Citations

Critically ill patients presenting with acute on chronic liver failure (ACLF) represent a particularly vulnerable population due to various considerations surrounding the syndrome definition, lack of robust prospective evaluation of outcomes, and allocation of resources such as organs for transplantation. Ninety-day mortality related to ACLF is high and patients who do leave the hospital are frequently readmitted. Artificial intelligence (AI), which encompasses various classical and modern machine learning techniques, natural language processing, and other methods of predictive, prognostic, probabilistic, and simulation modeling, has emerged as an effective tool in various areas of healthcare. These methods are now being leveraged to potentially minimize physician and provider cognitive load and impact both short-term and long-term patient outcomes. However, the enthusiasm is tempered by ethical considerations and a current lack of proven benefits. In addition to prognostic applications, AI models can likely help improve the understanding of various mechanisms of morbidity and mortality in ACLF. Their overall impact on patient-centered outcomes and countless other aspects of patient care remains unclear. In this review, we discuss various AI approaches being utilized in healthcare and discuss the recent and expected future impact of AI on patients with ACLF through prognostic modeling and AI-based approaches.

Patients with cirrhosis frequently require admission to the intensive care unit as complications arise in the course of their disease. These admissions are associated with high short- and long-term morbidity and mortality. Thus, understanding and characterizing complications and unique needs of patients with cirrhosis and acute-on-chronic liver failure helps providers identify appropriate level of care and evidence-based treatments. While there is no widely accepted critical care admission criteria for patients with cirrhosis, the presence of organ failure and primary or nosocomial infections are associated with particularly high in-hospital mortality. Optimal management of patients with cirrhosis in the critical care setting requires a system-based approach that acknowledges deviations from canonical pathophysiology. In this review, we discuss appropriate considerations and evidence-based practices for the general care of patients with cirrhosis and critical illness.

OBJECTIVES: To report the epidemiology, treatments, and outcomes of adult patients admitted to the ICU after cytokine release syndrome or immune effector cell-associated neurotoxicity syndrome. DESIGN: Retrospective cohort study SETTING: Nine centers across the U.S. part of the chimeric antigen receptor-ICU initiative. PATIENTS: Adult patients treated with chimeric antigen receptor T-cell therapy who required ICU admission between November 2017 and May 2019. INTERVENTIONS: Demographics, toxicities, specific interventions, and outcomes were collected. RESULTS: One-hundred five patients treated with axicabtagene ciloleucel required ICU admission for cytokine release syndrome or immune effector cell-associated neurotoxicity syndrome during the study period. At the time of ICU admission, the majority of patients had grade 3–4 toxicities (66.7%); 15.2% had grade 3–4 cytokine release syndrome and 64% grade 3–4 immune effector cell-associated neurotoxicity syndrome. During ICU stay, cytokine release syndrome was observed in 77.1% patients and immune effector cell-associated neurotoxicity syndrome in 84.8% of patients; 61.9% patients experienced both toxicities. Seventy-nine percent of patients developed greater than or equal to grade 3 toxicities during ICU stay, however, need for vasopressors (18.1%), mechanical ventilation (10.5%), and dialysis (2.9%) was uncommon. Immune Effector Cell-Associated Encephalopathy score less than 3 (69.7%), seizures (20.2%), status epilepticus (5.7%), motor deficits (12.4%), and cerebral edema (7.9%) were more prevalent. ICU mortality was 8.6%, with only three deaths related to cytokine release syndrome or immune effector cell-associated neurotoxicity syndrome. Median overall survival time was 10.4 months (95% CI, 6.64–not available mo). Toxicity grade or organ support had no impact on overall survival; higher cumulative corticosteroid doses were associated to decreased overall and progression-free survival. CONCLUSIONS: This is the first study to describe a multicenter cohort of patients requiring ICU admission with cytokine release syndrome or immune effector cell-associated neurotoxicity syndrome after chimeric antigen receptor T-cell therapy. Despite severe toxicities, organ support and in-hospital mortality were low in this patient population.

Background: Obesity paradox is a phenomenon in which obesity increases the risk of obesity-related chronic diseases but paradoxically is associated with improved survival among obese patients with these diagnoses. Objectives: The aim of this study was to explore the obesity paradox among critically ill patients with cirrhosis admitted to the Intensive Care Unit. Methods: A retrospective cohort of 1,143 consecutive patients with cirrhosis admitted to the ICU between January of 2006 and December of 2015 was analyzed. Primary outcome of interest was in-hospital mortality with secondary end points including ICU and short-term mortality at 30 days post ICU admission. Results: Logistic regression with generalized additive models was used, controlling for clinically relevant and statistically significant factors to determine the adjusted relationship between body mass index (BMI) and ICU, post-ICU in-hospital, and 30 day mortality following ICU discharge. ICU and hospital length of stay was similar across all BMI classes. Adjusted ICU mortality was also similar when stratified by BMI. However, a significant reduction in post-ICU hospital mortality was observed in class I and II obese patients with cirrhosis (BMI 30-39.9 kg/m 2 ) compared to normal BMI (OR = 0.41; 95% CI, 0.20 to 0.83; P = 0.014). Similarly, overweight (BMI 25-29.9 kg/m 2 ) and class I and II obese patients with cirrhosis had significantly lower 30-day mortality following ICU discharge (OR = 0.52, 95% CI 0.31 to 0.87; P = 0.014; OR = 0.50, 95% CI 0.29 to 0.86; P = 0.012, respectively) compared to those with normal BMI. Conclusion: The signal of obesity paradox is suggested among critically ill patients with cirrhosis.