Malnutrition in hospitalized patients in the United States is a common but underdiagnosed condition, affecting 20% to 50% of hospitalized patients. It can result in poor wound healing, higher infection rates and higher mortality rates.
Doctors at Mount Sinai Health System in New York City found that the standardized tools for assessing a patient’s risk of developing malnutrition lacked accuracy and resulted in missed chances to intervene early, so several years ago they began working with their clinical data science team – including front-line registered dietitians – to find a better way.
The result was NutriScan, an AI-powered tool that identifies malnourished patients faster and more precisely.
Mount Sinai Health System says it is now 2½ to 3 times more likely to identify malnutrition. The positive results have led to higher quality ratings and increased reimbursements from insurance companies as well as Medicaid and Medicare.
“NutriScan helps us get our team of registered dietitians to the right patient, at the right time,” says Robbie Freeman, chief digital transformation officer at the Mount Sinai Health System, who oversees the hospital’s efforts to integrate artificial intelligence and digital products into patient care.
Hospitals across the country rely on three main screening tools to diagnose malnutrition: the Malnutrition Universal Screening Tool, the Nutritional Risk Screening 2002 and the Mini Nutritional Assessment, designed for patients 65 and older.
