Doctors may soon be able to diagnose diseases before you ever feel sick
As some sectors of the AI industry seem dead set on replacing the hard, creative work that actual people earn jobs for, others are putting the technology to a more socially enriching use: using AI to predict diseases before symptoms even begin.
The approach, presented as an editorial in the journal Intelligent medicine by a team of researchers from China, is not just a technological shift, but a fundamental rethinking of how doctors diagnose patients. Diagnosing a disease today can require multiple visits to different doctors and numerous tests, with a lot of time in between while a patient waits for results. The researchers will use artificial intelligence to monitor how networks of genes, proteins and chemical signals change over time, looking for instabilities in the body that signal that something is going wrong. The key word here is about.
It’s an approach adapted from something called the dynamic network biomarker theory. It suggests that as the body approaches disease, certain molecular networks begin to fluctuate and become more connected than normal. In studies of influenza, for example, these patterns begin to emerge days before symptoms appear. In cancer research, they identified similar signals that appear around the point where cells begin to turn malignant. The prediction accuracy of these patterns is somewhere over 80 percent.
This AI could help predict disease before symptoms appear
A disadvantage of modern diagnosis is that it relies on population averages to determine when symptoms may occur. Newer AI methods would shift the focus to the patterns specific to a single person. It’s mostly theoretical right now, but in practice it would mean we could use AI to tailor health monitoring to each person.
These tools will be particularly useful for tracking the body’s small molecular networks as they change in response to, say, type I diabetes, where these AI models cannot predict blood sugar levels much more accurately than older predictive tools by creating digital simulations of an individual. The same idea can be applied to a number of health problems, including heart failure.
There are still plenty of hurdles to overcome before we reach the point where AI predicts a tumor long before symptoms appear. The system is heavily dependent on a constant stream of clean data. Without it, or even just with large gaps, the system can trigger all sorts of false alarms and detect correlations that don’t actually have a real causal relationship. And there’s also the vexing issue of AI hallucinations, known in the medical world as a black box, which is when an AI model spits out a prediction that even its own designers can’t explain.
None of this is to say that AI will replace doctors anytime soon, or even ever. At best, it will simply be an early warning system that flags risks before symptoms appear. It would still be up to a doctor specializing in this field to interpret the results and determine whether the AI was correct or making connections where none existed.
