Low birth weight is a strong indicator of current and future health, but it’s also tough to calculate prior to a baby actually being born.

A new AI tool out of India may change that.  Developed by Whadhwani AI, an “AI for social good” nonprofit, the mobile tool takes a video of a baby and “reconstructs” the infant as a 3D model.

According to an article at Fast Company, machine learning “has trained the tool on parameters like body shapes and volumes, from which it can calculate the baby’s weight within seconds. The data—tamper-proof and geo-tagged with the baby’s location—is then uploaded directly onto medical record dashboards.”

Given that it functions as a smartphone app, it’s ideal by healthcare workers in the developing world as extra equipment or software are unnecessary. After completing the calculation, healthcare workers can recommend simple interventions “such as careful temperature maintenance, and adapting breastfeeding and bathing regimens.”

The company has rolled out hospital and at-home pilots across four Indian states, including Gujarat and Telangana, via partnerships with state governments and nonprofits, and developers plan to “configure the tool to gauge other important health indicators, like a baby’s head and upper-arm circumferences.”

The tool has proven accurate in early trials. “We are able to detect low birth weight babies almost 90% of the time, with 90% accuracy,” said Rahul Panicker, Wadhwani AI’s chief research and innovation officer.

The company is planning a nationwide launch for next year, which will likely be followed by expansion to other developing countries, including Bangladesh, as well as regions such as East Africa.

In addition, Wadhwani is developing other AI tools in healthcare and technology. By leveraging AI in the developing world, Panicker said, “We are hoping that we can bring the power of AI to help the truly underserved, so that it doesn’t stay restricted to optimizing Netflix recommendations.”

According to the article, “visiting workers often have to use old-fashioned spring scales, which are low in supply and can be poorly calibrated. Weights are recorded by hand, and only weeks later inputted into central databases, at which point data is often lost or tampered with. The potential for human error is great.”

Currently, in India, which has one of the highest rates of low birth weights in the world, about 50% of the cases are never identified due to poor measurements.