Device-Based Neurotechnology to Improve Telecommunication in ALS Patients

By Giane Espiritu, Zach Tung 

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disorder affecting upper and lower motor neurons. It exhibits a diverse clinical heterogeneity, with numerous genetic and sporadic aetiologies identified, where over 120 genes are implicated in familial ALS. Environmental factors are also indicated, such as smoking, head trauma, and pesticides. These factors contribute to oxidative stress, excitotoxicity, mitochondrial and proteasomal dysfunctions, all of which were indicated in the pathophysiology of ALS. Current interventions that evidently improve quality of life (QOL) and survival of the patients include pharmacological approaches (Riluzole, Edaravone, and sodium phenylbutyrate) and non-invasive ventilation (NIV). Supportive care is also available, despite variable effectiveness, including occupational and speech therapists, nutrition support, and psychotherapy. 

As ALS progresses, patients develop debilitating symptoms such as chronic respiratory failure, difficulty swallowing, inability to speak (dysarthria), and immobility. Improvement in dysarthria and immobility, which are essential communicative mechanisms, would preserve the social participation of ALS patients and reduce the burden of carers, which could dramatically increase their QOL and independence. Therefore, in this blog, we decided to focus on the use of device-based neurotechnology that improves telecommunication in ALS, specifically the use of brain-computer interface (BCI) and robotics. 

Implantable BCI for Computer Control

Carried out by the University of Melbourne, a small implantable device has been developed to allow patients experiencing impaired motor function to text and email on a computer.

Stentrode™ is a small brain implant that acts as a “mind-reading” device and has been successfully placed into the motor cortex of two patients with upper limb paralysis caused by motor neuron disease (MND), specifically ALS. By converting wireless brain signals into action and using an eye-tracker for cursor control, this has enabled patients to perform zooming and clicking actions on the computer and even shop online. This minimally invasive procedure has the potential to transform communication for people experiencing severe motor neuron disease and various forms of paralysis. Compared to previous assistive devices that rely on large external hardware, a device like Stentrode™ presents more precise control whilst avoiding the risks and recovery associated with open brain surgery. Whilst it will take some years before such technology can fully restore independence, this innovation has provided paralysed individuals with the potential to carry out activities of daily living.

 Inner-Speech BCI for Communication

This is further synthesised in a similar study conducted by Stanford University researchers, who developed a novel brain-computer interface (BCI) to restore communication by decoding an individual’s inner speech. As ALS is a progressive degenerative disease that leads to the loss of control over the lips, tongue, and the building blocks of speech, communication restoration is echoed as a critical clinical need. By implanting microelectrode arrays into the motor cortex of participants with severe speech impairment, researchers recorded neural activity during attempted speech and inner speech. Using this data, they developed a system capable of decoding full sentences in real time, even across large vocabularies of up to 125,000 words.

This represents a significant advancement in neurotechnology, demonstrating that communication can be restored without remaining muscle function. By understanding that inner speech has a structured neural pattern within the motor cortex, researchers were able to translate brain activity into phonemes and full sentences, supporting meaningful communication. While current assistive technologies such as eye-tracking systems are slow, inner-speech BCIs offer a much faster and more natural form of communication, allowing conversations to be more reflective of everyday life. This approach has also addressed concerns surrounding mental privacy by introducing task-specific neural patterns, meaning the system is only trained to interpret signals associated with intentional speech production rather than spontaneous thought.

However, this approach is not without its limitations, since decoding inner speech remains less robust due to the variability of neural signals, resulting in lower accuracy compared to attempted speech. The study was also conducted on a small sample size, limiting how broadly these findings can be applied across ALS populations. Additionally, the use of invasive microelectrode implants presents surgical risks and raises questions about device longevity. Whilst this innovation offers the potential to change communication for individuals with paralysis, further improvements in accuracy and consistency are required before it can be implemented in everyday clinical settings.

Soft Robotics for Upper Limb Support

Despite being a relatively nascent field, neurorehabilitation using robotics is evolving rapidly. Technology such as KINARM, an exoskeleton developed in Canada used for assessments and training systems to collect clinical data, and Armeo Power, an exoskeleton designed for intense upper limb rehabilitation by a company based in Switzerland, and many more, have shown promising data for future standardization and clinical use.

Soft robotics offers a different perspective compared to the more established field of rigid robotics, even with some benefits over it for ALS intervention. In 2023, the Harvard/MGH group developed a soft shoulder wearable device; its aim is not rehabilitative, it instead focuses on functional compensation for individuals where recovery is unlikely or impossible. They conducted an experimental study with 10 ALS patients, using soft, compliant, lightweight hardware instead of mechanically rigid robotic joints. This serves several purposes: it overcomes the complex and highly mobile shoulder joint and prevents the use of overly complicated hardware and control. It is also important for mechanical transparency, which is the capability of the robotic wearable to not limit the user’s movements when powered off. This is especially useful clinically to establish a baseline of the patient’s range of motion. The control box can be worn on the waist or attached to a wheelchair, which does not affect shoulder movements.

