Lower frequency ECoG features improve longitudinal stability of speech and hand-grasp detection in a patient with progressive ALS
Year: 2026
Type: article
Abstract: Objective. Achieving long-term decoding stability is a critical challenge for chronic intracranial brain-computer interfaces (BCIs). High-gamma (HG) activity from intracranial recordings is the standard signal for BCI control, and lower-frequency features can enhance HG decoding performance. This study evaluated the longitudinal stability of speech and hand-grasp detection models using individual and joint spectral features, and the local motor potential (LMP). Approach. Longitudinal data from a single participant implanted with two 64-channel ECoG arrays were used to evaluate the long-term stability of logistic regression models for speech and hand-grasp detection. Models were trained on individual frequency bands and on the LMP, a time-domain low-frequency feature, and evaluated over 21 months for speech and 13 months for grasp. The best-performing band features were then combined into multi-band models and analyzed for their spatial contributions. Main Results. The LMP yielded the most accurate single feature models in both tasks (speech 93.8%, grasp 99.4%) and showed little or no decline. Multi-band models combining HG with lower frequency bands were substantially more stable than HG-only models and outperformed the LMP models for speech but not grasp. HG accuracy degraded strongly for both tasks (speech:-4.3 percentage points per 100 days, or pp/100d, grasp:-3.4 pp/100d). HG+beta for speech showed a negligible decline (-0.5 pp/100d, 95.6% ±0.06% overall), and for grasp, delta alone showed remarkable stability (+0.5 pp/100d), while HG+beta+delta maintained 98.2 ±0.09% overall accuracy with flat performance (+0.0 pp/100d). The advantage of the multi-band models increased over time, reaching +20.6 pp for speech and +10.2 pp for grasp in the last 100 days. Significance. Incorporating lower-frequency neural activity yields more stable long-term speech and grasp detection than HG alone. These findings indicate that lower-frequency and multi-band features may reduce recalibration requirements for simple BCI tasks, and may complement the precision control provided by HG activity.
Source: Journal of Neural Engineering
Institutions: Virginia Commonwealth University, Johns Hopkins University
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: hybrid
Estimated APC paid: $3,325
OpenAlex ID: W7225761360
FWCI:
Cites:
Cited by:
Related to: