Search

Adequate fluid resuscitation in adults with major burns is crucial to prevent or minimize burn shock, but needs to be balanced against the complications of over-resuscitation. A single-center, retrospective review of 95 ICU patients with severe burns from Jan 2014 to Aug 2021 was performed. Some 52 patients were managed with a liberal targeted fluid goal of 4 mL/kg/%TBSA, and 43 patients were managed after we incorporated a restricted fluid goal of 2 mL/kg/%TBSA into our standard resuscitation strategy. Of the 95 patients included in this analysis, 76 patients (80%) survived admission. The median age was 41 years, and the median TBSA was 36%. All patients received Ringer’s lactate as the primary fluid for resuscitation, and 40 of the 95 patients (42%) received colloids as a rescue infusion within 24 h of injury. Some 44 of the 95 patients (46.3%) had a concurrent inhalational injury. The median length of hospital stay was 37 days, and the median ICU length of stay was 18 days. A total of 17 of the 95 patients developed ARDS (17.9%), 51 of the 95 (53.7%) patients developed pneumonia, and 34 of the 95 patients (35.8%) developed AKI within the first 7 days of admission. The median fluid administered during the first day of hospitalization from 2019 onwards remained close to 4 mL/kg/%TBSA, despite transitioning to a 2 mL/kg/%TBSA formula for a 24 h fluid goal (unless there was an electrical burn, in which case the 4 cc/kg formula was utilized). Further exploratory analyses also suggested that under-resuscitation and administration of albumin may be associated with increased mortality, though this did not reach statistical significance. ARDS development was associated with increased age and TBSA as well as increased fluid intake within the first 24 h. A change in the targeted fluid goal from liberal (4 mL/kg/%TBSA) to a restricted (2 mL/kg/%TBSA) formula did not change the actual fluids administered over 24 h when guided by clinical criteria. Our review did suggest that under-resuscitation contributed to mortality, but that excessive fluid resuscitation likely contributed to ARDS risks for large TBSA patients. Our data suggest that strategies to optimize fluid administration are important to improve patient outcomes, but should focus on clinical parameters rather than calculated fluid goals.

Clinical deterioration (ICU transfer and cardiac arrest) occurs during approximately 5-10% of hospital admissions. Existing prediction models have a high false positive rate, leading to multiple false alarms and alarm fatigue. We used routine vital signs and laboratory values obtained from the electronic medical record (EMR) along with a machine learning algorithm called a neural network to develop a prediction model that would increase the predictive accuracy and decrease false alarm rates.Retrospective cohort study.The hematologic malignancy unit in an academic medical center in the United States.Adult patients admitted to the hematologic malignancy unit from 2009 to 2010.None.Vital signs and laboratory values were obtained from the electronic medical record system and then used as predictors (features). A neural network was used to build a model to predict clinical deterioration events (ICU transfer and cardiac arrest). The performance of the neural network model was compared to the VitalPac Early Warning Score (ViEWS). Five hundred sixty five consecutive total admissions were available with 43 admissions resulting in clinical deterioration. Using simulation, the neural network outperformed the ViEWS model with a positive predictive value of 82% compared to 24%, respectively.We developed and tested a neural network-based prediction model for clinical deterioration in patients hospitalized in the hematologic malignancy unit. Our neural network model outperformed an existing model, substantially increasing the positive predictive value, allowing the clinician to be confident in the alarm raised. This system can be readily implemented in a real-time fashion in existing EMR systems.