Post-intensive care syndrome and health-related quality of life in long-term survivors of cardiac arrest: a prospective cohort study.

Patients discharged from intensive care are at risk for post-intensive care syndrome (PICS), which consists of physical, psychological, and/or neurological impairments. This study aimed to analyze PICS at 24 months follow-up, to identify potential risk factors for PICS, and to assess health-related quality of life in a long-term cohort of adult cardiac arrest survivors. This prospective cohort study included adult cardiac arrest survivors admitted to the intensive care unit of a Swiss tertiary academic medical center. The primary endpoint was the prevalence of PICS at 24 months follow-up, defined as impairments in physical (measured through the European Quality of Life 5-Dimensions-3-Levels instrument [EQ-5D-3L]), neurological (defined as Cerebral Performance Category Score > 2 or Modified Rankin Score > 3), and psychological (based on the Hospital Anxiety and Depression Scale and the Impact of Event Scale-Revised) domains. Among 107 cardiac arrest survivors that completed the 2-year follow-up, 46 patients (43.0%) had symptoms of PICS, with 41 patients (38.7%) experiencing symptoms in the physical domain, 16 patients (15.4%) in the psychological domain, and 3 patients (2.8%) in the neurological domain. Key predictors for PICS in multivariate analyses were female sex (adjusted odds ratio [aOR] 3.17, 95% CI 1.08 to 9.3), duration of no-flow interval during cardiac arrest (minutes) (aOR 1.17, 95% CI 1.02 to 1.33), post-discharge job-loss (aOR 31.25, 95% CI 3.63 to 268.83), need for ongoing psychological support (aOR 3.64, 95% CI 1.29 to 10.29) or psychopharmacologic treatment (aOR 9.49, 95% CI 1.9 to 47.3), and EQ-visual analogue scale (points) (aOR 0.88, 95% CI 0.84 to 0.93). More than one-third of cardiac arrest survivors experience symptoms of PICS 2 years after resuscitation, with the highest impairment observed in the physical and psychological domains. However, long-term survivors of cardiac arrest report intact health-related quality of life when compared to the general population. Future research should focus on appropriate prevention, screening, and treatment strategies for PICS in cardiac arrest patients.

Prediction of outcomes after cardiac arrest by a generative artificial intelligence model.

Aims: To investigate the prognostic accuracy of a non-medical generative artificial intelligence model (Chat Generative Pre-Trained Transformer 4 - ChatGPT-4) as a novel aspect in predicting death and poor neurological outcome at hospital discharge based on real-life data from cardiac arrest patients. Methods: This prospective cohort study investigates the prognostic performance of ChatGPT-4 to predict outcomes at hospital discharge of adult cardiac arrest patients admitted to intensive care at a large Swiss tertiary academic medical center (COMMUNICATE/PROPHETIC cohort study). We prompted ChatGPT-4 with sixteen prognostic parameters derived from established post-cardiac arrest scores for each patient. We compared the prognostic performance of ChatGPT-4 regarding the area under the curve (AUC), sensitivity, specificity, positive and negative predictive values, and likelihood ratios of three cardiac arrest scores (Out-of-Hospital Cardiac Arrest [OHCA], Cardiac Arrest Hospital Prognosis [CAHP], and PROgnostication using LOGistic regression model for Unselected adult cardiac arrest patients in the Early stages [PROLOGUE score]) for in-hospital mortality and poor neurological outcome. Results: Mortality at hospital discharge was 43% (n = 309/713), 54% of patients (n = 387/713) had a poor neurological outcome. ChatGPT-4 showed good discrimination regarding in-hospital mortality with an AUC of 0.85, similar to the OHCA, CAHP, and PROLOGUE (AUCs of 0.82, 0.83, and 0.84, respectively) scores. For poor neurological outcome, ChatGPT-4 showed a similar prediction to the post-cardiac arrest scores (AUC 0.83). Conclusions: ChatGPT-4 showed a similar performance in predicting mortality and poor neurological outcome compared to validated post-cardiac arrest scores. However, more research is needed regarding illogical answers for potential incorporation of an LLM in the multimodal outcome prognostication after cardiac arrest.