AI Algorithm Detects Undiagnosed Early-Stage Liver Disease, Promising Improved Patient Care

AI Algorithm Detects Undiagnosed Liver Disease

Researchers have developed an artificial intelligence (AI) algorithm capable of accurately identifying early-stage metabolic-associated steatotic liver disease (MASLD) using electronic health records. The study, presented at The Liver Meeting 2024 hosted by the American Association for the Study of Liver Diseases, highlights the potential of AI to improve early diagnosis and patient care 1

1

Study Findings and Implications

The AI-driven algorithm analyzed imaging findings and other criteria in patient electronic medical records from three sites within the University of Washington Medical System. Out of 834 patients identified as meeting the criteria for MASLD, only 137 (17%) had an official MASLD-associated diagnosis in their records 2

2

Dr. Ariana Stuart, lead author of the study, emphasized the significance of these findings: "A significant proportion of patients who meet criteria for MASLD go undiagnosed, which can lead to delays in care and progression to advanced liver disease" 3

3

AI Algorithm Development and Accuracy

The machine learning algorithm was based on MASLD criteria from the American Association for the Study of Liver Diseases, including hepatic steatosis on imaging and at least one metabolic factor. After multiple iterations, the algorithm achieved an accuracy of approximately 88% 1

1

Importance of Early MASLD Detection

MASLD, affecting an estimated 4.5 million adults in the United States, occurs when fat isn't properly managed in the liver and is often associated with obesity, type 2 diabetes, and abnormal cholesterol levels. Early diagnosis is crucial as the condition can rapidly progress to more severe forms of liver disease 4

4

Related Stories

AI Model Detects Fatty Liver Disease in Chest X-Rays, Revolutionizing Early Diagnosis

EMA Approves AI Tool for MASH Clinical Trials: A Breakthrough in Liver Disease Research

AI-Powered Blood Test Detects Liver Cancer Across Diverse International Populations

AI Revolutionizes Heart Disease Detection: From ECGs to Hidden Conditions

Future Applications and Considerations

Researchers are now testing the algorithm on larger groups and over extended periods. They plan to implement a quality improvement program to increase awareness among clinicians and primary care providers, as well as train users on interpreting and acting upon findings of hepatic steatosis in patient records 1

1

Dr. Ashley Spann, an assistant professor at Vanderbilt University, emphasized the need for transparency in AI use, careful validation of data, and standardization across institutions. She stated, "What we ultimately need is an infrastructure that supports the simultaneous deployment and evaluation of these models" 1

1

Complementing Physician Workflow

The researchers stress that these findings should not be interpreted as a lack of primary care training or management. Instead, the study demonstrates how AI can complement physician workflow and address limitations in traditional clinical practice, potentially improving early diagnosis and patient outcomes in liver disease management 2

2