall. Unfortunately, this can generate physical and psychological damage, especially if they live alone and they are unable to get help. In this field, several studies have been performed aiming to alert potential falls of the older people by using different types of sensors and algorithms. In this paper, we present a novel non-invasive monitoring system for fall detection in older people who live alone. Our proposal is using very-low-resolution thermal sensors for classifying a fall and then alerting to the care staff. Also, we analyze the performance of three recurrent neural networks for fall detections: long short-term memory (LSTM), gated recurrent unit, and Bi-LSTM. As many learning algorithms, we have performed a training phase using different test subjects. After several tests, we can observe that the Bi-LSTM approach overcome the others techniques reaching a 93% of accuracy in fall detection. We believe that the bidirectional way of the Bi-LSTM algorithm gives excellent results because the use of their data is influenced by prior and new information, which compares to LSTM and GRU. Information obtained using this system did not compromise the user’s privacy, which constitutes an additional advantage of this alternative.

BACKGROUND Delirium is common among the critically ill. Nonpharmacologic interventions are reportedly effective in reducing incident delirium, but limited data specific to this population exist. OBJECTIVES To assess the efficacy and describe the implementation strategy of a multicomponent intervention to prevent delirium in an intensive care unit. METHODS A before-and-after study was conducted in an intensive care unit between May 2014 through August 2015. Adult participants were enrolled consecutively, excluding only those who refused to participate. Tailored interventions took available evidence into consideration. Components included early mobilization, physical therapy, reorientation, cognitive stimulation, drug reviews, environmental stimulation, avoidance of sensory deprivation, pain control, restraint use avoidance, and family participation. Incident delirium was assessed twice daily using the Confusion Assessment Method for the Intensive Care Unit. Multivariate logistic regression was used to control for confounders. RESULTS The study included 227 patients (54.7% male; mean [SD] age, 63.3 [18.3] years). Our strategy significantly reduced delirium (from 38% to 24%; relative risk, 0.62; 95% CI, 0.40–0.94; P = .02), an association that remained significant after adjusting for confounders. Adherence rates were more than 85% in all intervention domains (except daily reorientation) that were overseen by health care providers. CONCLUSIONs The strategy was successful in reducing delirium. Self-removals of invasive implements decreased, an observation that has not been previously described. No difference in mortality rate was seen, as has been reported in other studies. Early participation of the whole team, shared leadership, and the provision of concrete tasks were key to the success of this multicomponent intervention.