Classification Accuracy of Hepatitis C Virus Infection Outcome: Data Mining Approach.

BACKGROUND: The dataset from genes used to predict hepatitis C virus outcome was evaluated in a previous study using a conventional statistical methodology. OBJECTIVE: The aim of this study was to reanalyze this same dataset using the data mining approach in order to find models that improve the classification accuracy of the genes studied. METHODS: We built predictive models using different subsets of factors, selected according to their importance in predicting patient classification. We then evaluated each independent model and also a combination of them, leading to a better predictive model. RESULTS: Our data mining approach identified genetic patterns that escaped detection using conventional statistics. More specifically, the partial decision trees and ensemble models increased the classification accuracy of hepatitis C virus outcome compared with conventional methods. CONCLUSIONS: Data mining can be used more extensively in biomedicine, facilitating knowledge building and management of human diseases.

Usability Evaluation of a Distributed User Interface Application for Visuomotor Organization Assessment.

BACKGROUND: This article describes the development and evaluation of a distributed user interface (DUI) application to assess visuomotor organization ability. This application enables therapists to evaluate the acquired brain injury (ABI) on patients, and patients, to perform the assessment on a touch screen while therapists can observe the assessment process in real time on a separated monitor without interfering patients during the process as in traditional methodologies employing physical elements. OBJECTIVES: The main goal of this research is the evaluation of the quality in use of DUIs in the Pegboard Construction assessment with patients with ABI from the therapist perspective in the area of occupational therapy. METHODS: To evaluate our system, we have performed a usability evaluation following the ISO/IEC 25010 and ISO/IEC 25062 standards to evaluate software usability and quality and it was conducted in collaboration with therapists and psychologists that have previously worked with people with ABI in diagnostic and assessment tasks. RESULTS: We show the results of the evaluation collected in a table that shows the completeness rate for each user for both, assisted (i.e., the percentage of tasks where participants performed with test director assistance) and unassisted tasks (i.e., the percentage of tasks where participants completed tasks autonomously), the total time participants required to complete proposed tasks, the number of mistakes participants performed during the session, and the number of assists they required to finish proposed tasks. In addition, we also evaluated the user satisfaction regarding our application using the system usability scale. CONCLUSION: The use of information technologies in this field enables therapists to perform these evaluations in a simpler, efficient, and automated way. This proposal enables patients to perform the assessment as it is performed traditionally using paper providing them with a touch screen in which they can easily insert a set of pins into the holes. The usability evaluation of the proposal meets the appropriate design standards for applications of this type, and this is demonstrated by the high degree of satisfaction of the participants.

Exponential synchronization of semi-Markovian coupled neural networks with mixed delays via tracker information and quantized output controller.

In this paper, exponential synchronization of semi-Markovian coupled neural networks (NNs) with bounded time-varying delay and infinite-time distributed delay (mixed delays) is investigated. Since semi-Markov switching occurs by time-varying probability, it is difficult to capture its precise switching signal. To overcome this difficulty, a tracker is used to track the switching information with some accuracy. Then a quantized output controller (QOC) is designed by using the tracked information. Novel Lyapunov-Krasovskii functionals (LKFs) with negative terms and delay-partitioning approach, which reduce the conservativeness of the obtained results, are utilized to obtain LMI conditions ensuring the exponential synchronization. Moreover, an algorithm is proposed to design the control gains. Our results include both those derived by mode-dependent and mode-independent control schemes as special cases. Finally, numerical simulations validate the effectiveness of the methodology.

Scoping Review of Systems to Train Psychomotor Skills in Hearing Impaired Children.

OBJECTIVES: The aim of this work is to provide a scoping review to compile and classify the systems helping train and enhance psychomotor skills in hearing impaired (HI) children. METHODS: Based on an exhaustive review on psychomotor deficits in HI children, the procedure used to carry out a scoping review was: select keywords and identify synonyms, select databases and prepare the queries using keywords, analyze the quality of the works found using the PEDro Scale, classify the works based on psychomotor competences, analyze the interactive systems (e.g., sensors), and the achieved results. RESULTS: Thirteen works were found. These works used a variety of sensors and input devices such as cameras, contact sensors, touch screens, mouse and keyboard, tangible objects, haptic and virtual reality (VR) devices. CONCLUSIONS: From the research it was possible to contextualize the deficits and psychomotor problems of HI children that prevent their normal development. Additionally, from the analysis of different proposals of interactive systems addressed to this population, it was possible to establish the current state of the use of different technologies and how they contribute to psychomotor rehabilitation.

Performance on naturalistic virtual reality tasks depends on global cognitive functioning as assessed via traditional neurocognitive tests.

