Dataset Information

Incidence and predictors of delirium on the intensive care unit in patients with acute kidney injury, insight from a retrospective registry.

ABSTRACT: Acute kidney injury (AKI) and delirium are common complications on the intensive care unit (ICU). Few is known about the association of AKI and delirium, as well as about incidence and predictors of delirium in patients with AKI. In this retrospective study, all patients with AKI, as defined by the KDIGO (kidney disease improving global outcome) guideline, treated for more than 24 h on the ICU in an university hospital in 2019 were included and analyzed. Delirium was defined by a NuDesc (Nursing Delirium screening scale) ≥ 2, which is evaluated three times a day in every patient on our ICU as part of daily routine. A total of 383/919 (41.7%) patients developed an AKI during the ICU stay. Delirium was detected in 230/383 (60.1%) patients with AKI. Independent predictors of delirium were: age, psychiatric disease, alcohol abuse, mechanical ventilation, severe shock, and AKI stage II/III (all p < 0.05). The primary cause of illness had no influence on the onset of delirium. Among patients with AKI, the duration of the ICU stay correlated with higher stages of AKI and the presence of delirium (stage I/no delirium: median 1.9 (interquartile range (25th-75th) 1.3-2.9) days; stage II/III/no delirium: 2.6 (1.6-5.5) days; stage I/delirium: 4.1 (2.5-14.3) days; stage II/III/delirium: 6.8 (3.5-11.9) days; all p < 0.01). Delirium, defined as NuDesc ≥ 2 is frequent in patients with AKI on an ICU and independently predicted by higher stages of AKI.

SUBMITTER: Jackel M

PROVIDER: S-EPMC8390667 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundWhether perioperative hyperchloremia can induce postoperative acute kidney injury (AKI) is controversial. We investigated the association between perioperative hyperchloremia and postoperative AKI in patients admitted to the intensive care unit (ICU) after surgery.MethodsWe performed a retrospective observational study of patients admitted to the surgical ICU at a single tertiary care hospital between January 2011 and June 2016. Our primary objective was to determine whether hyperchloremia or an increase in serum chloride levels was associated with postoperative AKI. Perioperative hyperchloremia was defined as serum chloride levels ??110 mmol·L-?1 during postoperative days (PODs) 0-3. The increase in serum chloride levels was defined as the difference between preoperative and maximum postoperative serum chloride levels during the first 3 days after surgery.ResultsOf the 7991 patients included in the final analysis, 1876 (23.5%) developed hyperchloremia during PODs 0-3, and 1187 (14.9%) developed postoperative AKI. Exposure to hyperchloremia during the first 3 days after surgery was not associated with postoperative AKI (odds ratio, 1.09; 95% confidence interval, 0.80-1.49; P =?0.571). However, among patients with preoperative chronic kidney disease stage ??3 (estimated glomerular filtration rate?<?60 mL·min-?1·1.73·m-?2), the incidence of postoperative AKI was higher in patients with an increase >?6 mmol·L-?1 in serum chloride levels than in patients with an increase ??1 mmol·L-?1 (odds ratio, 1.42; 95% confidence interval, 1.09-1.84; P =?0.009). In addition, the incidence of postoperative AKI stage ??2 was not associated with exposure to hyperchloremia or with the increase in serum chloride levels during PODs 0-3, regardless of preoperative kidney function.ConclusionsExposure to perioperative hyperchloremia is not associated with postoperative AKI in surgical ICU patients. However, in patients with moderate-to-severe chronic kidney disease (stage ??3), a substantial perioperative increase in serum chloride levels may reflect a higher risk of AKI.

