Dataset Information

Automated tracking of level of consciousness and delirium in critical illness using deep learning.

ABSTRACT: Over- and under-sedation are common in the ICU, and contribute to poor ICU outcomes including delirium. Behavioral assessments, such as Richmond Agitation-Sedation Scale (RASS) for monitoring levels of sedation and Confusion Assessment Method for the ICU (CAM-ICU) for detecting signs of delirium, are often used. As an alternative, brain monitoring with electroencephalography (EEG) has been proposed in the operating room, but is challenging to implement in ICU due to the differences between critical illness and elective surgery, as well as the duration of sedation. Here we present a deep learning model based on a combination of convolutional and recurrent neural networks that automatically tracks both the level of consciousness and delirium using frontal EEG signals in the ICU. For level of consciousness, the system achieves a median accuracy of 70% when allowing prediction to be within one RASS level difference across all patients, which is comparable or higher than the median technician-nurse agreement at 59%. For delirium, the system achieves an AUC of 0.80 with 69% sensitivity and 83% specificity at the optimal operating point. The results show it is feasible to continuously track level of consciousness and delirium in the ICU.

SUBMITTER: Sun H

PROVIDER: S-EPMC6733797 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated tracking of level of consciousness and delirium in critical illness using deep learning.

Sun Haoqi H Kimchi Eyal E Akeju Oluwaseun O Nagaraj Sunil B SB McClain Lauren M LM Zhou David W DW Boyle Emily E Zheng Wei-Long WL Ge Wendong W Westover M Brandon MB

NPJ digital medicine 20190909

Over- and under-sedation are common in the ICU, and contribute to poor ICU outcomes including delirium. Behavioral assessments, such as Richmond Agitation-Sedation Scale (RASS) for monitoring levels of sedation and Confusion Assessment Method for the ICU (CAM-ICU) for detecting signs of delirium, are often used. As an alternative, brain monitoring with electroencephalography (EEG) has been proposed in the operating room, but is challenging to implement in ICU due to the differences between criti ...[more]

PMID: 31508499

Similar Datasets

Project description:BackgroundTo understand delirium heterogeneity, prior work relied on psychomotor symptoms or risk factors to identify subtypes. Data-driven approaches have used machine learning to identify biologically plausible, treatment-responsive subtypes of other acute illnesses but have not been used to examine delirium.MethodsWe conducted a secondary analysis of a large, multicenter prospective cohort study involving adults in medical or surgical ICUs with respiratory failure or shock who experienced delirium per the Confusion Assessment Method for the ICU. We used data collected before delirium diagnosis in an unsupervised latent class model to identify delirium subtypes and then compared demographics, clinical characteristics, and outcomes between subtypes in the final model.FindingsThe 731 patients who developed delirium during critical illness had a median age of 63 [IQR, 54-72] years, a median Sequential Organ Failure Assessment score of 8.0 [6.0-11.0] and 613 [83.4%] were mechanically ventilated at delirium identification. A four-class model best fit the data with 50% of patients in subtype (ST) 1, 18% in subtype 2, 17% in subtype 3, and 14% in subtype 4. Subtype 2-which had more shock and kidney impairment-had the highest mortality (33% [ST2] vs. 17% [ST1], 25% [ST3], and 17% [ST4], p = 0.003). Subtype 4-which received more benzodiazepines and opioids-had the longest duration of delirium (6 days [ST4] vs. 3 [ST1], 4 [ST2], and 3 days [ST3], p < 0.001) and coma (4 days [ST4] vs. 2 [ST1], 1 [ST2], and 2 days [ST3], p < 0.001). Each of the four data-derived delirium subtypes was observed within previously identified psychomotor and risk factor-based delirium subtypes. Clinically significant cognitive impairment affected all subtypes at follow-up, but its severity did not differ by subtype (3-month, p = 0.26; 12-month, p = 0.80).InterpretationThe four data-derived delirium subtypes identified in this study should now be validated in independent cohorts, examined for differential treatment effects in trials, and inform mechanistic work evaluating treatment targets.FundingNational Institutes of Health (T32HL007820, R01AG027472).

Project description:BackgroundThere are conflicting data on the effects of antipsychotic medications on delirium in patients in the intensive care unit (ICU).MethodsIn a randomized, double-blind, placebo-controlled trial, we assigned patients with acute respiratory failure or shock and hypoactive or hyperactive delirium to receive intravenous boluses of haloperidol (maximum dose, 20 mg daily), ziprasidone (maximum dose, 40 mg daily), or placebo. The volume and dose of a trial drug or placebo was halved or doubled at 12-hour intervals on the basis of the presence or absence of delirium, as detected with the use of the Confusion Assessment Method for the ICU, and of side effects of the intervention. The primary end point was the number of days alive without delirium or coma during the 14-day intervention period. Secondary end points included 30-day and 90-day survival, time to freedom from mechanical ventilation, and time to ICU and hospital discharge. Safety end points included extrapyramidal symptoms and excessive sedation.ResultsWritten informed consent was obtained from 1183 patients or their authorized representatives. Delirium developed in 566 patients (48%), of whom 89% had hypoactive delirium and 11% had hyperactive delirium. Of the 566 patients, 184 were randomly assigned to receive placebo, 192 to receive haloperidol, and 190 to receive ziprasidone. The median duration of exposure to a trial drug or placebo was 4 days (interquartile range, 3 to 7). The median number of days alive without delirium or coma was 8.5 (95% confidence interval [CI], 5.6 to 9.9) in the placebo group, 7.9 (95% CI, 4.4 to 9.6) in the haloperidol group, and 8.7 (95% CI, 5.9 to 10.0) in the ziprasidone group (P=0.26 for overall effect across trial groups). The use of haloperidol or ziprasidone, as compared with placebo, had no significant effect on the primary end point (odds ratios, 0.88 [95% CI, 0.64 to 1.21] and 1.04 [95% CI, 0.73 to 1.48], respectively). There were no significant between-group differences with respect to the secondary end points or the frequency of extrapyramidal symptoms.ConclusionsThe use of haloperidol or ziprasidone, as compared with placebo, in patients with acute respiratory failure or shock and hypoactive or hyperactive delirium in the ICU did not significantly alter the duration of delirium. (Funded by the National Institutes of Health and the VA Geriatric Research Education and Clinical Center; MIND-USA ClinicalTrials.gov number, NCT01211522 .).

Dataset Information

Automated tracking of level of consciousness and delirium in critical illness using deep learning.

Publications

Automated tracking of level of consciousness and delirium in critical illness using deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets