Probabilistic Modelling of Gait for Robust Passive Monitoring in Daily Life.

Passive monitoring in daily life may provide valuable insights into a person's health throughout the day. Wearable sensor devices play a key role in enabling such monitoring in a non-obtrusive fashion. However, sensor data collected in daily life reflect multiple health and behavior-related factors together. This creates the need for a structured principled analysis to produce reliable and interpretable predictions that can be used to support clinical diagnosis and treatment. In this work we develop a principled modelling approach for free-living gait (walking) analysis. Gait is a promising target for non-obtrusive monitoring because it is common and indicative of many different movement disorders such as Parkinson's disease (PD), yet its analysis has largely been limited to experimentally controlled lab settings. To locate and characterize stationary gait segments in free-living using accelerometers, we present an unsupervised probabilistic framework designed to segment signals into differing gait and non-gait patterns. We evaluate the approach using a new video-referenced dataset including 25 PD patients with motor fluctuations and 25 age-matched controls, performing unscripted daily living activities in and around their own houses. Using this dataset, we demonstrate the framework's ability to detect gait and predict medication induced fluctuations in PD patients based on free-living gait. We show that our approach is robust to varying sensor locations, including the wrist, ankle, trouser pocket and lower back.

Real-Life Gait Performance as a Digital Biomarker for Motor Fluctuations: The Parkinson@Home Validation Study.

BACKGROUND: Wearable sensors have been used successfully to characterize bradykinetic gait in patients with Parkinson disease (PD), but most studies to date have been conducted in highly controlled laboratory environments. OBJECTIVE: This paper aims to assess whether sensor-based analysis of real-life gait can be used to objectively and remotely monitor motor fluctuations in PD. METHODS: The Parkinson@Home validation study provides a new reference data set for the development of digital biomarkers to monitor persons with PD in daily life. Specifically, a group of 25 patients with PD with motor fluctuations and 25 age-matched controls performed unscripted daily activities in and around their homes for at least one hour while being recorded on video. Patients with PD did this twice: once after overnight withdrawal of dopaminergic medication and again 1 hour after medication intake. Participants wore sensors on both wrists and ankles, on the lower back, and in the front pants pocket, capturing movement and contextual data. Gait segments of 25 seconds were extracted from accelerometer signals based on manual video annotations. The power spectral density of each segment and device was estimated using Welch's method, from which the total power in the 0.5- to 10-Hz band, width of the dominant frequency, and cadence were derived. The ability to discriminate between before and after medication intake and between patients with PD and controls was evaluated using leave-one-subject-out nested cross-validation. RESULTS: From 18 patients with PD (11 men; median age 65 years) and 24 controls (13 men; median age 68 years), ≥10 gait segments were available. Using logistic LASSO (least absolute shrinkage and selection operator) regression, we classified whether the unscripted gait segments occurred before or after medication intake, with mean area under the receiver operator curves (AUCs) varying between 0.70 (ankle of least affected side, 95% CI 0.60-0.81) and 0.82 (ankle of most affected side, 95% CI 0.72-0.92) across sensor locations. Combining all sensor locations did not significantly improve classification (AUC 0.84, 95% CI 0.75-0.93). Of all signal properties, the total power in the 0.5- to 10-Hz band was most responsive to dopaminergic medication. Discriminating between patients with PD and controls was generally more difficult (AUC of all sensor locations combined: 0.76, 95% CI 0.62-0.90). The video recordings revealed that the positioning of the hands during real-life gait had a substantial impact on the power spectral density of both the wrist and pants pocket sensor. CONCLUSIONS: We present a new video-referenced data set that includes unscripted activities in and around the participants' homes. Using this data set, we show the feasibility of using sensor-based analysis of real-life gait to monitor motor fluctuations with a single sensor location. Future work may assess the value of contextual sensors to control for real-world confounders.

Probabilistic Modelling for Unsupervised Analysis of Human Behaviour in Smart Cities.

The growth of urban areas in recent years has motivated a large amount of new sensor applications in smart cities. At the centre of many new applications stands the goal of gaining insights into human activity. Scalable monitoring of urban environments can facilitate better informed city planning, efficient security, regular transport and commerce. A large part of monitoring capabilities have already been deployed; however, most rely on expensive motion imagery and privacy invading video cameras. It is possible to use a low-cost sensor alternative, which enables deep understanding of population behaviour such as the Global Positioning System (GPS) data. However, the automated analysis of such low dimensional sensor data, requires new flexible and structured techniques that can describe the generative distribution and time dynamics of the observation data, while accounting for external contextual influences such as time of day or the difference between weekend/weekday trends. In this paper, we propose a novel time series analysis technique that allows for multiple different transition matrices depending on the data's contextual realisations all following shared adaptive observational models that govern the global distribution of the data given a latent sequence. The proposed approach, which we name Adaptive Input Hidden Markov model (AI-HMM) is tested on two datasets from different sensor types: GPS trajectories of taxis and derived vehicle counts in populated areas. We demonstrate that our model can group different categories of behavioural trends and identify time specific anomalies.

Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab.

The use of wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the accuracy achievable with such technology is highly reliant on separating the useful from irrelevant sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety of practical challenges, such as recording unexpected user behaviors. These behaviors often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab and affect the accuracy of the subsequent data analysis and scientific conclusions. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data that are sufficiently reliable for further analysis. Combining both parametric and nonparametric signal processing and machine learning techniques, we demonstrate that across 100 subjects and 300 clinimetric tests from three different types of behavioral clinimetric protocols, the system shows an average segmentation accuracy of around 90%. By extracting reliable sensor data, it is possible to strip the data of confounding factors in the environment that may threaten reproducibility and replicability.

What to Do When K-Means Clustering Fails: A Simple yet Principled Alternative Algorithm.

The K-means algorithm is one of the most popular clustering algorithms in current use as it is relatively fast yet simple to understand and deploy in practice. Nevertheless, its use entails certain restrictive assumptions about the data, the negative consequences of which are not always immediately apparent, as we demonstrate. While more flexible algorithms have been developed, their widespread use has been hindered by their computational and technical complexity. Motivated by these considerations, we present a flexible alternative to K-means that relaxes most of the assumptions, whilst remaining almost as fast and simple. This novel algorithm which we call MAP-DP (maximum a-posteriori Dirichlet process mixtures), is statistically rigorous as it is based on nonparametric Bayesian Dirichlet process mixture modeling. This approach allows us to overcome most of the limitations imposed by K-means. The number of clusters K is estimated from the data instead of being fixed a-priori as in K-means. In addition, while K-means is restricted to continuous data, the MAP-DP framework can be applied to many kinds of data, for example, binary, count or ordinal data. Also, it can efficiently separate outliers from the data. This additional flexibility does not incur a significant computational overhead compared to K-means with MAP-DP convergence typically achieved in the order of seconds for many practical problems. Finally, in contrast to K-means, since the algorithm is based on an underlying statistical model, the MAP-DP framework can deal with missing data and enables model testing such as cross validation in a principled way. We demonstrate the simplicity and effectiveness of this algorithm on the health informatics problem of clinical sub-typing in a cluster of diseases known as parkinsonism.