Risk predictive models for delirium in the intensive care unit: a systematic review and meta-analysis

Chen, Xiangping; Lao, Yuewen; Zhang, Yi; Qiao, Lijie; Zhuang, Yiyu

doi:10.21037/apm-20-1183

Cited by 16 publications

(13 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such methods are relevant for understanding the problem of delirium and its consequences in terms of clinical outcomes. For predictive models, instead, logistic regression [ 25 , 26 ] is mostly used, recently with machine learning technique [ 27 ]. The Cox model (CM) is used when considering time to define the probability of developing an event.…”

Section: Introductionmentioning

confidence: 99%

Profiling Delirium Progression in Elderly Patients via Continuous-Time Markov Multi-State Transition Models

Ocagli

Azzolina

Soltanmohammadi

et al. 2021

JPM

View full text Add to dashboard Cite

Poor recognition of delirium among hospitalized elderlies is a typical challenge for health care professionals. Considering methodological insufficiency for assessing time-varying diseases, a continuous-time Markov multi-state transition model (CTMMTM) was used to investigate delirium evolution in elderly patients. This is a longitudinal observational study performed in September 2016 in an Italian hospital. Change of delirium states was modeled according to the 4AT score. A Cox model (CM) and a CTMMTM were used for identifying factors affecting delirium onset both with a two-state and three-state model. In this study, 78 patients were enrolled and evaluated for 5 days. Both the CM and the CTMMTM show that urine catheter (UC), aging, drugs, and invasive devices (ID) are risk factors for delirium onset. The CTMMTM model shows that transition from no-delirium/cognitive impairment to delirium was associated with aging (HR = 1.14; 95%CI, 1.05, 1.23) and neuroleptics (HR = 4.3; 1.57, 11.77), dopaminergic drugs (HR = 3.89; 1.2, 12.6), UC (HR = 2.92; 1.09, 7.79) and ID (HR = 1.67; 103, 2.71). These results are confirmed by the multivariable model. Aging, ID, antibiotics, drugs affecting the central nervous system, and absence of moving ability are identified as the significant predictors of delirium. Additionally, it seems that modeling with CTMMTM may show associations that are not directly detectable with the traditional CM.

show abstract

Section: Introductionmentioning

confidence: 99%

Profiling Delirium Progression in Elderly Patients via Continuous-Time Markov Multi-State Transition Models

Ocagli

Azzolina

Soltanmohammadi

et al. 2021

JPM

View full text Add to dashboard Cite

show abstract

“…Due to the fluctuating characteristics of delirium, non‐delirious patients may become delirious suddenly which required adjustment of restraint level. Integration of a tool that integrated delirium prediction models and has been shown with good performance in the ICU, such as E‐PRE‐DELIRIC and PRE‐DELIRIC (Chen et al, 2020), may further improve the accuracy of restraint decision making.…”

Section: Discussionmentioning

confidence: 99%

“…Due to the fluctuating characteristics of delirium, non-delirious patients may become delirious suddenly which required adjustment of restraint level. Integration of a tool that integrated delirium prediction models and has been shown with good performance in the ICU, such as E-PRE-DELIRIC and PRE-DELIRIC(Chen et al, 2020), may further improve the accuracy of restraint decision making.5 | CONCLUSIONThe Restraint Decision Tree was shown to be feasible, acceptable, and usable in critically ill adult patients, which significantly minimizes restraint use with no increase in accidental catheter removal. Our study is a further key initiative to enhance the appropriate use of restraint in the ICU.…”

mentioning

confidence: 96%

Development and implementation of a novel decision support tool on physical restraint use in critically ill adult patients

Chen

Zhuang

Lao

et al. 2021

Int J of Nursing Practice

Self Cite

View full text Add to dashboard Cite

Aim To investigate whether a novel decision support tool would effectively minimize physical restraint use in critically ill adult patients. Design A nonequivalent quasi‐experimental design combined with a descriptive qualitative approach was used. Methods A Restraint Decision Tree was developed based on a qualitative study that explored the barriers to employ the Restraint Decision Wheel. During the quasi‐experimental study, patients admitted to the unit between October 2017 and March 2018 were enrolled as the control group receiving the Restraint Decision Wheel (n = 528), whereas patients between April 2018 and September 2018 were enrolled as the intervention group receiving the Restraint Decision Tree (n = 564). The physical restraint rate, accidental catheter removal rate and nurses' satisfaction were compared. Results The Restraint Decision Tree significantly decreased physical restraint use. No significant difference in the rate of accidental catheter removal was found. Nurses reported increased satisfaction with the restraint decision‐making. Conclusions The Restraint Decision Tree could minimize physical restraint use. Physicians' involvement in the restraint decision‐making and nurses' competence in delirium assessment may be essential for successful implementation of the Restraint Decision Tree.

show abstract

“…Three recent systematic reviews found 26 unique prediction models for predicting delirium in ICU [9,12,13]. Of these models, 4 were identified by the review papers to be "dynamic" models: DYNAMIC-ICU [14], Auto-DelRAS [15], ABD-pm [16], and a model developed by Oh et al [17].…”

Section: Related Workmentioning

confidence: 99%

Predicting the Onset of Delirium on Hourly Basis in an Intensive Care Unit Following Cardiac Surgery

Lapp

Roper

Kavanagh

et al. 2022

2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)

View full text Add to dashboard Cite

Delirium, affecting up to 52% of cardiac surgery patients, can have serious long-term effects on patients by damaging cognitive ability and causing subsequent functional decline. This study reports on the development and evaluation of predictive models aimed at identifying the likely onset of delirium on an hourly basis in intensive care unit following cardiac surgery. Most models achieved a mean AUC > 0.900 across all lead times. A support vector machine achieved the highest performance across all lead times of AUC = 0.941 and Sensitivity = 0.907, and BARTm, where missing values were replaced with missForest imputation, achieved the highest Specificity of 0.892. Being able to predict delirium hours in advance gives clinicians the ability to intervene and optimize treatments for patients who are at risk and avert potentially serious and life-threatening consequences.

show abstract

Risk predictive models for delirium in the intensive care unit: a systematic review and meta-analysis

Cited by 16 publications

References 39 publications

Profiling Delirium Progression in Elderly Patients via Continuous-Time Markov Multi-State Transition Models

Profiling Delirium Progression in Elderly Patients via Continuous-Time Markov Multi-State Transition Models

Development and implementation of a novel decision support tool on physical restraint use in critically ill adult patients

Predicting the Onset of Delirium on Hourly Basis in an Intensive Care Unit Following Cardiac Surgery

Contact Info

Product

Resources

About