Kevin L. Kilgore

We demonstrate that five consecutive days of movement-related cortical stimulation can enhance corticospinal excitability, expand motor maps, and improve volitional motor unit recruitment in a person with severe incomplete spinal cord injury. These results support the brain’s adaptive capacity following spinal cord injury, despite limited motor drive to the muscle, and corroborate the potential to improve motor function by targeting higher-order networks during volitional motor intention with noninvasive brain stimulation.

Estimating blood pressure (BP) values from physiological signals (e.g., photoplethysmogram (PPG)) using deep learning models has recently received increased attention, yet challenges remain in terms of models' generalizability. Here, we propose taking a new approach by framing the problem as tracking the “changes” in BP over an interval, rather than directly estimating its value. Indeed, continuous monitoring of acute changes in BP holds promising implications for clinical applications (e.g., hypertensive emergencies). As a solution, we first present a self-contrastive masking (SCM) model, designed to perform pair-wise temporal comparisons within the input signal. We then leverage the proposed SCM model to introduce ΔBPNet, a model trained to detect elevations/drops greater than a given threshold in the systolic blood pressure (SBP) over an interval, from PPG. Using data from PulseDB, 1) we evaluate the performance of ΔBP-Net on previously unseen subjects, 2) we test ΔBP-Net's ability to generalize across domains by training and testing on different datasets, and 3) we compare the performance of ΔBP-Net with existing PPG-based BP-estimation models in detecting over-threshold SBP changes. Formulating the problem as a binary classification task (i.e., over-threshold SBP elevation/ drop or not), ΔBP-Net achieves 75.97%/73.19% accuracy on data from subjects unseen during training. Additionally, the proposed ΔBP-Net outperforms ΔSBP estimations derived from existing PPG-based BP-estimation methods. Overall, by shifting the focus from estimating the value of SBP to detecting overthreshold “changes” in SBP, this work introduces a new potential for using PPG in clinical BP monitoring, and takes a step forward in addressing the challenges related to the generalizability of PPG-based BP-estimation models.

Autonomic dysreflexia (AD) is a life-threatening and prevalent post-secondary health condition affecting individuals with spinal cord injury (SCI). Reliable and timely identification of AD requires continuous monitoring of changes in the blood pressure (BP), and alarming the patient of rapid BP elevations. However, conventional methods for identifying AD, including clinical observation and patient’s self-report, lack timeliness in addressing the immediate threat of acute hypertension, leading to cardiovascular damages in SCI patients. To address this issue, we target the problem of detecting onsets of rapid systolic BP (SBP) elevations from photoplethysmogram (PPG) signals, and present a batched Residual Network-Long Short Term Memory (ResNet-LSTM) deep learning model as a solution. Results indicate that the model achieves an accuracy of 74.38% and F-1 score of 72.99% on 356 leave-out testing subjects. With only one sensor required for providing input signals, the proposed method holds promise for implementing low-cost continuous monitoring systems, for the timely detection of onsets of AD in SCI patients.

Brain-machine interfaces have shown promise in extracting upper extremity movement intention from the thoughts of nonhuman primates and people with tetraplegia. Attempts to restore a user’s own hand and arm function have employed functional electrical stimulation (FES), but most work has restored discrete grasps. Little is known about how well FES can control continuous finger movements. Here, we use a low-power brain-controlled functional electrical stimulation (BCFES) system to restore continuous volitional control of finger positions to a monkey with a temporarily paralyzed hand. In a one-dimensional, continuous, finger-related target acquisition task, the monkey improved his success rate to 83% (1.5s median acquisition time) when using the BCFES system during temporary paralysis from 8.8% (9.5s median acquisition, equivalent to chance) when attempting to use his temporarily paralyzed hand. With two monkeys under general anesthesia, we found FES alone could control the monkeys’ fingers to rapidly reach targets in a median 1.1s but caused oscillation about the target. Finally, when attempting to perform a virtual two-finger continuous target acquisition task in brain-control mode following temporary hand paralysis, we found performance could be completely recovered by executing recalibrated feedback-intention training one time following temporary paralysis. These results suggest that BCFES can restore continuous finger function during temporary paralysis using existing low-power technologies and brain-control may not be the limiting performance factor in a BCFES neuroprosthesis.

The application of direct current (DC) produces a rapid and reversible nerve conduction block. However, prolonged injection of charge through a smooth platinum electrode has been found to cause damage to nervous tissue. This damage can be mitigated by incorporating high-capacitance materials (HCM) (e.g., activated carbon or platinum black) into electrode designs. HCMs increase the storage charge capacity (i.e., “Q value”) of capacitive devices. However, consecutive use of these HCM electrodes degrades their surface. This paper evaluates activated carbon and platinum black (PtB) electrode designs in vitro to determine the design parameters which improve surface stability of the HCMs. Electrode designs with activated carbon and PtB concentrations were stressed using soak, bend and vibration testing to simulate destructive in vivo environments. A Q value decrease represented the decreased stability of the electrode–HCM interface. Soak test results supported the long-term Q value stabilization (mean = 44.3 days) of HCM electrodes, and both HCMs displayed unique Q value changes in response to soaking. HCM material choices, Carbon Ink volume, and application of Nafion™ affected an electrode’s ability to resist Q value degradation. These results will contribute to future developments of HCM electrodes designed for extended DC application for in vivo nerve conduction block.

This paper presents a new solution that enables the use of transfer learning for cuff-less blood pressure (BP) monitoring via short duration of photoplethysmogram (PPG). The proposed method estimates BP with low computational budget by 1) creating images from segments of PPG via visibility graph (VG), hence, preserving the temporal information of the PPG waveform, 2) using pre-trained deep convolutional neural network (CNN) to extract feature vectors from VG images, and 3) solving for the weights and bias between the feature vectors and the reference BPs with ridge regression. Using the University of California Irvine (UCI) database consisting of 348 records, the proposed method achieves a best error performance of $0.00\pm 8.46$ mmHg for systolic blood pressure (SBP), and $-0.04\pm 5.36$ mmHg for diastolic blood pressure (DBP), respectively, in terms of the mean error (ME) and the standard deviation (SD) of error, ranking grade B for SBP and grade A for DBP under the British Hypertension Society (BHS) protocol. Our novel data-driven method offers a computationally-efficient end-to-end solution for rapid and user-friendly cuff-less PPG-based BP estimation.

Implantable motor neuroprostheses can restore functionality to individuals with neurological disabilities by electrically activating paralyzed muscles in coordinated patterns. The typical design of neuroprosthetic systems relies on a single multi-use device, but this limits the number of stimulus and sensor channels that can be practically implemented. To address this limitation, a modular neuroprosthesis, the “Networked Neuroprosthesis” (NNP), was developed. The NNP system is the first fully implanted modular neuroprosthesis that includes implantation of all power, signal processing, biopotential signal recording, and stimulating components. This paper describes the design of stimulation and recording modules, bench testing to verify stimulus outputs and appropriate filtering and recording, and validation that the components function properly while implemented in persons with spinal cord injury. The results of system testing demonstrated that the NNP was functional and capable of generating stimulus pulses and recording myoelectric, temperature, and accelerometer signals. Based on the successful design, manufacturing, and testing of the NNP System, multiple clinical applications are anticipated.

Individuals who sustain a traumatic spinal cord injury (SCI) often have a loss of multiple body systems. Significant functional improvement can be gained by individual SCI through the use of neur...