Project description:BackgroundDelirium frequently occurs among patients admitted to the intensive care unit (ICU). There is limited evidence to support interventions to treat or resolve delirium in patients who have already developed delirium. Therefore, the early recognition and prevention of delirium are important in the management of critically ill patients.ObjectiveThis study aims to develop and validate a delirium prediction model within 24 hours of admission to the ICU using electronic health record data. The algorithm was named the Prediction of ICU Delirium (PRIDE).MethodsThis is a retrospective cohort study performed at a tertiary referral hospital with 120 ICU beds. We only included patients who were 18 years or older at the time of admission and who stayed in the medical or surgical ICU. Patients were excluded if they lacked a Confusion Assessment Method for the ICU record from the day of ICU admission or if they had a positive Confusion Assessment Method for the ICU record at the time of ICU admission. The algorithm to predict delirium was developed using patient data from the first 2 years of the study period and validated using patient data from the last 6 months. Random forest (RF), Extreme Gradient Boosting (XGBoost), deep neural network (DNN), and logistic regression (LR) were used. The algorithms were externally validated using MIMIC-III data, and the algorithm with the largest area under the receiver operating characteristics (AUROC) curve in the external data set was named the PRIDE algorithm.ResultsA total of 37,543 cases were collected. After patient exclusion, 12,409 remained as our study population, of which 3816 (30.8%) patients experienced delirium incidents during the study period. Based on the exclusion criteria, out of the 96,016 ICU admission cases in the MIMIC-III data set, 2061 cases were included, and 272 (13.2%) delirium incidents occurred. The average AUROCs and 95% CIs for internal validation were 0.916 (95% CI 0.916-0.916) for RF, 0.919 (95% CI 0.919-0.919) for XGBoost, 0.881 (95% CI 0.878-0.884) for DNN, and 0.875 (95% CI 0.875-0.875) for LR. Regarding the external validation, the best AUROC were 0.721 (95% CI 0.72-0.721) for RF, 0.697 (95% CI 0.695-0.699) for XGBoost, 0.655 (95% CI 0.654-0.657) for DNN, and 0.631 (95% CI 0.631-0.631) for LR. The Brier score of the RF model is 0.168, indicating that it is well-calibrated.ConclusionsA machine learning approach based on electronic health record data can be used to predict delirium within 24 hours of ICU admission. RF, XGBoost, DNN, and LR models were used, and they effectively predicted delirium. However, with the potential to advise ICU physicians and prevent ICU delirium, prospective studies are required to verify the algorithm's performance.

Project description:BACKGROUND:Accurate prediction of delirium in the intensive care unit (ICU) may facilitate efficient use of early preventive strategies and stratification of ICU patients by delirium risk in clinical research, but the optimal delirium prediction model to use is unclear. We compared the predictive performance and user convenience of the prediction model for delirium (PRE-DELIRIC) and early prediction model for delirium (E-PRE-DELIRIC) in ICU patients and determined the value of a two-stage calculation. METHODS:This 7-country, 11-hospital, prospective cohort study evaluated consecutive adults admitted to the ICU who could be reliably assessed for delirium using the Confusion Assessment Method-ICU or the Intensive Care Delirium Screening Checklist. The predictive performance of the models was measured using the area under the receiver operating characteristic curve. Calibration was assessed graphically. A physician questionnaire evaluated user convenience. For the two-stage calculation we used E-PRE-DELIRIC immediately after ICU admission and updated the prediction using PRE-DELIRIC after 24 h. RESULTS:In total 2178 patients were included. The area under the receiver operating characteristic curve was significantly greater for PRE-DELIRIC (0.74 (95% confidence interval 0.71-0.76)) compared to E-PRE-DELIRIC (0.68 (95% confidence interval 0.66-0.71)) (z score of -?2.73 (p?<?0.01)). Both models were well-calibrated. The sensitivity improved when using the two-stage calculation in low-risk patients. Compared to PRE-DELIRIC, ICU physicians (n?=?68) rated the E-PRE-DELIRIC model more feasible. CONCLUSIONS:While both ICU delirium prediction models have moderate-to-good performance, the PRE-DELIRIC model predicts delirium better. However, ICU physicians rated the user convenience of E-PRE-DELIRIC superior to PRE-DELIRIC. In low-risk patients the delirium prediction further improves after an update with the PRE-DELIRIC model after 24 h. TRIAL REGISTRATION:ClinicalTrials.gov, NCT02518646 . Registered on 21 July 2015.

Dataset Information

Incidence and predictors of delirium on the intensive care unit in patients with acute kidney injury, insight from a retrospective registry.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets