Survivorship After Neurocritical Care: A Scoping Review of Outcomes Beyond Physical Status.

Following intensive care unit hospitalization, survivors of acute neurological injury often experience debilitating short-term and long-term impairments. Although the physical/motor impairments experienced by survivors of acute neurological injury have been described extensively, fewer studies have examined cognitive, mental health, health-related quality of life (HRQoL), and employment outcomes. This scoping review describes the publication landscape beyond physical and/or motor sequelae in neurocritical care survivors. Databases were searched for terms related to critical illness, intensive care, and outcomes from January 1970 to March 2022. English-language studies of critically ill adults with a primary neurological diagnosis were included if they reported on at least one outcome of interest: cognition, mental health, HRQoL or employment. Data extraction was performed in duplicate for prespecified variables related to study outcomes. Of 16,036 abstracts screened, 74 citations were identified for inclusion. The studies encompassed seven worldwide regions and eight neurocritical diagnosis categories. Publications reporting outcomes of interest increased from 3 before the year 2000 to 71 after. Follow-up time points included ≤ 1 (n = 15 [20%] citations), 3 (n = 28 [38%]), 6 (n = 28 [38%]), and 12 (n = 21 [28%]) months and 1 to 5 (n = 19 [26%]) and > 5 years (n = 8 [11%]), with 28 (38%) citations evaluating outcomes at multiple time points. Sixty-six assessment tools were used to evaluate the four outcomes of interest: 22 evaluating HRQoL (56 [76%] citations), 21 evaluating cognition (20 [27%] citations), 21 evaluating mental health (18 [24%] citations), and 2 evaluating employment (9 [12%] citations). This scoping review aimed to better understand the literature landscape regarding nonphysical outcomes in survivors of neurocritical care. Although a rising number of publications highlight growing awareness, future efforts are needed to improve study consistency and comparability and characterize outcomes in a disease-specific manner, including outlining of a minimum core outcomes set and associated assessment tools.

Effects of correction rate for severe hyponatremia in the intensive care unit on patient outcomes.

PURPOSE: Limited evidence exists regarding outcomes associated with different correction rates of severe hyponatremia. MATERIALS AND METHODS: This retrospective cohort analysis employed a multi-center ICU database to identify patients with sodium ≤120 mEq/L during ICU admission. We determined correction rates over the first 24 h and categorized them as rapid (> 8 mEq/L/day) or slow (≤ 8 mEq/L/day). The primary outcome was in-hospital mortality. Secondary outcomes included hospital-free days, ICU-free days, and neurological complications. We used inverse probability weighting for confounder adjustment. RESULTS: Our cohort included 1024 patients; 451 rapid and 573 slow correctors. Rapid correction was associated with lower in-hospital mortality (absolute difference: -4.37%; 95% CI, -8.47 to -0.26%), longer hospital-free days (1.80 days; 95% CI, 0.82 to 2.79 days), and longer ICU-free days (1.16 days; 95% CI, 0.15 to 2.17 days). There was no significant difference in neurological complications (2.31%; 95% CI, -0.77 to 5.40%). CONCLUSION: Rapid correction (>8 mEq/L/day) of severe hyponatremia within the first 24 h was associated with lower in-hospital mortality and longer ICU and hospital-free days without an increase in neurological complication. Despite major limitations, including the inability to identify the chronicity of hyponatremia, the results have important implications and warrant prospective studies.

Assessing Barriers to Implementation of Machine Learning and Artificial Intelligence-Based Tools in Critical Care: Web-Based Survey Study.

