Online speech synthesis using a chronically implanted brain-computer interface in an individual with ALS.

Brain-computer interfaces (BCIs) that reconstruct and synthesize speech using brain activity recorded with intracranial electrodes may pave the way toward novel communication interfaces for people who have lost their ability to speak, or who are at high risk of losing this ability, due to neurological disorders. Here, we report online synthesis of intelligible words using a chronically implanted brain-computer interface (BCI) in a man with impaired articulation due to ALS, participating in a clinical trial (ClinicalTrials.gov, NCT03567213) exploring different strategies for BCI communication. The 3-stage approach reported here relies on recurrent neural networks to identify, decode and synthesize speech from electrocorticographic (ECoG) signals acquired across motor, premotor and somatosensory cortices. We demonstrate a reliable BCI that synthesizes commands freely chosen and spoken by the participant from a vocabulary of 6 keywords previously used for decoding commands to control a communication board. Evaluation of the intelligibility of the synthesized speech indicates that 80% of the words can be correctly recognized by human listeners. Our results show that a speech-impaired individual with ALS can use a chronically implanted BCI to reliably produce synthesized words while preserving the participant's voice profile, and provide further evidence for the stability of ECoG for speech-based BCIs.

Continuous Monitoring of Cerebral Autoregulation in Adults Supported by Extracorporeal Membrane Oxygenation.

BACKGROUND: Impaired cerebral autoregulation (CA) is one of several proposed mechanisms of acute brain injury in patients supported by extracorporeal membrane oxygenation (ECMO). The primary aim of this study was to determine the feasibility of continuous CA monitoring in adult ECMO patients. Our secondary aims were to describe changes in cerebral oximetry index (COx) and other metrics of CA over time and in relation to functional neurologic outcomes. METHODS: This is a single-center prospective observational study. We measured COx, a surrogate measurement of cerebral blood flow measured by near-infrared spectroscopy, which is an index of CA derived from the moving correlation between mean arterial pressure (MAP) and slow waves of regional cerebral oxygen saturation. A COx value that approaches 1 indicates impaired CA. Using COx, we determined the optimal MAP (MAPOPT) and lower and upper limits of autoregulation for individual patients. These measurements were examined in relation to modified Rankin Scale (mRS) scores. RESULTS: Fifteen patients (median age 57 years [interquartile range 47-69]) with 150 autoregulation measurements were included for analysis. Eleven were on veno-arterial ECMO (VA-ECMO), and four were on veno-venous ECMO (VV-ECMO). Mean COx was higher on postcannulation day 1 than on day 2 (0.2 vs. 0.09, p < 0.01), indicating improved CA over time. COx was higher in VA-ECMO patients than in VV-ECMO patients (0.12 vs. 0.06, p = 0.04). Median MAPOPT for the entire cohort was highly variable, ranging from 55 to 110 mm Hg. Patients with mRS scores 0-3 (good outcome) at 3 and 6 months spent less time outside MAPOPT compared with patients with mRS scores 4-6 (poor outcome) (74% vs. 82%, p = 0.01). The percentage of time when observed MAP was outside the limits of autoregulation was higher on postcannulation day 1 than on day 2 (18.2% vs. 3.3%, p < 0.01). CONCLUSIONS: In ECMO patients, it is feasible to monitor CA continuously at the bedside. CA improved over time, most significantly between postcannulation days 1 and 2. CA was more impaired in VA-ECMO patients than in VV-ECMO patients. Spending less time outside MAPOPT may be associated with achieving a good neurologic outcome.

Continuous Monitoring of Cerebral Autoregulation in Adults Supported by Extracorporeal Membrane Oxygenation.

Background: Impaired cerebral autoregulation (CA) is one of several proposed mechanisms of acute brain injury in patients supported by extracorporeal membrane oxygenation (ECMO). The primary aim of this study was to determine the feasibility of continuous CA monitoring in adult ECMO patients. Our secondary aims were to describe changes in cerebral oximetry index (COx) and other metrics of CA over time and in relation to functional neurologic outcomes. Methods: This is a single-center prospective observational study. We measured Cox, a surrogate measurement of cerebral blood flow, measured by near-infrared spectroscopy, which is an index of CA derived from the moving correlation between mean arterial pressure and slow waves of regional cerebral oxygen saturation. A COx value that approaches 1 indicates impaired CA. Using COx, we determined the optimal MAP (MAPOPT), lower and upper limits of autoregulation for individual patients. These measurements were examined in relation to modified Rankin Scale (mRS) scores. Results: Fifteen patients (median age=57 years [IQR=47-69]) with 150 autoregulation measurements were included for analysis. Eleven were on veno-arterial ECMO and 4 on veno-venous. Mean COx was higher on post-cannulation day 1 than on day 2 (0.2 vs 0.09, p<0.01), indicating improved CA over time. COx was higher in VA-ECMO patients than in VV-ECMO (0.12 vs 0.06, p=0.04). Median MAPOPT for entire cohort was highly variable, ranging 55-110 mmHg. Patients with mRS 0-3 (good outcome) at 3 and 6 months spent less time outside of MAPOPT compared to patients with mRS 4-6 (poor outcome) (74% vs 82%, p=0.01). The percentage of time when observed MAP was outside the limits of autoregulation was higher on post-cannulation day 1 than on day 2 (18.2% vs 3.3%, p<0.01). Conclusions: In ECMO patients, it is feasible to monitor CA continuously at the bedside. CA improved over time, most significantly between post-cannulation days 1 and 2. CA was more impaired in VA-ECMO than VV-ECMO. Spending less time outside of MAPOPT may be associated with achieving a good neurologic outcome.

Online speech synthesis using a chronically implanted brain-computer interface in an individual with ALS.

Recent studies have shown that speech can be reconstructed and synthesized using only brain activity recorded with intracranial electrodes, but until now this has only been done using retrospective analyses of recordings from able-bodied patients temporarily implanted with electrodes for epilepsy surgery. Here, we report online synthesis of intelligible words using a chronically implanted brain-computer interface (BCI) in a clinical trial participant (ClinicalTrials.gov, NCT03567213) with dysarthria due to amyotrophic lateral sclerosis (ALS). We demonstrate a reliable BCI that synthesizes commands freely chosen and spoken by the user from a vocabulary of 6 keywords originally designed to allow intuitive selection of items on a communication board. Our results show for the first time that a speech-impaired individual with ALS can use a chronically implanted BCI to reliably produce synthesized words that are intelligible to human listeners while preserving the participants voice profile.