Factors associated with delayed enteral nutrition in the intensive care unit: a propensity score-matched retrospective cohort study

Role of artificial intelligence in critical care nutrition support and research

Nutrition plays a key role in the comprehensive care of critically ill patients. Determining optimal nutrition strategy, however, remains a subject of intense debate. Artificial intelligence (AI) applications are becoming increasingly common in medicine, and specifically in critical care, driven by the data-rich environment of intensive care units. In this review, we will examine the evidence regarding the application of AI in critical care nutrition. As of now, the use of AI in critical care nutrition is relatively limited, with its primary emphasis on malnutrition screening and tolerance of enteral nutrition. Despite the current scarcity of evidence, the potential for AI for more personalized nutrition management for critically ill patients is substantial. This stems from the ability of AI to integrate multiple data streams reflecting patients' changing needs while addressing inherent heterogeneity. The application of AI in critical care nutrition holds promise for optimizing patient outcomes through tailored and adaptive nutrition interventions. A successful implementation of AI, however, necessitates a multidisciplinary approach, coupled with careful consideration of challenges related to data management, financial aspects, and patient privacy.

Impact of early enteral nutrition on ventilator associated pneumonia in intubated severe trauma patients: A propensity score-matched study

Background

Early enteral nutrition (EN) is recommended for critically ill patients. However, the impact of early EN on intubated severe trauma patients remains unclear.

Methods

Severely traumatized adult patients who received invasive mechanical ventilation (MV) for more than 48 h during intensive care unit (ICU) stay at our institution between 2017 and 2022 were retrospectively included. Early EN was defined as EN initiation ≤48 h from ICU admission and late EN >48 h. Propensity score matching (PSM) analysis was used to compare outcomes between the groups. The primary endpoint was the incidence of ventilator-associated pneumonia (VAP). Multivariable logistic regression analysis was performed to identify independent predictors of delayed EN.

Results

For final analysis, 337 intubated severe trauma patients were available, including 204 (60.5%) in the early EN group and 133 (39.5%) in the late EN group. After PSM, early EN patients had a lower incidence of VAP (12.9 vs. 25.8%, p = 0.026) and a shorter length of hospital stay (21 vs. 24 days, p = 0.015) compared to late EN patients. There was no demonstrable difference in mortality between the two groups. Abdominal trauma, massive blood transfusion, and serum albumin were identified as independent risk factors for delayed EN.

Conclusion

Early EN decreased the VAP rate and reduced the length of hospital stay in invasively ventilated patients with severe trauma. Abdominal injury, massive blood transfusion and low albumin were associated with delayed EN.

High prevalence, low identification and screening tools of hospital malnutrition in critically- ill patients in Malawi

BACKGROUND/OBJECTIVES

In Africa, approximately two-thirds of patients are at risk of malnutrition on admission and the nutritional status of patients deteriorates during hospitalization, with associated increased morbidity, mortality, and hospital-related cost. This cross-sectional study aimed at estimating rates of malnutrition in critical care units and determining the extent to which malnutrition diagnoses are documented in medical records by physicians, at two public tertiary hospitals in Malawi.

METHODS

A total of 315 adult (n = 112) and paediatric (n = 203) participants from Queen Elizabeth Central Hospital and Kamuzu Central Hospital, were included in the analysis. Nutrition status was measured by Subjective Global Assessment (SGA) and Mid-Upper Arm circumference (MUAC) and medical notes were reviewed, in both adults and paediatrics.

RESULTS

In adults, more than half were malnourished, with a higher proportion considered moderately-to-severely malnourished using SGA compared to MUAC (84.8%; 57.3%, respectively). Likewise, in paediatrics, a higher proportion was considered moderately-to-severely malnourished using SGA compared to MUAC (84.7%; 23.4%, respectively). Both adult and paediatric patients with cancer had the highest rates of malnutrition. Only 12.9% and 9.6% had documentation of malnutrition diagnosis in the medical record, for paediatrics and adult patients, respectively.

CONCLUSION

The high rates of hospital malnutrition in critically ill patients in Malawi call for comprehensive screening practices and methods; complemented by documentation of the malnutrition diagnosis and use of nutrition interventions by dietitians. This includes enteral, parenteral and supplemental nutrition as a prerequisite for patient recovery in hospitals.