Design-development of an at-home modular brain-computer interface (BCI) platform in a case study of cervical spinal cord injury.

OBJECTIVE: The objective of this study was to develop a portable and modular brain-computer interface (BCI) software platform independent of input and output devices. We implemented this platform in a case study of a subject with cervical spinal cord injury (C5 ASIA A). BACKGROUND: BCIs can restore independence for individuals with paralysis by using brain signals to control prosthetics or trigger functional electrical stimulation. Though several studies have successfully implemented this technology in the laboratory and the home, portability, device configuration, and caregiver setup remain challenges that limit deployment to the home environment. Portability is essential for transitioning BCI from the laboratory to the home. METHODS: The BCI platform implementation consisted of an Activa PC + S generator with two subdural four-contact electrodes implanted over the dominant left hand-arm region of the sensorimotor cortex, a minicomputer fixed to the back of the subject's wheelchair, a custom mobile phone application, and a mechanical glove as the end effector. To quantify the performance for this at-home implementation of the BCI, we quantified system setup time at home, chronic (14-month) decoding accuracy, hardware and software profiling, and Bluetooth communication latency between the App and the minicomputer. We created a dataset of motor-imagery labeled signals to train a binary motor imagery classifier on a remote computer for online, at-home use. RESULTS: Average bluetooth data transmission delay between the minicomputer and mobile App was 23 ± 0.014 ms. The average setup time for the subject's caregiver was 5.6 ± 0.83 min. The average times to acquire and decode neural signals and to send those decoded signals to the end-effector were respectively 404.1 ms and 1.02 ms. The 14-month median accuracy of the trained motor imagery classifier was 87.5 ± 4.71% without retraining. CONCLUSIONS: The study presents the feasibility of an at-home BCI system that subjects can seamlessly operate using a friendly mobile user interface, which does not require daily calibration nor the presence of a technical person for at-home setup. The study also describes the portability of the BCI system and the ability to plug-and-play multiple end effectors, providing the end-user the flexibility to choose the end effector to accomplish specific motor tasks for daily needs. Trial registration ClinicalTrials.gov: NCT02564419. First posted on 9/30/2015.

Continuous action deep reinforcement learning for propofol dosing during general anesthesia.

PURPOSE: Anesthesiologists simultaneously manage several aspects of patient care during general anesthesia. Automating administration of hypnotic agents could enable more precise control of a patient's level of unconsciousness and enable anesthesiologists to focus on the most critical aspects of patient care. Reinforcement learning (RL) algorithms can be used to fit a mapping from patient state to a medication regimen. These algorithms can learn complex control policies that, when paired with modern techniques for promoting model interpretability, offer a promising approach for developing a clinically viable system for automated anesthestic drug delivery. METHODS: We expand on our prior work applying deep RL to automated anesthetic dosing by now using a continuous-action model based on the actor-critic RL paradigm. The proposed RL agent is composed of a policy network that maps observed anesthetic states to a continuous probability density over propofol-infusion rates and a value network that estimates the favorability of observed states. We train and test three versions of the RL agent using varied reward functions. The agent is trained using simulated pharmacokinetic/pharmacodynamic models with randomized parameters to ensure robustness to patient variability. The model is tested on simulations and retrospectively on nine general anesthesia cases collected in the operating room. We utilize Shapley additive explanations to gain an understanding of the factors with the greatest influence over the agent's decision-making. RESULTS: The deep RL agent significantly outperformed a proportional-integral-derivative controller (median episode median absolute performance error 1.9% ± 1.8 and 3.1% ± 1.1). The model that was rewarded for minimizing total doses performed the best across simulated patient demographics (median episode median performance error 1.1% ± 0.5). When run on real-world clinical datasets, the agent recommended doses that were consistent with those administered by the anesthesiologist. CONCLUSIONS: The proposed approach marks the first fully continuous deep RL algorithm for automating anesthestic drug dosing. The reward function used by the RL training algorithm can be flexibly designed for desirable practices (e.g. use less anesthetic) and bolstered performances. Through careful analysis of the learned policies, techniques for interpreting dosing decisions, and testing on clinical data, we confirm that the agent's anesthetic dosing is consistent with our understanding of best-practices in anesthesia care.

Machine learning of EEG spectra classifies unconsciousness during GABAergic anesthesia.

