The eyes are not just a window to the soul. Tracking saccades can help doctors identify a number of brain health problems. That’s why the Franco-Belgian medtech startup neuroClues builds accessible, high-speed eye-tracking technology that incorporates AI-based analysis. He wants to make it easier for healthcare providers to use eye tracking to support the diagnosis of neurodegenerative conditions.
The company is starting with a focus on Parkinson’s disease, which already typically incorporates a test of a patient’s eye movement. Today, a doctor asks a patient to “follow my finger,” but neuroClues wants clinicians to use its proprietary, wearable headset to record eye movements at 800 frames per second, after which they can they do an analysis of the data in just a few seconds.
The 3.5-year-old outfit’s founders — two of whom are neuroscience researchers — point to the high misdiagnosis rates of Parkinson’s disease as one of the factors informing their decision to focus on the disease first. But them ambitions are broader. They paint a picture of the future in which their device becomes a “stethoscope for the brain.” Imagine, for example, if your annual trip to the optician could come with a quick brain health scan and compare you to typical benchmarks for your age. According to the startup, which says it aims to help 10 million patients by 2032, the eye-tracking protocols could also help test for other diseases and conditions, including concussions, Alzheimer’s, MS and stroke.
The startup is in the process of applying for FDA approval and hopes to license its device as a clinical support tool in the US later this year. It is processing the same type of application in the European Union and expects to receive regulatory approval in the EU in 2025.
So how does the device work? The patient looks through the headset and sees a screen where dots appear. A clinician will then tell them to follow the dots with their eyes, and then the device outputs data that can be used as biomarkers of disease by recording and analyzing their eye movements, measuring things like latency and error rate. It also provides the clinician a typical value expected from a healthy population for comparison with patient results.
“The first scientific paper using eye tracking to diagnose patients is in 1905,” neuroClues co-founder and CEO Antoine Pouppez told TechCrunch in an exclusive interview, noting that the technique was originally used to diagnose schizophrenia . In the 1960s, when eye tracking videos arrived, there was an explosion in research into the tracking technique neurological disorders. But decades of research into the utility of eye tracking as a diagnostic technique didn’t translate into widespread clinical uptake because the technology wasn’t there yet and/or was too expensive, Pouppez said.
“That’s where this technology comes from: The frustration of my co-founders seeing that eye tracking has a lot of value – it’s been proven in research that’s been clinically proven in thousands of patients in research facilities – and it’s still not being used in clinical practice,” he said. “Doctors today use their fingers – and literally say ‘follow my finger’ – while an eye moves 600 degrees per second. You make three eye movements per second. And so it’s very, very difficult — almost impossible — to assess how well you’re moving [by human eye alone].”
Others have also identified the potential to do more with eye tracking as a diagnostic aid.
based in the USA Neurosync, for example, offers a virtual reality headset paired with FDA-cleared eye-tracking software that it says can analyze the user’s eye movements “to aid in concussion diagnosis.” The product is aimed at football players and athletes of other contact sports who face an increased risk of head injury.
There are also mobile app makers — such as BrainEye — consumer promotion of smartphone-based eye-tracking technology for self-monitoring of “brain health.” (However, such claims are not evaluated by medical device regulators.)
But neuroClues stands out in several ways. First, he says his headset can sit in a regular clinician’s office, without the need for a darkroom setup or specialized computing hardware. It does not use off-the-shelf hardware, but develops special eye-tracking headsets for eye testing designed for high-speed recording and control of the recording environment. The outfit’s founders further argue that by building its own hardware and software, neuroClues enjoys unrivaled download speed in a commercially developed, non-static device.
To protect these apparent advantages, neuroClues has granted (or filed) a number of patents covering various aspects of the design, such as the synchronization of hardware and software and its approach to data analysis.
“We’re the only ones in the market today that capture 800 frames per second on a handheld device,” said Pouppez, noting that the “gold standard” of research is 1,000 frames per second. “There’s no clinical or non-clinical product that can do it at this frame rate, which meant we had to break barriers that no one had broken before.”
Image credit: neuroClues
neuroClues, which was incubated at the Paris Brain Institute, expects the first eye-tracking headsets to be deployed in specialist settings such as university hospitals, to be used on patients who have already been referred to consultants. He notes that the service will be reimbursed through existing health insurance codes, since follow-up eye exams are an established medical intervention. The company says it is also in talks with a number of other companies in the US and Europe that are interested in its hardware and software.
This first version of the device is designed as a diagnostic aid, meaning that the clinician is still responsible for interpreting the results. However, Pouppez said the team’s goal is to evolve the technology to offer interpretations of the data, too, so the device can be deployed more widely.
“Our goal is to move quickly down the line to bring these diagnostic capabilities to professionals,” he told us. “We hope to be on the market with such a device in ’26/’27. And so to broaden our market prospects and really be in [the toolbox of] every neurologist in the US and Europe.”
The startup announces the closing of a €5 million pre-Series A funding round, led by the White Fund and the European Commission’s EIC Accelerator program. Existing investors Invest.BW also participated, as well as several business angels, such as Fiona du Monceau, former chairman of the board of UCB, Artwall, and Olivier Legrain, CEO of IBA. Including this round, neuroClues has raised a total of €12 million since its founding in 2020.
Pouppez said he would look to raise a Series A in the next 12 to 18 months. “Our existing investors and the European Commission have already shown interest in participating, so I’m basically looking for a lead investor,” he added.