Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
Co-inventor of Apple’s FaceID and Vision Pro technology has spent the past six years developing a smart border-based system that could one day help detect electrical activity in the brain to diagnose cognitive disorders.
Now, Gidi Littwin’s startup, Hemispheric, raised $52 million after collecting data on the brains of 100,000 people to train deep learning models to analyze the brain without the need for invasive techniques.
Littwin left Apple in 2020, looking for a change. He found it when Hemispheric co-founder Hagai Lalazar sent him a message on LinkedIn. Lalazar had started developing artificial intelligence to study the brain without the need for surgery, and was looking for a business partner to take the company forward. When he found Littwin, he talked to about 75 people.
Littwin helped develop FaceID, and at the time was working on a hands-on research project for a popular product, the Vision Pro. As part of that, he had to raise what he told WIRED were “thousands of dollars in scholarship money” to teach deep learning techniques that support technology.
“There was a huge data collection effort behind these projects and we knew we had to do something very similar in the Hemispheric,” says Littwin, “and we have.”
Because everyone’s brain activity looks different, doctors have had to rely on questionnaires and behavioral tests to diagnose depression, Alzheimer’s, and Parkinson’s. To overcome this, Littwin and Hagai gathered their “valuable resources”: a quarter of a million brains from 100,000 paid volunteers throughout Asia, as well as Tel Aviv, and Boston. People did a series of activities that looked like games but activated different parts of their brains.
That data helped to train the model of the boundary, which makes the brain work from the electricity inside the skull as the big languages know the meaning by analyzing the text. He then tested the model on a small group of people, including those diagnosed with PTSD, schizophrenia, and depression and said the model accurately predicted the health of the person’s brain. The team is currently working on a clinical trial to test whether their model can detect and predict Alzheimer’s.
The team will submit their first drug, which will be used to study PTSD, to the FDA for approval early next year. They hope that this will allow them to release the product to the public in 2027.
To help diagnose cognitive impairment, the patient wears a lightweight EEG headset that measures electrical activity in the brain for about 15 minutes while interacting with an app on a tablet. Hemispheric says its AI model will help clinicians identify symptoms to diagnose disease, choose the best course of action by predicting treatments, and monitor progress.
“The future we’re seeing is one that parallels blood testing,” Lalazar told WIRED in an interview. “This device will be very cheap; it can be sold and distributed in all mental hospitals, clinics, even in the offices of psychiatrists.”
AI-powered diagnostic tools for conditions like lung cancer are already being used in clinical practice and speeding up access to treatment across Europe. Meanwhile, AI giants including OpenAI and Anthropic are increasingly moving into healthcare, intensifying the competition for startups in the space.
Hemispheric has raised initial capital from investors including American and Israeli venture capital firms and individual investors, among them the first Uber-backer Howard Morgan. They will use the money to develop relationships with governments, medical institutions, and pharmaceutical companies, to lend to others in the US, and to work toward regulatory approval. They also plan to measure brain data from millions of people in an attempt to improve their performance
The pair are also developing their own brain imaging system to capture data that the company believes will provide more useful information for its models than traditional EEGs. “These tools are not built for machine learning and not for deep learning,” says Littwin.
