Sunday, April 16, 2023

New System-on-Chip Identifies and Manages Neurological Disorders

About Topic In Short:

Who:

Mahsa Shoaran and Stéphanie Lacour from Ecole Polytechnique Fédérale de Lausanne

What:

Development of a closed-loop neuromodulation system-on-chip called NeuralTree that can detect and alleviate neurological disorder symptoms by identifying and blocking electrical signals associated with disorders such as epileptic seizure and Parkinsonian tremor.

How:

Biomarkers are extracted and classified from real patient data and animal models of disease in-vivo using a 256-channel high-resolution input sensing array and an energy-efficient machine learning processor. If a symptom is detected, a neurostimulator located on the chip sends an electrical pulse to block it.

Introduction

Neurological disorders are a growing concern worldwide, and their prevalence is increasing at an alarming rate. To address this issue, researchers from the Integrated Neurotechnologies Laboratory at Ecole Polytechnique Fédérale de Lausanne have developed a new system-on-chip that can identify and manage neurological disorders. This new technology has the potential to revolutionize the field of neurology by providing accurate and timely diagnosis and treatment options for patients.

Background

The study conducted by the researchers at Ecole Polytechnique Fédérale de Lausanne focuses on the development of NeuralTree, a closed-loop neuromodulation system-on-chip that can detect and alleviate disease symptoms. The system uses a 256-channel high-resolution input sensing array and an energy-efficient machine learning processor to extract and classify a broad set of biomarkers from real patient data and animal models of disease in-vivo.

Process of Creation

The researchers first collected datasets from both epilepsy and Parkinson's disease patients to train the machine learning algorithm. They then developed an area-efficient design, making the chip extremely small (3.48mm2) and highly scalable to more channels. The integration of an "energy-aware" learning algorithm further enhanced its energy efficiency.

How it Works

Biomarkers are patterns of electrical signals known to be associated with certain neurological disorders. NeuralTree's machine learning algorithm can accurately classify pre-recorded neural signals from both epilepsy and Parkinson's disease patients, identifying the possibility of disorders like epileptic seizure or Parkinsonian tremor. If a symptom is detected, a neurostimulator, also located on the chip, is activated, sending an electrical pulse to block it.

Thus Speak Authors/Experts

According to Mahsa Shoaran, lead researcher of the Integrated Neurotechnologies Laboratory, "NeuralTree's unique ability to detect a broader range of symptoms than other devices, which until now have focused primarily on epileptic seizure detection, can revolutionize the way we diagnose and manage neurological disorders."

Conclusion

In conclusion, the development of the NeuralTree system-on-chip has the potential to significantly impact the field of neurology by providing accurate and timely diagnosis and treatment options for patients with neurological disorders. The chip's energy efficiency and small size make it highly scalable and suitable for widespread use in the medical industry. As researchers continue to improve the machine learning algorithm and update the chip's software, NeuralTree has the potential to become a game-changer in the management of neurological disorders.

Image Gallery

All Images Credit: from References/Resources sites [Internet]

Hashtag/Keyword/Labels:

neurotechnology, neurological disorders, system-on-chip, biomarkers, machine learning, neuromodulation, energy-efficient, Ecole Polytechnique Fédérale de Lausanne.