RESUMEN
GOAL: During mechanical ventilation, patient-ventilator disharmony is frequently observed and may result in increased breathing effort, compromising the patient's comfort and recovery. This circumstance requires clinical intervention and becomes challenging when verbal communication is difficult. In this study, we propose a brain-computer interface (BCI) to automatically and noninvasively detect patient-ventilator disharmony from electroencephalographic (EEG) signals: a brain-ventilator interface (BVI). METHODS: Our framework exploits the cortical activation provoked by the inspiratory compensation when the subject and the ventilator are desynchronized. Use of a one-class approach and Riemannian geometry of EEG covariance matrices allows effective classification of respiratory states. The BVI is validated on nine healthy subjects that performed different respiratory tasks that mimic a patient-ventilator disharmony. RESULTS: Classification performances, in terms of areas under receiver operating characteristic curves, are significantly improved using EEG signals compared to detection based on air flow. Reduction in the number of electrodes that can achieve discrimination can be often desirable (e.g., for portable BCI systems). By using an iterative channel selection technique, the common highest order ranking, we find that a reduced set of electrodes (n = 6) can slightly improve for an intrasubject configuration, and it still provides fairly good performances for a general intersubject setting. CONCLUSION: Results support the discriminant capacity of our approach to identify anomalous respiratory states, by learning from a training set containing only normal respiratory epochs. SIGNIFICANCE: The proposed framework opens the door to BVIs for monitoring patient's breathing comfort and adapting ventilator parameters to patient respiratory needs.
Asunto(s)
Interfaces Cerebro-Computador , Encéfalo/fisiología , Electroencefalografía/métodos , Reconocimiento de Normas Patrones Automatizadas/métodos , Respiración Artificial/métodos , Mecánica Respiratoria/fisiología , Adulto , Diagnóstico por Computador/métodos , Femenino , Humanos , Aprendizaje Automático , MasculinoRESUMEN
The need of a reliable seizure prediction is motivated by the 50 million people in the world suffering from epilepsy, of whom 30% have no control on seizures with current pharmacological treatments. Seizure prediction research holds great promise for such patients, since an effective algorithm will enable the development of a closed-loop system that intervenes before the clinical onset of a seizure. As a step toward practical implementation of this technology, we present a new method based on a measure of brain excitability identified by couplings between low-frequency phases and high-frequency amplitudes of brain oscillations. The proposed method was applied to long-term intracranial recordings of 20 patients with partial epilepsy, for a total of 267 seizures and more than 3400-hour-long interictal activities. We found that our predictor was in 50% of cases better than chance, with an average sensitivity of 98.9% and false prediction rate of 1.84/hour. From these observations, we concluded that our method enables a new quantitative way to identify preictal states with a high risk of seizure generation.