Cambridge, UK & Montreal, CA – 27 January 2019 – BIOS, a leading neural engineering startup, today announced findings for its groundbreaking research in which it was able to automatically extract the neural signals regulating physiological biomarkers using an AI-enabled neural interface. This advance creates a new way of investigating conditions, accelerates the discovery of neural biomarkers, and opens the door for a new generation of AI-based neural healthcare treatments. The team is revealing its findings today at The International Neuromodulation Society’s 14th World Congress in Sydney, Australia.

 

Bioelectronic medicine, neuroceuticals and closed-loop neuromodulation therapies have emerged as a new way to treat chronic conditions, offering an alternative to pharmaceuticals. The central role the brain and neural pathways play in controlling our major organ systems has begun to be understood scientifically over the past 20 years. These therapies adapt neural signals directly and offer the ability to create more targeted and more effective treatments than pharmaceuticals, at a lower cost and with fewer side effects. For chronic diseases such as heart disease, arthritis or diabetes, which can be expensive and difficult to treat, the potential exists to revolutionise treatment for billions of people.

 

A major bottleneck to date in the development of such treatments has been the speed and accuracy with which scientists could discover and recreate the exact neural signal patterns (biomarkers) capable of affecting our health. Once identified these biomarkers can be used to design new treatments. Neural data is incredibly complex so vast amounts of neural data and more powerful interpretation techniques are key to correctly finding the signal patterns that can be used as biomarkers.

 

BIOS’s approach has been to develop a neural data biomarker discovery platform combining long lifetime neural interfaces (connections that allow computers to read and write neural data directly to and from the body) with a deep learning based AI system to “learn” the biomarkers directly from the neural data.

 

The findings come after the company used its data platform to facilitate the discovery of peripheral nervous system neural biomarkers in pre-clinical models. The team recorded raw neural data through its proprietary neural interfaces and also recorded physiological signals through more traditional methods including heart rate, blood pressure, glucose levels, activity levels, and temperature. The data captured allowed BIOS to capture and synchronise months of continuous neural and physiological data on timescales long enough for their AI engine to observe and identify persistent neural biomarkers and their relation to changes in organ function.

 

By being able to understand the “language” of the nervous system for the first time, this biomarker discovery platform will enable BIOS and its research partners to conduct closed-loop experiments to easily test neuromodulation therapies on new disease targets. The use of closed-loop neuromodulation and bioelectronic medicine is growing within healthcare, which aims to treat everything from diabetes to heart disease. By proving the ability to intercept neural data and derive physiologically relevant neural biomarkers, this pioneering research platform accelerates treatment development for a range of chronic conditions and is also a huge step towards real-world clinical applications of AI within the body.

 

Oliver Armitage, Co-Founder and Chief Scientific Officer at BIOS, said: