An epidemic that advances silently

In a normal, healthy liver the amount of fat is negligible. Yet in many adults, and even children, fat exceeds 5 percent and sometimes 10 percent of the organ's total weight. That unnatural presence causes inflammation, cell damage and the formation of scar tissue known as fibrosis. As Wired reports, fatty liver disease now affects approximately 30 percent of adults worldwide, and the change is under way in the livers of more than a billion people.

The real difficulty is how quietly it progresses. Accumulating fat can ultimately lead to liver failure, and it has been linked to increased risk of cardiovascular disease and various cancers. But the condition typically develops without noticeable symptoms, so it is rarely caught at an early and treatable stage. Even in cases of cirrhosis or advanced scarring, three-quarters of people are only diagnosed once their condition has become life-threatening.

What changes if it is caught early

What makes this picture frustrating is that early detection genuinely works. In the initial stages much of the damage is highly reversible. Lifestyle changes such as reducing alcohol intake, losing weight through dietary improvements and exercise, and even drinking more coffee have all been shown to reverse scarring and inflammation. For people with moderate to advanced scarring, the GLP-1 medication semaglutide and a drug called resmetirom have been shown to be highly effective therapeutics.

Jeffrey Lazarus, a professor at the CUNY Graduate School of Public Health and Health Policy, points to the liver's versatility: the organ can regenerate, fibrosis can be reversed, and a person can be completely healthy again. The problem, in his account, is that the field has traditionally focused on late-stage care and on how long a patient can be kept alive, rather than on finding them early and preventing progression.

The tools exist and go unused

What frustrates specialists most is that simple, noninvasive ways of assessing liver health already exist, yet are rarely used even in high-risk groups.

  • The Fib-4 index rates the risk of advanced fibrosis on a scale of 0 to 6, based on a person's age, the levels of two liver enzymes and their blood-clotting ability. The liver blood test it needs is often already carried out as part of an annual checkup in the US.
  • The enhanced liver fibrosis test is a more accurate second-line blood test measuring two proteins involved in creating scar tissue and an enzyme that inhibits the clearance of scars.
  • Using both tests in patients with worrying amounts of liver fat has been shown to improve the diagnosis of advanced fibrosis four-fold.

Even so, for physicians facing a growing workload and administrative burden, simply adding more testing to the workflow is not seen as sustainable. Jonathan Dranoff, a professor of medicine at Yale University, puts it plainly: it has to be something that can run in the background, or that is easy to trigger with a single button.

Where AI fits

That is why Dranoff and Lazarus cast AI not as inventing a new test but as making the existing one visible. A layer that takes data from routine blood tests and automates the calculation of Fib-4 scores would let a primary care physician see immediately which patients to refer to a liver specialist. In Lazarus's words, AI can retrospectively go through massive numbers of hospital visits and lab reports, and that can be used to prioritise who is most at risk.

Imaging is the second route. In 2025, scientists at Osaka Metropolitan University in Japan published a study using an AI model capable of ingesting and analysing routine x-ray images. The logic is the same: extract signal from data already collected, without generating an extra procedure for the patient.

In short, this is not an argument about AI replacing the physician. Health systems hold millions of rows of data that currently go unread. For a disease that is reversible early and lethal late, making unread data readable is itself a treatment decision.