This investigation sought to understand whether performance in naturalistic virtual reality tasks for cognitive assessment relates to the cognitive domains that are supposed to be measured. The Shoe Closet Test (SCT) was developed based on a simple visual search task involving attention skills, in which participants have to match each pair of shoes with the colors of the compartments in a virtual shoe closet. The interaction within the virtual environment was made using the Microsoft Kinect. The measures consisted of concurrent paper-and-pencil neurocognitive tests for global cognitive functioning, executive functions, attention, psychomotor ability, and the outcomes of the SCT. The results showed that the SCT correlated with global cognitive performance as measured with the Montreal Cognitive Assessment (MoCA). The SCT explained one third of the total variance of this test and revealed good sensitivity and specificity in discriminating scores below one standard deviation in this screening tool. These findings suggest that performance of such functional tasks involves a broad range of cognitive processes that are associated with global cognitive functioning and that may be difficult to isolate through paper-and-pencil neurocognitive tests.

Technologies Solutions Schemes for Patients' Rehabilitation. Methodologies, Models and Algorithms.

OBJECTIVE: The present editorial is part of the focus theme of Methods of Information in Medicine entitled "Technologies solutions schemes for Patients' Rehabilitation: Methodologies, Models and Algorithms". The focus theme aims to present nowadays most innovative solutions to improve patients' rehabilitation by applying and using sophisticated and pioneering Information and Communication Technologies (ICT) and human factors. METHODS: The focus theme explores the different existent research works and tools used, applied and developed for incapable people in terms of rehabilitation and health care, as to look into the extent methodologies, models and algorithms by means of ICT in this process. RESULTS: The focus theme lists a group of research works, which are presenting various solutions using ICT systems to improve the rehabilitation process of people with physical incapacities and to help them in carrying out their daily life.

Recognition of familiar people with a mobile cloud architecture for Alzheimer patients.

PURPOSE: This article aims to the evaluation of a prototypal assistive technology for Alzheimer's disease (AD) patients that helps them to remember personal details of familiar people they meet in their daily lives. METHOD: An architecture is proposed for a personal information system powered by face recognition, where the main AD patient's interaction is performed in a smart watch device and the face recognition is carried out on the Cloud. A prototype was developed to perform some tests in a real-life scenario. RESULTS: The prototype showed correct results as a personal information system based on face recognition. However, usability flaws were identified in the interaction with the smart watch. CONCLUSIONS: Our architecture showed correct performance and we realized that it could be introduced in other fields, apart from assistive technology. However, when being targeted to patients with dementia some usability problems appeared, such as difficulties to read information in a small screen or take a proper photo. These problems should be addressed in further research. Implications for Rehabilitation This article presents a prototypal assistive technology for Alzheimer's disease (AD) patients. It targets AD patients to recognize their familiars, especially in medium-advanced stages of the disease. Analysing pictures taken by a smart watch, which the patient carries, the person in front is recognized and information about him is sent to the watch. This technology enables patients to have all the information of any close person, as a remainder, easing their daily lives, improving their self-esteem and stimulating the patient with novel technology.

Virtual rehabilitation for multiple sclerosis using a kinect-based system: randomized controlled trial.

BACKGROUND: The methods used for the motor rehabilitation of patients with neurological disorders include a number of different rehabilitation exercises. For patients who have been diagnosed with multiple sclerosis (MS), the performance of motor rehabilitation exercises is essential. Nevertheless, this rehabilitation may be tedious, negatively influencing patients' motivation and adherence to treatment. OBJECTIVE: We present RemoviEM, a system based on Kinect that uses virtual reality (VR) and natural user interfaces (NUI) to offer patients with MS an intuitive and motivating way to perform several motor rehabilitation exercises. It offers therapists a new motor rehabilitation tool for the rehabilitation process, providing feedback on the patient's progress. Moreover, it is a low-cost system, a feature that can facilitate its integration in clinical rehabilitation centers. METHODS: A randomized and controlled single blinded study was carried out to assess the influence of a Kinect-based virtual rehabilitation system on the balance rehabilitation of patients with MS. This study describes RemoviEM and evaluates its effectiveness compared to standard rehabilitation. To achieve this objective, a clinical trial was carried out. Eleven patients from a MS association participated in the clinical trial. The mean age was 44.82 (SD 10.44) and the mean time from diagnosis (years) was 9.77 (SD 10.40). Clinical effectiveness was evaluated using clinical balance scales. RESULTS: Significant group-by-time interaction was detected in the scores of the Berg Balance Scale (P=.011) and the Anterior Reach Test in standing position (P=.011). Post-hoc analysis showed greater improvement in the experimental group for these variables than in the control group for these variables. The Suitability Evaluation Questionnaire (SEQ) showed good results in usability, acceptance, security, and safety for the evaluated system. CONCLUSIONS: The results obtained suggest that RemoviEM represents a motivational and effective alternative to traditional motor rehabilitation for MS patients. These results have encouraged us to improve the system with new exercises, which are currently being developed.