Freezing of gait assessment with inertial measurement units and deep learning: effect of tasks, medication states, and stops.

BACKGROUND: Freezing of gait (FOG) is an episodic and highly disabling symptom of Parkinson's Disease (PD). Traditionally, FOG assessment relies on time-consuming visual inspection of camera footage. Therefore, previous studies have proposed portable and automated solutions to annotate FOG. However, automated FOG assessment is challenging due to gait variability caused by medication effects and varying FOG-provoking tasks. Moreover, whether automated approaches can differentiate FOG from typical everyday movements, such as volitional stops, remains to be determined. To address these questions, we evaluated an automated FOG assessment model with deep learning (DL) based on inertial measurement units (IMUs). We assessed its performance trained on all standardized FOG-provoking tasks and medication states, as well as on specific tasks and medication states. Furthermore, we examined the effect of adding stopping periods on FOG detection performance. METHODS: Twelve PD patients with self-reported FOG (mean age 69.33 ± 6.02 years) completed a FOG-provoking protocol, including timed-up-and-go and 360-degree turning-in-place tasks in On/Off dopaminergic medication states with/without volitional stopping. IMUs were attached to the pelvis and both sides of the tibia and talus. A temporal convolutional network (TCN) was used to detect FOG episodes. FOG severity was quantified by the percentage of time frozen (%TF) and the number of freezing episodes (#FOG). The agreement between the model-generated outcomes and the gold standard experts' video annotation was assessed by the intra-class correlation coefficient (ICC). RESULTS: For FOG assessment in trials without stopping, the agreement of our model was strong (ICC (%TF) = 0.92 [0.68, 0.98]; ICC(#FOG) = 0.95 [0.72, 0.99]). Models trained on a specific FOG-provoking task could not generalize to unseen tasks, while models trained on a specific medication state could generalize to unseen states. For assessment in trials with stopping, the agreement of our model was moderately strong (ICC (%TF) = 0.95 [0.73, 0.99]; ICC (#FOG) = 0.79 [0.46, 0.94]), but only when stopping was included in the training data. CONCLUSION: A TCN trained on IMU signals allows valid FOG assessment in trials with/without stops containing different medication states and FOG-provoking tasks. These results are encouraging and enable future work investigating automated FOG assessment during everyday life.

Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks.

BACKGROUND: Freezing of gait (FOG) is a common and debilitating gait impairment in Parkinson's disease. Further insight into this phenomenon is hampered by the difficulty to objectively assess FOG. To meet this clinical need, this paper proposes an automated motion-capture-based FOG assessment method driven by a novel deep neural network. METHODS: Automated FOG assessment can be formulated as an action segmentation problem, where temporal models are tasked to recognize and temporally localize the FOG segments in untrimmed motion capture trials. This paper takes a closer look at the performance of state-of-the-art action segmentation models when tasked to automatically assess FOG. Furthermore, a novel deep neural network architecture is proposed that aims to better capture the spatial and temporal dependencies than the state-of-the-art baselines. The proposed network, termed multi-stage spatial-temporal graph convolutional network (MS-GCN), combines the spatial-temporal graph convolutional network (ST-GCN) and the multi-stage temporal convolutional network (MS-TCN). The ST-GCN captures the hierarchical spatial-temporal motion among the joints inherent to motion capture, while the multi-stage component reduces over-segmentation errors by refining the predictions over multiple stages. The proposed model was validated on a dataset of fourteen freezers, fourteen non-freezers, and fourteen healthy control subjects. RESULTS: The experiments indicate that the proposed model outperforms four state-of-the-art baselines. Moreover, FOG outcomes derived from MS-GCN predictions had an excellent (r = 0.93 [0.87, 0.97]) and moderately strong (r = 0.75 [0.55, 0.87]) linear relationship with FOG outcomes derived from manual annotations. CONCLUSIONS: The proposed MS-GCN may provide an automated and objective alternative to labor-intensive clinician-based FOG assessment. Future work is now possible that aims to assess the generalization of MS-GCN to a larger and more varied verification cohort.

Automating the Calibration of Visible Light Positioning Systems.

Visible light positioning is one of the most popular technologies used for indoor positioning research. Like many other technologies, a calibration procedure is required before the system can be used. More specifically, the location and identity of each light source need to be determined. These parameters are often measured manually, which can be a labour-intensive and error-prone process. Previous work proposed the use of a mobile robot for data collection. However, this robot still needed to be steered by a human operator. In this work, we significantly improve the efficiency of calibration by proposing two novel methods that allow the robot to autonomously collect the required calibration data. In postprocessing, the necessary system parameters can be calculated from these data. The first novel method will be referred to as semi-autonomous calibration, and requires some prior knowledge of the LED locations and a map of the environment. The second, fully-autonomous calibration procedure requires no prior knowledge. Simulation results show that the two novel methods are both more accurate than manual steering. Fully autonomous calibration requires approximately the same amount of time to complete, whereas semi-autonomous calibration is significantly faster.

