Recent advancements in deep learning have produced significant progress in markerless human pose estimation, making it possible to estimate human kinematics from single camera videos without the need for reflective markers and specialized labs equipped with motion capture systems. Such algorithms have the potential to enable the quantification of clinical metrics from videos recorded with a handheld camera. Here we used DeepLabCut, an open-source framework for markerless pose estimation, to fine-tune a deep network to track 5 body keypoints (hip, knee, ankle, heel, and toe) in 82 below-waist videos of 8 patients with stroke performing overground walking during clinical assessments. We trained the pose estimation model by labeling the keypoints in 2 frames per video and then trained a convolutional neural network to estimate 5 clinically relevant gait parameters (cadence, double support time, swing time, stance time, and walking speed) from the trajectory of these keypoints. These results were then compared to those obtained from a clinical system for gait analysis (GAITRite®, CIR Systems). Absolute accuracy (mean error) and precision (standard deviation of error) for swing, stance, and double support time were within 0.04 ± 0.11 s; Pearson’s correlation with the reference system was moderate for swing times (r = 0.4–0.66), but stronger for stance and double support time (r = 0.93–0.95). Cadence mean error was −0.25 steps/min ± 3.9 steps/min (r = 0.97), while walking speed mean error was −0.02 ± 0.11 m/s (r = 0.92). These preliminary results suggest that single camera videos and pose estimation models based on deep networks could be used to quantify clinically relevant gait metrics in individuals poststroke, even while using assistive devices in uncontrolled environments. Such development opens the door to applications for gait analysis both inside and outside of clinical settings, without the need of sophisticated equipment.

Despite the common focus of gait in rehabilitation, there are few tools that allow quantitatively characterizing gait in the clinic. We recently described an algorithm, trained on a large dataset from our clinical gait analysis laboratory, which produces accurate cycle-by-cycle estimates of spatiotemporal gait parameters including step timing and walking velocity. Here, we demonstrate this system generalizes well to clinical care with a validation study on prosthetic users seen in therapy and outpatient clinics. Specifically, estimated walking velocity was similar to annotated 10-m walking velocities, and cadence and foot contact times closely mirrored our wearable sensor measurements. Additionally, we found that a 2D keypoint detector pretrained on largely able-bodied individuals struggles to localize prosthetic joints, particularly for those individuals with more proximal or bilateral amputations, but after training a prosthetic-specific joint detector video-based gait analysis also works on these individuals. Further work is required to validate the other outputs from our algorithm including sagittal plane joint angles and step length. Code for the gait transformer and the trained weights are available at https://github.com/peabody124/GaitTransformer.

Marker-based Optical Motion Capture (OMC) paired with biomechanical modeling is currently considered the most precise and accurate method for measuring human movement kinematics. However, combining differentiable biomechanical modeling with Markerless Motion Capture (MMC) offers a promising approach to motion capture in clinical settings, requiring only minimal equipment, such as webcams, and minimal effort for data collection. This study compares key kinematic outcomes from biomechanically modeled MMC and OMC data in 15 individuals with stroke performing the drinking task, a functional task recommended for assessing upper limb movement quality. We observed a high level of agreement in kinematic trajectories between MMC and OMC, as indicated by high correlations (median r > 0.95 for the majority of kinematic trajectories) and median RMSE (root mean squared error) values ranging from 2∘-5∘ for joint angles, 0.04 m/s for end-effector velocity, and 6mm for trunk displacement. Trial-to-trial biases between OMC and MMC were consistent within participant sessions, with interquartile ranges of bias around 1-3∘ for joint angles, 0.01m/s in end-effector velocity, and approximately 3mm for trunk displacement. Our findings indicate that our MMC for arm tracking is approaching the accuracy of marker-based methods, supporting its potential for use in clinical settings. MMC could provide valuable insights into movement rehabilitation after stroke, potentially enhancing the effectiveness of rehabilitation strategies.

Sensory data about most natural task-relevant variables are entangled with task-irrelevant nuisance variables. The neurons that encode these relevant signals typically constitute a nonlinear population code. Here we present a theoretical framework for quantifying how the brain uses or decodes its nonlinear information. Our theory obeys fundamental mathematical limitations on information content inherited from the sensory periphery, describing redundant codes when there are many more cortical neurons than primary sensory neurons. The theory predicts that if the brain uses its nonlinear population codes optimally, then more informative patterns should be more correlated with choices. More specifically, the theory predicts a simple, easily computed quantitative relationship between fluctuating neural activity and behavioral choices that reveals the decoding efficiency. This relationship holds for optimal feedforward networks of modest complexity, when experiments are performed under natural nuisance variation. We analyze recordings from primary visual cortex of monkeys discriminating the distribution from which oriented stimuli were drawn, and find these data are consistent with the hypothesis of near-optimal nonlinear decoding.

Minimally invasive, high-bandwidth brain-computer-interface (BCI) devices can revolutionize human applications. With orders-of-magnitude improvements in volumetric efficiency over other BCI technologies, we developed a 50-μm-thick, mechanically flexible micro-electrocorticography (μECoG) BCI, integrating a 256×256 array of electrodes, signal processing, data telemetry, and wireless powering on a single complementary metal-oxide-semiconductor (CMOS) substrate containing 65,536 recording channels, from which we can simultaneously record a selectable subset of up to 1024 channels at a given time. Fully implanted below the dura, our chip is wirelessly powered, communicating bi-directionally with an external relay station outside the body. We demonstrated chronic, reliable recordings for up to two weeks in pigs and up to two months in behaving non-human primates from somatosensory, motor, and visual cortices, decoding brain signals at high spatiotemporal resolution.