Mount Sinai Wins Hearst Prize for AI-Based Nutrition Application

June 7, 2024
New York health system’s NutriScan AI facilitates faster identification and treatment of malnutrition in hospitalized patients

Mount Sinai Health System has won the 2024 Hearst Health Prize for a machine learning application called NutriScan AI that facilitates faster identification and treatment of malnutrition in hospitalized patients. 

The $100,000 award, from Hearst Health and the UCLA Center for SMART Health, was presented by Gregory Dorn, M.D., president of Hearst Health, during UCLA Health Data Day on June 4.

Malnutrition is a highly prevalent condition that often goes undiagnosed in hospitalized patients and can significantly impact their path to recovery. The condition is associated with increases in mortality, morbidity, risk of complications and length of hospital stay. While early identification and treatment with nutritional support can prevent or reverse malnutrition, standard screening tools lack accuracy, resulting in missed opportunities for intervention.

Mount Sinai Health System started a clinical data science team to develop a more reliable malnutrition screening tool. Working with an extensive historical cohort of data, the team used over 80 variables to build a model that significantly outperformed the traditional rule-based model used in standard screening tools. Integrating directly within the electronic health record, NutriScan AI offers a precise method to identify patients in whom a diagnosis is likely to be present. This enables registered dieticians to prioritize visits with these patients to confirm a diagnosis and initiate treatment.

Since 2019, Mount Sinai Health System has deployed NutriScan AI in six hospitals, resulting in improved registered dietician resource utilization, a sustained increase in the malnutrition diagnosis rate, and a consistent financial return on investment. Mount Sinai Health System is now approximately 2.5 to 3 times more likely to identify malnutrition, contributing to increased reimbursements for the hospital and higher quality ratings on observed-to-expected outcomes.

"Receiving the Hearst Health Prize not only acknowledges our efforts and provides resources to further this work, it creates a platform for us to share our learnings, which can hopefully speed advancements in other areas of care," said David L. Reich, M.D., president of The Mount Sinai Hospital and Mount Sinai Queens, in a statement. "The development of screening tools like NutriScan AI is just one example of how artificial intelligence is enabling providers to operate more efficiently but the possibilities are endless.”

The 2024 Hearst Health Prize competition attracted a diverse set of applications from across the U.S., which were evaluated by UCLA reviewers and an expert judging panel. The Mount Sinai Health System program received the highest combined score across six evaluation criteria, with particularly high rankings for demonstrated health impact and operational and financial sustainability.

The other finalist in the competition was the University of Texas MD Anderson Cancer Center, which was selected for its work developing data science pipelines for cancer research, specifically in the realm of lung cancer. The team has conducted studies that show promise in the ability of deep learning to advance cancer care and reshape clinical trials, including aiding in the identification of high-risk patients for lung cancer prevention, expediting lung cancer diagnosis, and facilitating treatment decision making for individualized therapy for lung cancer patients.

The Hearst Health network includes FDB (First Databank), Zynx Health, MCG, Homecare Homebase and MHK. Hearst also holds a minority interest in the precision medicine and oncology analytics company Aster Insights.

Sponsored Recommendations

Clinical Evaluation: An AI Assistant for Primary Care

The AAFP's clinical evaluation offers a detailed analysis of how an innovative AI solution can help relieve physicians' administrative burden and aid them in improving health ...

From Chaos to Clarity: How AI Is Making Sense of Clinical Documentation

From Chaos to Clarity dives deep into how AI Is making sense of disorganized patient data and turning it into evidence-based diagnosis suggestions that physicians can trust, leading...

Bridging the Health Plan/Provider Gap: Data-Driven Collaboration for a Value-Based Future

Download the findings report to understand the current perspective of provider and health plan leaders’ shift to value-based care—with a focus on the gaps holding them back and...

Exploring the future of healthcare with Advanced Practice Providers

Discover how Advanced Practice Providers are transforming healthcare: boosting efficiency, cutting wait times and enhancing patient care through strategic integration and digital...