Computational systems that process multiple affective states may benefit from explicitly considering the interaction between the states to enhance their recognition performance. This work proposes the combination of a multi-label classifier, Circular Classifier Chain (CCC), with a multimodal classifier, Fusion using a Semi-Naive Bayesian classifier (FSNBC), to include explicitly the dependencies between multiple affective states during the automatic recognition process. This combination of classifiers is applied to a virtual rehabilitation context of post-stroke patients. We collected data from post-stroke patients, which include finger pressure, hand movements, and facial expressions during ten longitudinal sessions. Videos of the sessions were labelled by clinicians to recognize four states: tiredness, anxiety, pain, and engagement. Each state was modelled by the FSNBC receiving the information of finger pressure, hand movements, and facial expressions. The four FSNBCs were linked in the CCC to exploit the dependency relationships between the states. The convergence of CCC was reached by 5 iterations at most for all the patients. Results (ROC AUC) of CCC with the FSNBC are over 0.940 ± 0.045 (mean ± std. deviation) for the four states. Relationships of mutual exclusion between engagement and all the other states and co-occurrences between pain and anxiety were detected and discussed.
Summary. Given its virtually algorithmic process, the Fugl-Meyer Assessment (FMA) of motor recovery is prone to automatization reducing subjectivity, alleviating therapists' burden and collaterally reducing costs. Several attempts have been recently reported to achieve such automatization of the FMA. However, a cost-effective solution matching expert criteria is still unfulfilled, perhaps because these attempts are sensor-specific representation of the limb or have thus far rely on a trial and error strategy for building the underpinning computational model. Here, we propose a sensor abstracted representation. In particular, we improve previously reported results in the automatization of FMA by classifying a manifold embedded representation capitalizing on quaternions, and explore a wider range of classifiers. By enhancing the modeling, overall classification accuracy is boosted to 87% (mean: 82% ± 4.53: ) well over the maximum reported in literature thus far 51.03% (mean: 48.72 ± std: 2.10). The improved model brings automatic FMA closer to practical usage with implications for rehabilitation programs both in ward and at home.
Motor dexterity assessment is regularly performed in rehabilitation wards to establish patient status and automatization for such routinary task is sought. A system for automatizing the assessment of motor dexterity based on the Fugl-Meyer scale and with loose restrictions on sensing technologies is presented. The system consists of two main elements: 1) A data representation that abstracts the low level information obtained from a variety of sensors, into a highly separable low dimensionality encoding employing t-distributed Stochastic Neighbourhood Embedding, and, 2) central to this communication, a multi-label classifier that boosts classification rates by exploiting the fact that the classes corresponding to the individual exercises are naturally organized as a network. Depending on the targeted therapeutic movement class labels i.e. exercises scores, are highly correlated-patients who perform well in one, tends to perform well in related exercises-; and critically no node can be used as proxy of others - an exercise does not encode the information of other exercises. Over data from a cohort of 20 patients, the novel classifier outperforms classical Naive Bayes, random forest and variants of support vector machines (ANOVA: p < 0.001). The novel multi-label classification strategy fulfills an automatic system for motor dexterity assessment, with implications for lessening therapist's workloads, reducing healthcare costs and providing support for home-based virtual rehabilitation and telerehabilitation alternatives.
Poor understanding of brain recovery after injury, sparsity of evaluations and limited availability of healthcare services hinders the success of neurorehabilitation programs in rural communities. The availability of neuroimaging capacities in remote communities can alleviate this scenario supporting neurorehabilitation programs in remote settings. This research aims at building a multimodal EEG-fNIRS neuroimaging platform deployable to rural communities to support neurorehabilitation efforts. A Raspberry Pi 4 is chosen as the CPU for the platform responsible for presenting the neurorehabilitation stimuli, acquiring, processing and storing concurrent neuroimaging records as well as the proper synchronization between the neuroimaging streams. We present here two experiments to assess the feasibility and characterization of the Raspberry Pi as the core for a multimodal EEG-fNIRS neuroimaging platform; one over controlled conditions using a combination of synthetic and real data, and another from a full test during resting state. CPU usage, RAM usage and operation temperature were measured during the tests with mean operational records below 40% for CPU cores, 13.6% for memory and 58.85 • C for temperatures. Package loss was inexistent on synthetic data and negligible on experimental data. Current consumption can be satisfied with a 1000 mAh 5V battery. The Raspberry Pi 4 was able to cope with the required workload in conditions of operation similar to those needed to support a neurorehabilitation evaluation.
Validated clinical scales of functional dexterity of stroke patients provide only sparse and controlled observations of the neurorehabilitation process. Continuous naturalistic monitoring the progress during the rehabilitation therapy of outpatients remains unsatisfactorily resolved. We propose a new indicator of functional performance capitalizing on smart devices and the cloud services. The new index of limb usage balance (ILUB) derived from accelerometry data, provides an objective scalar that it is easy to estimate and interpret, and adequate for continuous uncontrolled monitoring. Three studies for the verification and validation of the index and accompanying platform are presented. We show that the index is unbiased to handedness dominance and provide preliminary evidence that it is appropriate for patients even during the subacute stage. The new index can complement clinical scales to observe the patient progress. CCS Concepts • Social and professional topics → Medical technologies; • Human-centered computing → Ubiquitous and mobile computing; Ubiquitous and mobile computing systems and tools; • Applied computing → Health care information systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.