Validation of inertial measurement units for the assessment of trunk control in subjects with spinal cord injury.

BACKGROUND: Trunk control (TC) constitutes one of the main objectives in the rehabilitation of people with a spinal cord injury (SCI), but there are few clinically validated tests to assess it. Accelerometers have been proposed as sensitive and suitable procedures to assess TC. OBJECTIVE: To evaluate test-retest reliability, construct and criterion validity of accelerometer parameters to assess TC in people with SCI. METHODS: A cross-sectional study of simultaneous application of Clinical Trunk Control Test (CTCT) and accelerometer evaluation was conducted. Accelerometers were placed on the trunks of 27 people with SCI and 15 people without SCI. Reliability was assessed by three repeated measures in random order of selected static and dynamic TC tasks. Acceleration on three axes was analyzed using five metrics. Criterion validity was assessed by analyzing correlation of acceleration to CTCT scores. Construct validity was assessed by analyzing capacity of inertial measurement units (IMU) to differentiate individual's characteristics, ASIA Impairment scale, gait capacity, level of TC, and neurological level of injury. RESULTS: Reliable IMU data were obtained in people with SCI and without SCI, of all accelerometer axes, metrics, and tested items of the CTCT. Reliability of acceleration decreases with the increasing demand for TC tasks. Ten acceleration parameters showed construct and criterion validity. CONCLUSION: Accelerometer parameters are reliable, valid, and sensitive to evaluate TC in people with SCI. SIGNIFICANCE: A set of IMU parameters were validated as reliable and valid measures to evaluate TC, which could be useful for the assessment of progression of people with SCI and clinical interventions.

Aplicación de Redes Neuronales Artificiales para la Clasificación de Actividades de la Vida Diaria en Sujetos con Enfermedad de Párkinson / Classification of Daily Living Activities in subjects with Parkinson's Disease using Artificial Neural Networks

Resumen El presente trabajo es un seguimiento a la propuesta para la contribución con especialistas en la salud para enriquecer los sistemas de seguimiento y apoyo en pacientes con Enfermedad de Párkinson a través de la clasificación de actividades de la vida diaria (AVDs) utilizando Redes Neuronales Artificiales programadas en lenguaje Python. El método propuesto de aprendizaje supervisado permitió la clasificación de 6 AVDs mediante 22 señales procedentes de haber aplicado Análisis de Componentes Principales; conformando la base de datos utilizada para entrenar un Perceptrón Multicapa, logrando un acercamiento a la clasificación con el 93% de medida F1-score. El presente estudio demuestra la versatilidad de las RNA basadas en MLP combinadas con la técnica de PCA, pues incluso en una base de datos desbalanceada como la utilizada permite alcanzar excelentes valores en la medida F1-score. El uso de Inteligencia Artificial y otras herramientas aplicadas en este trabajo pueden eventualmente ayudar a especialistas a desempeñar una evaluación más certera en el monitoreo de la rehabilitación en pacientes con enfermedad de Párkinson mejorando los registros y así evitar subjetividad en la interpretación de los resultados del tratamiento.

Abstract This paper is a proposal to contribute with health specialists to enrich the follow-up and support systems in patients with Parkinson's by identifying and classifying Daily Living Activities (DLAs) using Artificial Neural Networks programmed in Python language. The proposed method of supervised learning allowed the classification of 6 DLAs through 22 signals obtained from the application of Principal Component Analysis, creating a database used to train a Multilayer Perceptron. This model achieved an approximation of classification with 93% of the F1-score. The present study demonstrates the versatility of ANNs based on MLP combined with the PCA technique since, even in an unbalanced database such as the one used, it allows excellent values to be achieved in the F1-score measure. The use of Artificial Intelligence and other tools applied in this work may eventually help specialists to perform a more accurate assessment in the monitoring of rehabilitation for patients with Parkinson's disease by improving records and thus avoiding subjectivity in the interpretation of treatment results.