Modelling and identification of characteristic kinematic features preceding freezing of gait with convolutional neural networks and layer-wise relevance propagation.

BACKGROUND: Although deep neural networks (DNNs) are showing state of the art performance in clinical gait analysis, they are considered to be black-box algorithms. In other words, there is a lack of direct understanding of a DNN's ability to identify relevant features, hindering clinical acceptance. Interpretability methods have been developed to ameliorate this concern by providing a way to explain DNN predictions. METHODS: This paper proposes the use of an interpretability method to explain DNN decisions for classifying the movement that precedes freezing of gait (FOG), one of the most debilitating symptoms of Parkinson's disease (PD). The proposed two-stage pipeline consists of (1) a convolutional neural network (CNN) to model the reduction of movement present before a FOG episode, and (2) layer-wise relevance propagation (LRP) to visualize the underlying features that the CNN perceives as important to model the pathology. The CNN was trained with the sagittal plane kinematics from a motion capture dataset of fourteen PD patients with FOG. The robustness of the model predictions and learned features was further assessed on fourteen PD patients without FOG and fourteen age-matched healthy controls. RESULTS: The CNN proved highly accurate in modelling the movement that precedes FOG, with 86.8% of the strides being correctly identified. However, the CNN model was unable to model the movement for one of the seven patients that froze during the protocol. The LRP interpretability case study shows that (1) the kinematic features perceived as most relevant by the CNN are the reduced peak knee flexion and the fixed ankle dorsiflexion during the swing phase, (2) very little relevance for FOG is observed in the PD patients without FOG and the healthy control subjects, and (3) the poor predictive performance of one subject is attributed to the patient's unique and severely flexed gait signature. CONCLUSIONS: The proposed pipeline can aid clinicians in explaining DNN decisions in clinical gait analysis and aid machine learning practitioners in assessing the generalization of their models by ensuring that the predictions are based on meaningful kinematic features.

Calibration of Visible Light Positioning Systems with a Mobile Robot.

Most indoor positioning systems require calibration before use. Fingerprinting requires the construction of a signal strength map, while ranging systems need the coordinates of the beacons. Calibration approaches exist for positioning systems that use Wi-Fi, radio frequency identification or ultrawideband. However, few examples are available for the calibration of visible light positioning systems. Most works focused on obtaining the channel model parameters or performed a calibration based on known receiver locations. In this paper, we describe an improved procedure that uses a mobile robot for data collection and is able to obtain a map of the environment with the beacon locations and their identities. Compared to previous work, the error is almost halved. Additionally, this approach does not require prior knowledge of the number of light sources or the receiver location. We demonstrate that the system performs well under a wide range of lighting conditions and investigate the influence of parameters such as the robot trajectory, camera resolution and field of view. Finally, we also close the loop between calibration and positioning and show that our approach has similar or better accuracy than manual calibration.

Meropenem Stability in Human Plasma at -20 °C: Detailed Assessment of Degradation.

There are concerns about the stability of meropenem in plasma samples, even when frozen at -20 °C. Previous smaller studies suggested significant degradation of meropenem at -20 °C after 3-20 days. However, in several recent clinical studies, meropenem plasma samples were still stored at -20 °C, or the storage temperature and/or time were not mentioned in the paper. The aim of this study was to describe and model meropenem degradation in human plasma at -20 °C over 1 year. Stability of meropenem in human plasma at -20 °C was investigated at seven concentrations (0.44, 4.38, 17.5, 35.1, 52.6, 70.1, and 87.6 mg/L) representative for the range of relevant concentrations encountered in clinical practice. For each concentration, samples were stored for 0, 7, 14, 21, 28, 42, 56, 70, 84, 112, 140, 168, 196, 224, 252, 280, 308, 336, and 364 days at -20 °C before being transferred to -80 °C until analysis. Degradation was modeled using polynomial regression analysis and artificial neural network (ANN). Meropenem showed significant degradation over time in human plasma when stored at -20 °C. Degradation was present over the whole concentration range and increased with higher concentrations until a concentration of 35.1 mg/L. Both models showed accurate prediction of meropenem degradation. In conclusion, this study provides detailed insights into the concentration-dependent degradation of meropenem in human plasma stored at -20 °C over 1 year. Meropenem in human plasma is shown to be stable at least up to approximately 80 days when stored at -20 °C. The polynomial model allows calculating original meropenem concentrations in samples stored for a known period of time at -20 °C.

Dynamic Semantic World Models and Increased Situational Awareness for Highly Automated Inland Waterway Transport.