The wearable is controlled to assist movement, not to passively mobilize the limb, by reacting within 150 ms of detecting the user’s intention to move their limb. Thus, accuracy and speed during task performance are linked to the user's residual ability.

This wearable is also easy to use, only requiring minimal training and a short initial calibration. After that, the participants were able to manoeuvre it independently and seamlessly switch between movements and activities. With the assistance of the wearable, participants’ range of motion, including abduction and flexion of the shoulder joint, had all been improved. There was also a reduction in shoulder muscle activity and an increase in endurance while holding weight.

Despite its benefits, some aspects can be improved, such as the limitation to only being able to assist the shoulder joint and its lack of ability to assist those without voluntary movement. Additionally, improving the motion intention detection, possibly via BCI, and shortening the donning process duration, or even developing a self-donning mechanism, will further promote patients’ independence.  Although a shoulder-only device would not provide sufficient support for all ALS patients, there are subsets of patients, like those with progressive muscular atrophy, for whom this device would provide marked improvements in independence. While the discussion here is mostly concerning ALS, the goal of this device, ultimately, is to improve upper limb impairments, which can be utilised in conditions like stroke and spinal cord injury. Lastly, to highlight the rapidly evolving nature of this field, this device was modified in 2025 with a combination of a personalized machine learning detection model and various sensors to decode the user’s motion intention, making it the first soft robotic shoulder device to use machine learning for personalized assistance.

Conclusion

From these studies, it is understood that device-based neurotechnology is progressively improving telecommunication in ALS patients. While inner-speech BCIs demonstrate the potential for thought-driven communication, devices such as Stentrode™ provide a more clinically accessible approach by translating neural signals into digital actions. Together, these innovations show a shift towards more independent communication, addressing a key limitation faced by individuals with ALS.

Similarly, developments in robotics demonstrate potential for improving functional movement and supporting independence, particularly through soft wearable devices designed for functional compensation. While current robotic systems remain limited in their scope and rely on an individual’s remaining muscle control, advancements such as machine learning integration and improved motion intention detection may further enhance their effectiveness.

Although challenges in accuracy, accessibility, and long-term reliability remain, these developments represent a transformative step in restoring communication and improving quality of life for individuals with ALS.

References

1.        Brotman RG, Moreno-Escobar MC, Joseph J, Pawar G. Amyotrophic lateral sclerosis [Internet]. PubMed. Treasure Island (FL): StatPearls Publishing; 2024. Available from: https://www.ncbi.nlm.nih.gov/books/NBK556151/

2.        Wang Z, Huang J, Yun D. Current and emerging therapeutic strategies for amyotrophic lateral sclerosis: from pharmacological approaches to gene and stem cell therapies. Frontiers in Neurology. 2026 Jan 22;17.

3.        Goldman, B. (2025). Study of promising speech-enabling interface offers hope for restoring communication. [online] News Center. Available at: https://med.stanford.edu/news/all-news/2025/08/brain-computer-interface.html.

4.        Kunz EM, Abramovich Krasa B, Kamdar F, Avansino DT, Hahn N, Yoon S, et al. Inner speech in motor cortex and implications for speech neuroprostheses. Cell [Internet]. 2025 Aug 14; Available from: https://www.sciencedirect.com/science/article/pii/S0092867425006816

5.        Oxley TJ, Yoo PE, Rind GS, Ronayne SM, Lee CMS, Bird C, et al. Motor neuroprosthesis implanted with neurointerventional surgery improves capacity for activities of daily living tasks in severe paralysis: first in-human experience. Journal of NeuroInterventional Surgery [Internet]. 2020 Oct 23;13(2). Available from: https://jnis.bmj.com/content/early/2020/10/30/neurintsurg-2020-016862

6.        Pugliese R, Sala R, Regondi S, Beltrami B, Lunetta C. Emerging technologies for management of patients with amyotrophic lateral sclerosis: from telehealth to assistive robotics and neural interfaces. Journal of Neurology. 2022 Jan 21;

7.        Proietti T, O’Neill CT, Gerez L, Cole T, Mendelowitz S, Nuckols K, et al. Restoring arm function with a soft robotic wearable for individuals with amyotrophic lateral sclerosis. Science Translational Medicine. 2023 Feb 1;15(681).

8.        Arnold J, Pathak P, Jin Y, Pont-Esteban D, McCann CM, Lehmacher C, et al. Personalized ML-based wearable robot control improves impaired arm function. Nature Communications [Internet]. 2025 Aug 2 [cited 2025 Aug 26];16(1). Available from: https://www.nature.com/articles/s41467-025-62538-8