Evaluación de la Calidad de los Agentes Conversacionales para la Creación de Instrumentos de Evaluación en Medición de Señales Bioeléctricas / Evaluation of the Quality of Conversational Agents for the Creation of Evaluation Instruments in Bioelectric Signals Measurement

Resumen El objetivo de esta investigación es evaluar la calidad de agentes conversacionales basados en Modelos de Lenguaje Grandes, para la evaluación de aplicación de conocimiento en Ingeniería Biomédica. Se desarrolló un instrumento de evaluación sobre seis temas de medición de señales bioeléctricas elaborado por un agente humano y los agentes conversacionales Chat-GPT y Bard. Se evaluó la calidad del instrumento en términos de nivel de pensamiento, validez, relevancia, claridad, dificultad y capacidad de discriminación, mediante índice kappa (k) del acuerdo de dos expertos y análisis Rasch de resultados de treinta y ocho estudiantes. Tras eliminar siete preguntas de los agentes conversacionales por problemas de validez y originalidad se integró un instrumento de seis preguntas. Las preguntas fueron válidas y relevantes, claras (>0.95, k=1.0), con dificultad baja a alta (0.61-0.87, k=0.83), índice de discriminación adecuado (0.11-0.47), a nivel de pensamiento de análisis (k=0.22). El promedio de los estudiantes fue de 7.24±2.40. Este es el primer análisis crítico de la calidad de los agentes conversacionales a un nivel de pensamiento superior al de comprensión. Los agentes conversacionales presentaron limitaciones en términos de validez, originalidad, dificultad y discriminación en comparación con el experto humano lo que resalta la necesidad aún de su supervisión.

Abstract This research aims to evaluate the quality of conversational agents based on Large Language Models for evaluating the application of knowledge in Biomedical Engineering. An evaluation instrument was developed on six topics for measuring bioelectrical signals prepared by a human agent and the conversational agents Chat-GPT and Bard. The quality of the instrument was evaluated in terms of level of thinking, validity, relevance, clarity, difficulty, and discrimination capacity, using the kappa (k) index of the agreement of two experts and Rasch analysis of results from thirty-eight students. After eliminating seven questions from the conversational agents due to validity and originality problems, a 6-question instrument was integrated. The questions were valid and relevant, clear (>0.95, k=1.0), with low to high difficulty (0.61-0.87, k=0.83), adequate discrimination index (0.11-0.47), at the analysis level of thinking (k =0.22). The average score of the students was 7.24±2.40. This is the first critical analysis of the quality of conversational agents at a level of thinking higher than comprehension. The conversational agents presented limitations in terms of validity, originality, difficulty, and discrimination compared to the human expert, which highlights the need for their supervision.

Design and Implementation of a Rehabilitation Upper-limb Exoskeleton Robot Controlled by Cognitive and Physical Interfaces.

This paper presents an upper limb exoskeleton that allows cognitive (through electromyography signals) and physical user interaction (through load cells sensors) for passive and active exercises that can activate neuroplasticity in the rehabilitation process of people who suffer from a neurological injury. For the exoskeleton to be easily accepted by patients who suffer from a neurological injury, we used the ISO9241-210:2010 as a methodology design process. As the first steps of the design process, design requirements were collected from previous usability tests and literature. Then, as a second step, a technological solution is proposed, and as a third step, the system was evaluated through performance and user testing. As part of the technological solution and to allow patient participation during the rehabilitation process, we have proposed a hybrid admittance control whose input is load cell or electromyography signals. The hybrid admittance control is intended for active therapy exercises, is easily implemented, and does not need musculoskeletal modeling to work. Furthermore, electromyography signals classification models and features were evaluated to identify the best settings for the cognitive human-robot interaction.

[Familiarization to treadmill walking in unimpaired Parkinson's disease patients]. / Familiarización de la marcha en banda sinfin de individuos con enfermedad de Parkinson.

