Smart feeding: the role of artificial intelligence and integrated nutrition platforms in the ICU

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not reported — no quantitative synthesis performed

• Primary Outcome: Descriptive synthesis of ML algorithms and integrated platforms for ICU nutritional management, including prediction of enteral feeding intolerance and refeeding hypophosphatemia, nasogastric tube positioning verification, and optimisation of energy delivery

• Nnt Or Sensitivity: Not reported — individual study performance metrics for ML models (e.g., AUROC, sensitivity, specificity) are not synthesised or tabulated in the available abstract

• Confidence Interval: Not reported

Clinical Application

Implementation feasibility is currently low-to-moderate in most ICUs globally. Barriers include heterogeneous EHR systems, absence of validated and commercially available integrated nutrition platforms, need for local algorithm validation, clinical workflow integration challenges, and requirement for data science expertise. The review acknowledges that algorithmic predictions still require validation before routine clinical use. In the Australian context, ICU nutrition practice is guided by ANZICS and ESPEN recommendations, with the Australian and New Zealand Intensive Care Society (ANZICS) providing relevant clinical practice guidelines. Enteral nutrition products are TGA-regulated, and dietitian-led nutrition support teams are standard in major Australian ICUs. The PBS does not currently subsidise AI-based nutrition platforms. Australian ICUs participating in the ANZICS Adult Patient Database may have data infrastructure amenable to ML research, but prospective validation studies in Australian ICU populations are absent. RACGP guidelines are less directly relevant given the ICU-specific focus. Clinicians should await prospective, externally validated trials before adopting AI-driven nutrition platforms in Australian ICU practice. Adult ICU patients requiring enteral nutrition, particularly those at risk of feeding intolerance, refeeding syndrome, or requiring nasogastric tube placement verification. Applicability is currently limited to institutions with advanced electronic health record infrastructure capable of supporting ML integration.

Abstract

PURPOSE OF REVIEW: Tremendous improvement in the use of artificial intelligence has opened new opportunities to analyze the data obtained from electronic health records and imaging. New technologies have tried to overcome obstacles to implement guidelines and recommendations. This review aims to describe the recent progress in the use of machine learning and new technologies in the field of nutrition of the critically ill. RECENT FINDINGS: Increase in data availability, ability to extract these data and analyze them using machine learning has allowed data scientists together with ICU specialists to improve nutritional screening and assessment and to predict occurrence of obstacles like enteral feeding intolerance or refeeding hypophosphatemia. In addition, new technologies can ensure nasogastric tube positioning and enteral feeding efficacy. Integrated platforms can integrate nutritional needs with most adequate prescriptions and modulate the nutritional administration according to the patient's tolerance and requirements. Analysis of continuous recording of imaging obtained from ultrasound can also predict gastric intolerance. SUMMARY: Using machine learning, numerous algorithms and nomograms have been suggested to predict enteral feeding intolerance but validation of these predictions is still required. New technologies integrating energy requirements and delivery of the optimal enteral feeding are very promising.

References

1. 1.Singer, P., & Raphaeli, O. (2026). Smart feeding: the role of artificial intelligence and integrated nutrition platforms in the ICU. Current Opinion in Critical Care. https://doi.org/10.1097/MCC.0000000000001397