Embedded Files
Published Date : 28/09/2025
Amyotrophic Lateral Sclerosis (ALS) progressively impairs motor functions, making communication increasingly difficult. The HALO system, which combines surface electromyography (sEMG) with Large Language Models (LLMs), offers a new solution by enabling patients to communicate with simple eyebrow movements.
Amyotrophic Lateral Sclerosis (ALS) progressively impairs motor functions, making communication increasingly difficult. The HALO system, which combines surface electromyography (sEMG) with Large Language Models (LLMs), offers a new solution by enabling patients to communicate with simple eyebrow movements.
Amyotrophic Lateral Sclerosis (ALS) is a devastating neurological disorder that progressively impairs motor functions, making it increasingly difficult for affected individuals to communicate. However, many patients with ALS retain control over their ocular and periocular muscles, presenting a unique opportunity for Augmentative and Alternative Communication (AAC) systems. This article introduces the HALO system, an innovative AAC solution that combines surface electromyography (sEMG) with Large Language Models (LLMs) to facilitate communication for individuals with severe motor impairments.
The HALO system is designed to be calibration-free and user-friendly. It harnesses the power of LLMs to generate personalized, context-aware response options. The user can select a full-sentence reply with a single eyebrow muscle contraction, making communication both efficient and low-effort. The system captures eyebrow muscle activity through textile electrodes embedded in a headband, which are then processed in real time using a Recurrent Neural Network (RNN).
Trained and evaluated on data from patients with ALS, the model achieved impressive results, with 96% accuracy and an 85% F1-score. These metrics demonstrate the model's reliable gesture detection capabilities, which are crucial for supporting efficient communication in individuals with severe motor impairments.
While direct comparisons to existing systems are limited, as many sEMG-based AAC systems are rarely benchmarked on ALS cohorts and often fail to report key metrics such as gesture detection accuracy, the HALO system stands out for its robust performance. The system's reliability and ease of use make it a promising solution for improving the quality of life for individuals with ALS.
The development of the HALO system was supported by several funding sources, including FCT - Fundação para a Ciência e a Tecnologia, I.P., and the European Regional Development Fund (FEDER) through the Lisbon Regional Programme (LISBOA 2030) of the Portugal 2030 framework. The project also received ethical approval from the Ethics Committee of Universidade de Trás-os-Montes e Alto Douro (UTAD), ensuring that all necessary patient/participant consent was obtained and the appropriate institutional forms were archived.
The dataset used for training and evaluating the HALO system is not publicly available due to proprietary restrictions. However, data may be made available from the corresponding author upon reasonable request and with permission from HALO NeuroAI. This ensures that the system's development remains protected while allowing for potential future research and collaboration.
In summary, the HALO system represents a significant advancement in AAC technology for individuals with ALS. By combining sEMG with LLMs, it offers a reliable and user-friendly solution that can significantly enhance communication for those with severe motor impairments. The system's high accuracy and F1-score, along with its calibration-free design, make it a promising tool for improving the quality of life for ALS patients.
Frequently Asked Questions (FAQS):
Frequently Asked Questions (FAQS):
Q: What is Amyotrophic Lateral Sclerosis (ALS)?
A: Amyotrophic Lateral Sclerosis (ALS) is a progressive neurological disorder that affects motor neurons, leading to the gradual loss of muscle control and function. It often results in difficulties with speaking, swallowing, and eventually, breathing.
Q: How does the HALO system work?
A: The HALO system uses surface electromyography (sEMG) to detect muscle activity in the eyebrow region. This activity is then processed in real time using a Recurrent Neural Network (RNN) to generate personalized, context-aware response options. Users can select a full-sentence reply with a single eyebrow muscle contraction.
Q: What are the key metrics of the HALO system?
A: The HALO system achieved 96% accuracy and an 85% F1-score in detecting eyebrow muscle activity. These metrics indicate the system's reliability in supporting efficient communication for individuals with severe motor impairments.
Q: How is the HALO system different from existing AAC systems?
A: The HALO system stands out for its calibration-free design and the use of Large Language Models (LLMs) to generate personalized responses. It also achieved higher accuracy and F1-scores compared to many existing sEMG-based AAC systems, which are often not benchmarked on ALS cohorts.
Q: Where can I find more information about the HALO system?
A: For more information about the HALO system, you can contact the corresponding author or visit the HALO NeuroAI website. The dataset used for training and evaluation is not publicly available but may be accessible upon reasonable request and with permission.
More Related Topics :
More Related Topics :
Page updated
Report abuse