Familiarization to treadmill walking in unimpaired Parkinson's disease (PD) patients is assessed, across multiple treadmill walking sessions. Thirteen PD subjects were enrolled into the study (Eight were in a moderate stage of the disease, and 5 in an advanced stage). PD subjects attended a progressive program consisting of 12 sessions of 20 min. Walking speed, cadence, step length and coefficient of variation were assessed. ANOVA test were used to evaluate progression of disease and time influence over familiarization. PD Subjects baseline characteristics did not differ significantly between both groups and typical dependencies over progression of disease and velocity were found for cadence, step length and coefficient of variation. However, we showed that some PD subjects may require longer familiarization times and that familiarization is an adaptation process which involves parameters as velocity, cadence and gait stability. A better definition of familiarization to treadmill is needed since some parameters such as step length does not change significantly while others such as cadence, coefficient of variation and intraclass correlation coefficient does. Therefore familiarization to treadmill walking should remain on measures of velocity, cadence, reliability and variability. However, a bigger sample size is needed in order to improve the results of the present study.

Evidence-based design and development of a VR-based treadmill system for gait research and rehabilitation of patients with Parkinson's disease.

Virtual reality (VR) in neurorehabilitation allows to reduce patient's risk and allows him to learn on a faster way. Up to now VR has been used in patients with Parkinson disease (PD) as a research tool and none of the developed systems are used in clinical practice. The goal of this project is to develop a VR-based system for gait therapy, and gait research of patients with PD designed based on published evidence. The developed system uses a digital camera to measure spatiotemporal gait parameters. The software was developed in C#, using Open-Source libraries that facilitates VR programming. The system has potential uses in clinical and research settings.

[Dynamic plantar pressure distribution after percutaneous hallux valgus correction using the Reverdin-Isham osteotomy]. / Distribución de la presión plantar dinámica después del tratamiento corrective de hallux valgus mediante la ténica de Reverdin-Isham.

Percutaneous surgical techniques are suitable for the correction of the hallux valgus deformity. Satisfactory aesthetic and functional results obtained with the Reverdin- Isham osteotomy have been reported. The aim of this study was to describe dynamic plantar pressure redistribution after the correction of the deformity using this technique. A sample of 20 feet with mild or moderate hallux valgus was conformed and surgically treated using the Reverdin-Isham osteotomy. Clinical, radiological, surface and pressure assessments were performed pre and postoperatively. Postoperative mean (± SD) values of the American Orthopaedic Foot and Ankle Society (AOFAS) score, metatarsophalangeal, first intermetatarsal and proximal articular sect angles were 95.7 (3.3), 15.5° (5.4), 9.5° (1.5) y 5.3° (3.0), respectively. A significant decrease was observed in surface values of both lateral (P = 0.003) and medial (P = 0.001) masks of the forefoot. Mean pressure values of the lateral forefoot region denoted a significant increase (P < 0.001) while the medial forefoot region showed no change (P = 0.137). There is evidence that this particular surgical technique promotes a new plantar pressure pattern in the foot that might significantly favour the increase of the pressure observed under the lesser metatarsal heads and might not induce meaningful changes in the mean pressure registered under the first metatarsal head and hallux.

Botulinum toxin, physical and occupational therapy, and neuromuscular electrical stimulation to treat spastic upper limb of children with cerebral palsy: a pilot study.

Spasticity has been successfully managed with different treatment modalities or combinations. No information is available on the effectiveness or individual contribution of botulinum toxin type A (BTA) combined with physical and occupational therapy and neuromuscular electrical stimulation to treat spastic upper limb. The purpose of this study was to assess the effects of such treatment and to inform sample-size calculations for a randomized controlled trial. BTA was injected into spastic upper limb muscles of 10 children. They received 10 sessions of physical and occupational therapy followed by 10 sessions of neuromuscular electrical stimulation on the wrist extensors (antagonist muscles). Degree of spasticity using the Modified Ashworth scale, active range of motion, and manual function with the Jebsen hand test, were assessed. Meaningful improvement was observed in hand function posttreatment (P = 0.03). Median spasticity showed a reduction trend and median amplitude of wrist range of motion registered an increase; however, neither of these were significant (P > 0.05). There is evidence of a beneficial effect of the combined treatment. Adequate information has been obtained on main outcome-measurement variability for calculating sample size for a subsequent study to quantify the treatment effect precisely.