Lieven Billiet

Accelerometry-Based Activity Recognition and Assessment in Rheumatic and Musculoskeletal Diseases

One of the important aspects to be considered in rheumatic and musculoskeletal diseases is the patient’s activity capacity (or performance), defined as the ability to perform a task. Currently, it is assessed by physicians or health professionals mainly by means of a patient-reported questionnaire, sometimes combined with the therapist’s judgment on performance-based tasks. This work introduces an approach to assess the activity capacity at home in a more objective, yet interpretable way. It offers a pilot study on 28 patients suffering from axial spondyloarthritis (axSpA) to demonstrate its efficacy. Firstly, a protocol is introduced to recognize a limited set of six transition activities in the home environment using a single accelerometer. To this end, a hierarchical classifier with the rejection of non-informative activity segments has been developed drawing on both direct pattern recognition and statistical signal features. Secondly, the recognized activities should be assessed, similarly to the scoring performed by patients themselves. This is achieved through the interval coded scoring (ICS) system, a novel method to extract an interpretable scoring system from data. The activity recognition reaches an average accuracy of 93.5%; assessment is currently 64.3% accurate. These results indicate the potential of the approach; a next step should be its validation in a larger patient study.

Interval Coded Scoring Index with Interaction Effects

Scoring systems have been used since long in medical practice, but often they are based on experience rather than a structural approach. In literature, the interval coded scoring index (ICS) has been introduced as an alternative. It derives a scoring system from data using optimization techniques. This work discusses an extension, ICS*, that takes variable interactions into account. Furthermore, a study is performed to give insight into the new modelâ??s sensitivity to noise, the size of the data set and the number of non-informative variables. The study shows interactions can mostly be discovered robustly, even in the presence of noise and spurious variables. A final validation on two UCI data sets further indicates the quality of the approach.

Activity recognition for physical therapy: fusing signal processing features and movement patterns

This paper discusses the classification of activities in the context of physical therapy. Usually, specific standardized activities are subjectively assessed, often by means of a patient-reported questionnaire, to estimate a patients activity capacity, defined as the ability to execute a task. Automatic recognition of these activities is of vital importance for a more objective and quantitative approach to the problem. The proposed accelerometry-based algorithm merges standard signal processing features with information obtained from direct activity pattern matching using dynamic time warping (DTW) in a linear model. This study with 28 spondyloarthritis patients performing 10 activities shows the improvement in activity classification accuracy due to the fusion of the two approaches, up to 93.6%. This is a significant increase compared to similar models based on either of the approaches alone (p < 0.01). Although this paper mainly contributes to the activity recognition step, it also briefly discusses the advantages of the approach with regard to further automated evaluation of the recognized activities.

Interval Coded Scoring: a toolbox for interpretable scoring systems

Over the last decades, clinical decision support systems have been gaining importance. They help clinicians to make effective use of the overload of available information to obtain correct diagnoses and appropriate treatments. However, their power often comes at the cost of a black box model which cannot be interpreted easily. This interpretability is of paramount importance in a medical setting with regard to trust and (legal) responsibility. In contrast, existing medical scoring systems are easy to understand and use, but they are often a simplified rule-of-thumb summary of previous medical experience rather than a well-founded system based on available data. Interval Coded Scoring (ICS) connects these two approaches, exploiting the power of sparse optimization to derive scoring systems from training data. The presented toolbox interface makes this theory easily applicable to both small and large datasets. It contains two possible problem formulations based on linear programming or elastic net. Both allow to construct a model for a binary classification problem and establish risk profiles that can be used for future diagnosis. All of this requires only a few lines of code. ICS differs from standard machine learning through its model consisting of interpretable main effects and interactions. Furthermore, insertion of expert knowledge is possible because the training can be semi-automatic. This allows end users to make a tradeoff between complexity and performance based on cross-validation results and expert knowledge. Additionally, the toolbox offers an accessible way to assess classification performance via accuracy and the ROC curve, whereas the calibration of the risk profile can be evaluated via a calibration curve. Finally, the colour-coded model visualization has particular appeal if one wants to apply ICS manually on new observations, as well as for validation by experts in the specific application domains. The validity and applicability of the toolbox is demonstrated by comparing it to standard Machine Learning approaches such as Naive Bayes and Support VectorMachines for several reallife datasets. These case studies on medical problems show its applicability as a decision support system. ICS performs similarly in terms of classification and calibration. Its slightly lower performance is countered by its model simplicity which makes it the method of choice if interpretability is a key issue. Subjects Data Mining and Machine Learning, Data Science, Optimization Theory and Computation

Recognition of Physical Activities from a Single Arm-Worn Accelerometer: A Multiway Approach

In current clinical practice, functional limitations due to chronic musculoskeletal diseases are still being assessed subjectively, e.g., using questionnaires and function scores. Performance-based methods, on the other hand, offer objective insights. Hence, they recently attracted more interest as an additional source of information. This work offers a step towards the shift to performance-based methods by recognizing standardized activities from continuous readings using a single accelerometer mounted on a patient’s arm. The proposed procedure consists of two steps. Firstly, activities are segmented, including rejection of non-informative segments. Secondly, the segments are associated to predefined activities using a multiway pattern matching approach based on higher order discriminant analysis (HODA). The two steps are combined into a multi-layered framework. Experiments on data recorded from 39 patients with spondyloarthritis show results with a classification accuracy of 94.34% when perfect segmentation is assumed. Automatic segmentation has 89.32% overlap with this ideal scenario. However, combining both drops performance to 62.34% due to several badly-recognized subjects. Still, these results are shown to significantly outperform a more traditional pattern matching approach. Overall, the work indicates promising viability of the technique to automate recognition and, through future work, assessment, of functional capacity.

Single Trial Classification for Mobile BCI

Subspace methods have been applied in various application fields to obtain robust results. Using multilinear algebra, they can also be applied on structured tensorial data. This work combines this principle with the power of non-linear kernels to investigate its merits in single trial classification for a mobile BCI ERP classification task. The accuracy difference with regard to more conventional vector kernels is evaluated for sitting and walking condition, increasing training data set and averaging over multiple trials. The study concludes that in general, the tensorial approach does not yield any advantage, though it might for specific subjects.