Alonso-Vázquez Denise, Mendoza-Montoya Omar, Caraza Ricardo, Martinez Hector R, Antelis Javier M
Escuela de Ingeniería y Ciencias, Tecnologico de Monterrey, Monterrey, Mexico.
Escuela de Medicina y Ciencias de la Salud, Tecnologico de Monterrey, Monterrey, Mexico.
Front Neuroinform. 2025 Jun 27;19:1583428. doi: 10.3389/fninf.2025.1583428. eCollection 2025.
decoding using EEG holds promising applications for individuals with motor neuron diseases, although its performance remains limited due to small dataset sizes and the absence of sensory feedback. Here, we investigated whether incorporating EEG data from (pronounced) speech could enhance classification.
Our approach systematically compares four classification scenarios by modifying the training dataset: intra-subject (using only , combining and , and using only ) and multi-subject (combining data from different participants with the of the target participant). We implemented all scenarios using the convolutional neural network EEGNet. To this end, twenty-four healthy participants pronounced and imagined five Spanish words.
In binary word-pair classifications, combining and data in the intra-subject scenario led to accuracy improvements of 3%-5.17% in four out of 10 word pairs, compared to training with only. Although the highest individual accuracy (95%) was achieved with alone, the inclusion of data allowed more participants to surpass 70% accuracy, increasing from 10 () to 15 participants. In the intra-subject multi-class scenario, combining and did not yield statistically significant improvements over using exclusively.
Finally, we observed that features such as word length, phonological complexity, and frequency of use contributed to higher discriminability between certain word pairs. These findings suggest that incorporating data can improve decoding in individualized models, offering a feasible strategy to support the early adoption of brain-computer interfaces before speech deterioration occurs in individuals with motor neuron diseases.
尽管由于数据集规模小且缺乏感觉反馈，基于脑电图（EEG）的解码技术在运动神经元疾病患者中的应用效果仍有限，但该技术具有广阔的应用前景。在此，我们研究了纳入（发音的）语音脑电数据是否能提高分类效果。
我们的方法通过修改训练数据集系统地比较了四种分类方案：个体内（仅使用，结合和，仅使用）和多个体（将来自不同参与者的数据与目标参与者的相结合）。我们使用卷积神经网络EEGNet实现了所有方案。为此，24名健康参与者发音并想象五个西班牙语单词。
在二元单词对分类中，与仅使用训练相比，个体内方案中结合和数据使10个单词对中的4个准确率提高了3%-5.17%。尽管仅使用时个体最高准确率达到了95%，但纳入数据使更多参与者的准确率超过了70%，从10名（仅使用）增加到了15名。在个体内多类场景中，结合和与仅使用相比，未产生统计学上的显著改善。
最后，我们观察到单词长度、语音复杂性和使用频率等特征有助于提高某些单词对之间的可区分性。这些发现表明，纳入数据可以改善个性化模型中的解码，为运动神经元疾病患者在语音恶化之前支持脑机接口的早期采用提供了一种可行的策略。
