AI shows promise in early detection of liver disease through electronic health records

A groundbreaking study conducted by the University of Washington has demonstrated the efficacy of an artificial intelligence algorithm in diagnosing early-stage metabolic-associated steatotic liver disease (MASLD) through electronic health records. The findings, which may significantly enhance early detection rates of this common yet underdiagnosed liver condition, have shed light on the potential of AI in transforming medical diagnostics.

MASLD, the most prevalent form of liver disease, arises when the liver fails to properly manage fat, often in conjunction with other health issues such as obesity, Type-2 diabetes, and elevated cholesterol levels. Early detection is crucial in preventing the disease from advancing to more severe stages. However, MASLD frequently goes unnoticed due to its asymptomatic nature in the early phases. This often results in diagnoses occurring only when it reaches advanced stages, which are much more challenging to treat.

In this study, the AI-driven algorithm analysed imaging results drawn from the electronic health records of patients across three sites within the University of Washington Medical System. The aim was to pinpoint individuals that fulfilled the criteria for MASLD, a task which has traditionally posed a challenge for medical professionals due to the lack of visible symptoms in the early stages of the disease.

Out of the 834 patients identified by the algorithm as meeting the MASLD criteria, only 137 had an official diagnosis documented in their medical records. This implies that a staggering 83% of cases were undiagnosed, highlighting a significant gap in the current diagnostic processes within the healthcare system.

Dr Ariana Stuart, a resident at the University of Washington Internal Medicine Residency Program and the lead author of the study, expressed concern over these findings. “A significant proportion of patients who meet criteria for MASLD go undiagnosed,” she stated. “This is concerning because delays in early diagnosis increase the likelihood of progression to advanced liver disease.”

Dr Stuart was careful to emphasise that the study’s results should not be viewed as a critique of primary care provider training or management. Instead, she posited that the research underscores how AI can enhance the traditional clinical environment by working in tandem with healthcare professionals to overcome existing diagnostic hurdles.

The implications of this study suggest a promising future where AI algorithms could serve as a powerful tool in the early detection of MASLD, potentially leading to timely interventions and better patient outcomes. With further development and integration into healthcare systems, such algorithms could significantly reduce the number of undiagnosed cases and curb the progression of the disease. As the body of research continues to grow, the role of AI in healthcare appears poised to expand, opening new possibilities for patient care and disease management.

Source: Noah Wire Services