Disease progression and clinical outcomes in latent osteoarthritis phenotypes: Data from the Osteoarthritis Initiative.

The prevalence of knee osteoarthritis (OA) is widespread and the heterogeneous patient factors and clinical symptoms in OA patients impede developing personalized treatments for OA patients. In this study, we used unsupervised and supervised machine learning to organize the heterogeneity in knee OA patients and predict disease progression in individuals from the Osteoarthritis Initiative (OAI) dataset. We identified four distinct knee OA phenotypes using unsupervised learning that were defined by nutrition, disability, stiffness, and pain (knee and back) and were strongly related to disease fate. Interestingly, the absence of supplemental vitamins from an individual's diet was protective from disease progression. Moreover, we established a phenotyping tool and prognostic model from 5 variables (WOMAC disability score of the right knee, WOMAC total score of the right knee, WOMAC total score of the left knee, supplemental vitamins and minerals frequency, and antioxidant combination multivitamins frequency) that can be utilized in clinical practice to determine the risk of knee OA progression in individual patients. We also developed a prognostic model to estimate the risk for total knee replacement and provide suggestions for modifiable variables to improve long-term knee health. This combination of unsupervised and supervised data-driven tools provides a framework to identify knee OA phenotype in a clinical scenario and personalize treatment strategies.

Optimism persists when walking in unpredictable environments.

Humans continuously modulate their control strategies during walking based on their ability to anticipate disturbances. However, how people adapt and use motor plans to create stable walking in unpredictable environments is not well understood. Our purpose was to investigate how people adapt motor plans when walking in a novel and unpredictable environment. We evaluated the whole-body center of mass (COM) trajectory of participants as they performed repetitions of a discrete goal-directed walking task during which a laterally-directed force field was applied to the COM. The force field was proportional in magnitude to forward walking velocity and randomly directed towards either the right or left each trial. We hypothesized that people would adapt a control strategy to reduce the COM lateral deviations created by the unpredictable force field. In support of our hypothesis, we found that with practice the magnitude of COM lateral deviation was reduced by 28% (force field left) and 44% (force field right). Participants adapted two distinct unilateral strategies, implemented regardless of if the force field was applied to the right or to the left, that collectively created a bilateral resistance to the unpredictable force field. These strategies included an anticipatory postural adjustment to resist against forces applied to the left, and a more lateral first step to resist against forces applied to the right. In addition, during catch trials when the force field was unexpectedly removed, participants exhibited trajectories similar to baseline trials. These findings were consistent with an impedance control strategy that provides a robust resistance to unpredictable perturbations. However, we also found evidence that participants made predictive adaptations in response to their immediate experience that persisted for three trials. Due to the unpredictable nature of the force field, this predictive strategy would sometimes result in greater lateral deviations when the prediction was incorrect. The presence of these competing control strategies may have long term benefits by allowing the nervous system to identify the best overall control strategy to use in a novel environment.

People adapt a consistent center-of-mass trajectory in a novel force field.

During human walking the whole body center-of-mass (COM) trajectory may be a control objective, a goal the central nervous system uses to plan and regulate movement. Our previous observation, that after practice walking in a novel laterally directed force field people adapt a COM trajectory similar to their normal trajectory, supports this idea. However, our prior work only presented data demonstrating changes in COM trajectory in response to a single force field. To evaluate whether this phenomena is robust, in the present study we present new data demonstrating that people adapt their COM trajectory in a similar manner when the direction of the external force field is changed resulting in drastically different lower limb joint dynamics. Specifically, we applied a continuous, left-directed force field (in the previous experiment the force field was applied to the right) to the COM as participants performed repeated trials of a discrete walking task. We again hypothesized that with practice walking in the force field people would adapt a COM trajectory that was similar to their baseline performance and exhibit aftereffects, deviation of their COM trajectory in the opposite direction of force field, when the field was unexpectedly removed. These hypotheses were supported and suggest that participants formed an internal model to control their COM trajectory. Collectively these findings demonstrate that people adapt their gait patterns to anticipate consistent aspects of the external environment. These findings suggest that this response is robust to force fields applied in multiple directions that may require substantially different neural control.NEW & NOTEWORTHY With experience people adapted a predictive internal model to control their whole body center-of-mass walking trajectory that anticipated the disruptive laterally directed forces of a novel and consistent external environment. Collectively these findings demonstrate that adaptation of gait to anticipate consistent aspects of the external environment is a response that is robust to force fields in multiple directions that require substantially different lower limb dynamics and neural control.

Disease progression and clinical outcomes in latent osteoarthritis phenotypes: Data from the Osteoarthritis Initiative.

The prevalence of knee osteoarthritis (OA) is widespread and the heterogeneous patient factors and clinical symptoms in OA patients impede developing personalized treatments for OA patients. In this study, we used unsupervised and supervised machine learning to organize the heterogeneity in knee OA patients and predict disease progression in individuals from the Osteoarthritis Initiative (OAI) dataset. We identified four distinct knee OA phenotypes using unsupervised learning that were defined by nutrition, disability, stiffness, and pain (knee and back) and were strongly related to disease fate. Interestingly, the absence of supplemental vitamins from an individual's diet was protective from disease progression. Moreover, we established a phenotyping tool and prognostic model from 5 variables (WOMAC disability score of the right knee, WOMAC total score of the right knee, WOMAC total score of the left knee, supplemental vitamins and minerals frequency, and antioxidant combination multivitamins frequency) that can be utilized in clinical practice to determine the risk of knee OA progression in individual patients. We also developed a prognostic model to estimate the risk for total knee replacement and provide suggestions for modifiable variables to improve long-term knee health. This combination of unsupervised and supervised data-driven tools provides a framework to identify knee OA phenotype in a clinical scenario and personalize treatment strategies.

American Society of Biomechanics Journal of Biomechanics Award 2018: Adaptive motor planning of center-of-mass trajectory during goal-directed walking in novel environments.

To aid in the successful execution of goal-directed walking (discrete movement from a start location to an end target) the central nervous system forms a predictive motor plan. For the motor plan to be effective, it must be adapted in response to environmental changes. Despite motor planning being inherent to goal-directed walking, it is not understood how the nervous system adapts these plans to interact with changing environments. Our objective was to understand how people adapt motor plans of center of mass (COM) trajectory during goal-directed walking in response to a consistent change in environmental dynamics. Participants preformed a series of goal-directed walking trials in a novel environment created by a cable robot that applied a lateral force field to their COM. We hypothesized that participants would adapt to the environment by forming an internal model of their COM trajectory within the force field. Our findings support this hypothesis. Initially, we found COM trajectory significantly deviated in the same direction as the applied field, relative to baseline (no field) (p = 0.002). However, with practice in the field, COM trajectory adapted back to the baseline (p = 0.6). When we unexpectedly removed the field, participants demonstrated after-effects, COM trajectory deviated in the direction opposite of the field relative to baseline (p < 0.001). Our findings suggest that when performing a goal-directed walking task, people adapt a motor plan that predicts the COM trajectory that will emerge from the interaction between a specific set of motor commands and the external environment.