Automated surface vessels must integrate many tasks and motions at the same time. Moreover, vessels as well as monitoring and control services need to react to physical disturbances, to dynamically allocate software resources available within a particular environment, and to communicate with various other actors in particular navigation and traffic situations. In this work, the responsibility for the situational awareness is given to a mediator that decides how: 1) to assess the impact of the actual physical environment on the quality and performance of the ongoing task executions; 2) to make sure these tasks satisfy the system requirements; and 3) to be robust against disturbances. This paper proposes a set of semantic world models within the context of inland waterway transport, and discusses policies and methodologies to compose, use, and connect these models. Model-conform entities and relations are composed dynamically, that is, corresponding to the opportunities and challenges offered by the actual situation. The semantic world models discussed in this work are divided into two main categories: 1) the semantic description of a vessel's own properties and relationships, called the internal world model, or body model, and 2) the semantic description of its local environment, called the external world model, or map. A range of experiments illustrate the potential of using such models to decide the reactions of the application at runtime. Furthermore, three dynamic, context-dependent, ship domains are integrated in the map as two-dimensional geometric entities around a moving vessel to increase the situational awareness of automated vessels. Their geometric representations depend on the associated relations; for example, with: 1) the motion of the vessel, 2) the actual, desired, or hypothesised tasks, 3) perception sensor information, and 4) other geometries, e.g., features from the Inland Electronic Navigational Charts. The ability to unambiguously understand the environmental context, as well as the motion or position of surrounding entities, allows for resource-efficient and straightforward control decisions. The semantic world models facilitate knowledge sharing between actors, and significantly enhance explainability of the actors' behaviour and control decisions.

A data-driven approach for detecting gait events during turning in people with Parkinson's disease and freezing of gait.

BACKGROUND: Manual annotation of initial contact (IC) and end contact (EC) is a time consuming process. There are currently no robust techniques available to automate this process for Parkinson's disease (PD) patients with freezing of gait (FOG). OBJECTIVE: To determine the validity of a data-driven approach for automated gait event detection. METHODS: 15 freezers were asked to complete several straight-line and 360 degree turning trials in a 3D gait laboratory during the off-period of their medication cycle. Trials that contained a freezing episode were indicated as freezing trials (FOG) and trials without a freezing episode were termed as functional gait (FG). Furthermore, the highly varied gait data between onset and termination of a FOG episode was excluded. A Temporal Convolutional Neural network (TCN) was trained end-to-end with lower extremity kinematics. A Bland-Altman analysis was performed to evaluate the agreement between the results of the proposed model and the manual annotations. RESULTS: For FOG-trials, F1 scores of 0.995 and 0.992 were obtained for IC and EC, respectively. For FG-trials, F1 scores of 0.997 and 0.999 were obtained for IC and EC, respectively. The Bland-Altman plots indicated excellent timing agreement, with on average 39% and 47% of the model predictions occurring within 10 ms from the manual annotations for FOG-trials and FG-trials, respectively. SIGNIFICANCE: These results indicate that our data-driven approach for detecting gait events in PD patients with FOG is sufficiently accurate and reliable for clinical applications.

In-Depth Analysis of Unmodulated Visible Light Positioning Using the Iterated Extended Kalman Filter.

Indoor positioning with visible light has become increasingly important in recent years. Usually, light sources are modulated at high speeds in order to wirelessly transmit data from the fixtures to a receiver. The accuracy of such systems can range from a few decimeters to a few centimeters. However, additional modulation hardware is required for every light source, thereby increasing cost and system complexity. This paper investigates the use of unmodulated light for indoor positioning. Contrary to previous work, a Kalman filter is used instead of a particle filter to decrease the computational load. As a result, the update rate of position estimation can be higher. Additionally, more resources could be made available for other tasks (e.g., path planning for autonomous robots). We evaluated the performance of our proposed approach through simulations and experiments. The accuracy depends on a number of parameters, but is generally lower than 0.5 m. Moreover, temporary occlusion of the receiver can be compensated in most cases.

Stability of Drugs Used in Helicopter Air Medical Emergency Services: An Exploratory Study.

OBJECTIVE: Transportation by air exposes drugs used in emergency medical services to vibrations. The aim of the study was to determine whether or not vibrations caused by a helicopter induce the degradation of 5 drugs used in this setting. METHODS: A longitudinal study in an operating medical helicopter along with a worst case was conducted. The studied drugs were 3 drugs labeled for refrigeration (cisatracurium, lorazepam, and succinylcholine) and 2 albumin solutions (human albumin 4% and 20%). These drugs were stored for 4 months according to the following conditions: inside a helicopter, worst case with exposure to extreme vibrations, at room temperature, and according to manufacturers' recommendations. Samples were analyzed with validated high-performance liquid chromatography assay methods. A drug was considered stable if the remaining drug content was above 90% of the label claim. Except for the albumin solutions, visual inspection was used to determine instability by the formation of aggregates. RESULTS: Only the samples stored at room temperature became unstable after 4 months. No difference in extreme foaming was observed in the albumin solutions. CONCLUSIONS: These data suggest that the effect of degradation of drugs caused by vibrations is negligible. Temperature was observed as the main cause of drug degradation.