In current anesthesiology practice, anesthesiologists infer the state of unconsciousness without directly monitoring the brain. Drug- and patient-specific electroencephalographic (EEG) signatures of anesthesia-induced unconsciousness have been identified previously. We applied machine learning approaches to construct classification models for real-time tracking of unconscious state during anesthesia-induced unconsciousness. We used cross-validation to select and train the best performing models using 33,159 2s segments of EEG data recorded from 7 healthy volunteers who received increasing infusions of propofol while responding to stimuli to directly assess unconsciousness. Cross-validated models of unconsciousness performed very well when tested on 13,929 2s EEG segments from 3 left-out volunteers collected under the same conditions (median volunteer AUCs 0.99-0.99). Models showed strong generalization when tested on a cohort of 27 surgical patients receiving solely propofol collected in a separate clinical dataset under different circumstances and using different hardware (median patient AUCs 0.95-0.98), with model predictions corresponding with actions taken by the anesthesiologist during the cases. Performance was also strong for 17 patients receiving sevoflurane (alone or in addition to propofol) (median AUCs 0.88-0.92). These results indicate that EEG spectral features can predict unconsciousness, even when tested on a different anesthetic that acts with a similar neural mechanism. With high performance predictions of unconsciousness, we can accurately monitor anesthetic state, and this approach may be used to engineer infusion pumps to intelligibly respond to patients' neural activity.

Implantable brain-computer interface for neuroprosthetic-enabled volitional hand grasp restoration in spinal cord injury.

Loss of hand function after cervical spinal cord injury severely impairs functional independence. We describe a method for restoring volitional control of hand grasp in one 21-year-old male subject with complete cervical quadriplegia (C5 American Spinal Injury Association Impairment Scale A) using a portable fully implanted brain-computer interface within the home environment. The brain-computer interface consists of subdural surface electrodes placed over the dominant-hand motor cortex and connects to a transmitter implanted subcutaneously below the clavicle, which allows continuous reading of the electrocorticographic activity. Movement-intent was used to trigger functional electrical stimulation of the dominant hand during an initial 29-weeks laboratory study and subsequently via a mechanical hand orthosis during in-home use. Movement-intent information could be decoded consistently throughout the 29-weeks in-laboratory study with a mean accuracy of 89.0% (range 78-93.3%). Improvements were observed in both the speed and accuracy of various upper extremity tasks, including lifting small objects and transferring objects to specific targets. At-home decoding accuracy during open-loop trials reached an accuracy of 91.3% (range 80-98.95%) and an accuracy of 88.3% (range 77.6-95.5%) during closed-loop trials. Importantly, the temporal stability of both the functional outcomes and decoder metrics were not explored in this study. A fully implanted brain-computer interface can be safely used to reliably decode movement-intent from motor cortex, allowing for accurate volitional control of hand grasp.

An early phase of instructive plasticity before the typical onset of sensory experience.

While early experience with moving stimuli is necessary for the development of direction selectivity in visual cortex of carnivores, it is unclear whether experience exerts a permissive or instructive influence. To test if the specific parameters of the experienced stimuli could instructively sculpt the emergent responses, visually naive ferrets were exposed to several hours of experience with unusual spatiotemporal patterns. In the most immature ferrets, cortical neurons developed selectivity to these patterns, indicating an instructive influence. In animals that were 1-10 days more mature, exposure to the same patterns led to a developmentally-typical increase in direction selectivity. We conclude that visual development progresses via an early phase of instructive plasticity, when the specific patterns of neural activity shape the specific parameters of the emerging response properties, followed by a late phase of permissive maturation, when sensory-driven activity merely serves to enhance the response properties already seeded in cortical circuits.

Synaptic and intrinsic mechanisms underlying development of cortical direction selectivity.

Modifications of synaptic inputs and cell-intrinsic properties both contribute to neuronal plasticity and development. To better understand these mechanisms, we undertook an intracellular analysis of the development of direction selectivity in the ferret visual cortex, which occurs rapidly over a few days after eye opening. We found strong evidence of developmental changes in linear spatiotemporal receptive fields of simple cells, implying alterations in circuit inputs. Further, this receptive field plasticity was accompanied by increases in near-spike-threshold excitability and input-output gain that resulted in dramatically increased spiking responses in the experienced state. Increases in subthreshold membrane responses induced by the receptive field plasticity and the increased input-output spiking gain were both necessary to explain the elevated firing rates in experienced ferrets. These results demonstrate that cortical direction selectivity develops through a combination of plasticity in inputs and in cell-intrinsic properties.