A Fitbit a day just might help keep your post-surgery woes at bay. Research today finds that wearable data can predict children’s risk of health problems following a removed appendix.

Scientists in Chicago conducted the study, which equipped over a hundred children with Fitbits after their appendectomy. Using a specially designed algorithm, the Fitbits accurately detected whether children would develop postoperative complications, often days before they were formally diagnosed. The findings suggest that wearables can be turned into a reliable early warning system for people leaving medical care, particularly children, the researchers say.

“This work has significant implications for enabling precise, real-time, remote monitoring of recovery in children following surgery,” study co-author Megan O’Brien, a research scientist at the Shirley Ryan AbilityLab, told Gizmodo.

Leaving aside Robert F. Kennedy Jr.’s strange dream of having every American use a wearable, scientists are genuinely excited about the potential for these devices. The biometric data a wearable can collect, such as our heart rate or sleeping patterns, can be key clues to our overall health. By looking for subtle disruptions of these markers, the hope is that we can proactively catch a person’s illness or flare-ups of an existing condition sooner than usual.

O’Brien notes that the risk of new health problems is relatively high in children who undergo surgery. One of the most common complications of an appendectomy, for instance, is infections at the surgery site. And compared to adults, kids might be less willing or able to communicate when they’re feeling sick again.

O’Brien and her colleagues at the Shirley Ryan AbilityLab teamed up with researchers at the Ann and Robert H. Lurie Children’s Hospital of Chicago and the University of Alabama at Birmingham for this new study.

103 children (ages 3 to 18) were given a Fitbit (either the Inspire HR or Inspire 2) to wear for 21 days after their appendix was removed. The researchers created a machine learning algorithm to analyze the typical health data collected by the wearables, including heart rate and activity. They trained the AI model to look beyond these simple metrics; instead, it used them to calculate a child’s typical biorhythms according to their internal body clock (a common example being our circadian rhythm). The researchers then used the model to retroactively predict whether the children ended up getting sick again.

The algorithm correctly identified 91% of the children who were diagnosed with postoperative complications (this is known as a sensitivity rate), up to three days before it happened. It was also 74% accurate at identifying children who didn’t need follow-up care (its specificity rate).

“Our findings suggest that wearable-derived biorhythms offer a promising, unobtrusive method for evaluating postoperative recovery,” the researchers wrote in their paper, published Wednesday in Science Advances.

While this study only looked at appendectomy patients, the researchers say this approach could be used to track children’s recovery from a broad range of surgeries and possibly even to detect non-surgical conditions marked by clear behavioral or physiological changes. They also argue that it can easily be combined with existing tools to truly predict people’s health problems before they happen.

“The algorithm can be integrated into a clinician-friendly dashboard that delivers daily summaries, on-demand reports, and real-time alerts to a child’s care team, providing data-driven treatment support and enabling more proactive follow-up with patients,” O’Brien said. “As such, these tools could support more efficient healthcare engagement for families and improve equity in post-discharge care.”

This study is only one part of a larger four-year project funded by the National Institutes of Health. The researchers’ next step will involve directly testing their algorithm as a real-time warning system for children having their appendix removed.