BACKGROUND: Although there is considerable interest in machine learning (ML) and artificial intelligence (AI) in critical care, the implementation of effective algorithms into practice has been limited. OBJECTIVE: We sought to understand physician perspectives of a novel intubation prediction tool. Further, we sought to understand health care provider and nonprovider perspectives on the use of ML in health care. We aim to use the data gathered to elucidate implementation barriers and determinants of this intubation prediction tool, as well as ML/AI-based algorithms in critical care and health care in general. METHODS: We developed 2 anonymous surveys in Qualtrics, 1 single-center survey distributed to 99 critical care physicians via email, and 1 social media survey distributed via Facebook and Twitter with branching logic to tailor questions for providers and nonproviders. The surveys included a mixture of categorical, Likert scale, and free-text items. Likert scale means with SD were reported from 1 to 5. We used student t tests to examine the differences between groups. In addition, Likert scale responses were converted into 3 categories, and percentage values were reported in order to demonstrate the distribution of responses. Qualitative free-text responses were reviewed by a member of the study team to determine validity, and content analysis was performed to determine common themes in responses. RESULTS: Out of 99 critical care physicians, 47 (48%) completed the single-center survey. Perceived knowledge of ML was low with a mean Likert score of 2.4 out of 5 (SD 0.96), with 7.5% of respondents rating their knowledge as a 4 or 5. The willingness to use the ML-based algorithm was 3.32 out of 5 (SD 0.95), with 75% of respondents answering 3 out of 5. The social media survey had 770 total responses with 605 (79%) providers and 165 (21%) nonproviders. We found no difference in providers' perceived knowledge based on level of experience in either survey. We found that nonproviders had significantly less perceived knowledge of ML (mean 3.04 out of 5, SD 1.53 vs mean 3.43, SD 0.941; P<.001) and comfort with ML (mean 3.28 out of 5, SD 1.02 vs mean 3.53, SD 0.935; P=.004) than providers. Free-text responses revealed multiple shared concerns, including accuracy/reliability, data bias, patient safety, and privacy/security risks. CONCLUSIONS: These data suggest that providers and nonproviders have positive perceptions of ML-based tools, and that a tool to predict the need for intubation would be of interest to critical care providers. There were many shared concerns about ML/AI in health care elucidated by the surveys. These results provide a baseline evaluation of implementation barriers and determinants of ML/AI-based tools that will be important in their optimal implementation and adoption in the critical care setting and health care in general.

Association Between ICU-Acquired Hypernatremia and In-Hospital Mortality: Data From the Medical Information Mart for Intensive Care III and the Electronic ICU Collaborative Research Database.

OBJECTIVES: Describe the relationship between ICU-acquired hypernatremia and in-hospital mortality and investigate the optimal hypernatremia correction rate. DESIGN SETTING PARTICIPANTS AND MEASUREMENTS: Observational study including two individual ICU cohorts. We used the Medical Information Mart for Intensive Care III v. 1.4 database consists of all ICU patients admitted to the Beth Israel Deaconess Medical Center in Boston from 2001 to 2012 (n = 46,476). The electronic ICU v. 2.0 database consists of all ICU patients admitted to 208 distinct hospitals across the United States from 2014 to 2015 (n = 200,859). We included all adult patients admitted to an ICU with two consecutive sodium samples within normal range (135-145 mmol/L) and without two consecutive hyponatremic samples (< 135 mmol/L) during the ICU stay. RESULTS: Of 23,445 patients identified in Medical Information Mart for Intensive Care III, 9% (n = 2,172) developed hypernatremia during their ICU stay. In electronic ICU, 88,160 patients were identified and 7% (n = 5,790) developed hypernatremia. In both cohorts, patients with hypernatremia had a higher mortality (Medical Information Mart for Intensive Care III: 20% vs 42%; p < 0.01 and electronic ICU: 6% vs 22%; p < 0.01), with hypernatremia increasing the risk of in-hospital mortality (Medical Information Mart for Intensive Care III: odds ratio, 1.15; 95% CI, 1.13-1.17 and electronic ICU: odds ratio, 1.11; 95% CI, 1.10-1.12) and over time using a Cox regression. Rapid sodium correction rate (> 0.5 mmol/L/hr) was associated with an increased in-hospital mortality in both cohorts (Medical Information Mart for Intensive Care III: odds ratio, 1.08; 95% CI, 1.03-1.13 and electronic ICU: odds ratio, 1.10; 95% CI, 1.06-1.13). In the electronic ICU cohort, rapid correction rates were associated with a significant difference in in-hospital mortality, but there was no statistically significant association in the Medical Information Mart for Intensive Care III cohort. CONCLUSIONS: ICU-acquired hypernatremia is associated with increased in-hospital mortality. Furthermore, a rapid sodium correction rates may be harmful. This suggests it is important to both prevent ICU-acquired hypernatremia and to avoid rapid correction rates if a patient becomes hypernatremic.

Machine Learning for Pulmonary and Critical Care Medicine: A Narrative Review.

Machine learning (ML) is a discipline of computer science in which statistical methods are applied to data in order to classify, predict, or optimize, based on previously observed data. Pulmonary and critical care medicine have seen a surge in the application of this methodology, potentially delivering improvements in our ability to diagnose, treat, and better understand a multitude of disease states. Here we review the literature and provide a detailed overview of the recent advances in ML as applied to these areas of medicine. In addition, we discuss both the significant benefits of this work as well as the challenges in the implementation and acceptance of this non-traditional methodology for clinical purposes.