A recent study revealed that critically ill patients who require ventilation often fail to get enough nutrition, especially during their first days in intensive care.
According to a research published in Nature Communications, artificial intelligence (AI) could assist doctors detect this problem earlier.
Researchers at the Icahn School of Medicine at Mount Sinai in New York City discovered that the cutting-edge AI tool can predict which ventilated patients are expected to be underfed during their first week in the ICU.
Co-senior author Dr. Ankit Sakhuja, an associate professor at Mount Sinai stated, “Too many patients on ventilators don’t get the nutrition they need during the critical first week,”
He further mentioned that patients’ needs change rapidly, leading to delays in additional nutrition.
Scientists developed an AI program called NutriSighT that assesses routine ICU data such as vital signs, lab results, medications, and feeding records to project nutrition risk.
The system updates its predictions every four hours, enabling care teams to track changes in a patient’s condition.
As per the data across the U.S. and Europe, scientists discovered that underfeeding was common.
Between 41% and 53% of patients were underfed by day three on a ventilator, and 25% to 35% remained underfed by day seven.
Moreover, the AI-powered model underscored associated factors of underfeeding risk that include sodium levels, blood pressure, and sedation.
The tool is not meant to replace doctors or dietitians but to serve as an early warning system. The team further plans to test whether real-time use enhances patient recovery and explore incorporation into electronic health records.
