Real-time gait analysis with accelerometer-based smart shoes.

In this paper, we present the evaluation of a new smart shoe capable of performing gait analysis in real time. The system is exclusively based on accelerometers which minimizes the power consumption. The estimated parameters are activity class (rest/walk/run), step cadence, ground contact time, foot impact (zone, strength, and balance), forward distance, and speed. The different parameters have been validated with a customized database of 26 subjects on a treadmill and video data labeled manually. Key measures for running analysis such as the cadence is retrieved with a maximum error of 2%, and the ground contact time with an average error of 3.25%. The classification of the foot impact zone achieves a precision between 72% and 91% depending of the running style. The presented algorithm has been licensed to ICON Health & Fitness Inc. for their line of wearables under the brand iFit.

Towards VO2 monitoring: Validation of a heart rate based algorithm.

This article presents and validates a novel algorithm for the continuous monitoring of the VO2 during exercise. The algorithm relies on instantaneous HR measurements to provide a continuous estimation, and can be integrated in a wearable device (e.g., smartwatch, sensor patch). It can be customized by user's main anthropomorphic parameters and automatically learns from newly incoming data recalibrating itself if needed. The system is evaluated against a database of 14 healthy subjects performing various maximal endurance tests. The proposed method provides a VO2 estimation with average RMSE of 4.63 ml/kg/min.

An autonomous medical monitoring system: Validation on arrhythmia detection.

In this paper, we present a generic platform for autonomous medical monitoring and diagnostics. We validated the platform in the context of arrhythmia detection with publicly available databases. The big advantage of this platform is its capacity to deal with various types of physiological signals. Many pre-processing steps are performed to bring the input information into a uniform state that will be explored by a machine learning algorithm. Since this block plays a crucial role in the entire processing pipeline, three different methods were evaluated for detection and classification of anomalies. The results presented in this work are validated on cardiac beats, where the highest accuracy was obtained on the classification of normal beats (94%). On the other hand, atrial fibrillation and premature ventricular contraction beats were classified with an accuracy of 78%.

Real-time monitoring of swimming performance.

This article presents the performance results of a novel algorithm for swimming analysis in real-time within a low-power wrist-worn device. The estimated parameters are: lap count, stroke count, time in lap, total swimming time, pace/speed per lap, total swam distance, and swimming efficiency (SWOLF). In addition, several swimming styles are automatically detected. Results were obtained using a database composed of 13 different swimmers spanning 646 laps and 858.78 min of total swam time. The final precision achieved in lap detection ranges between 99.7% and 100%, and the classification of the different swimming styles reached a sensitivity and specificity above 98%. We demonstrate that a swimmers performance can be fully analyzed with the smart bracelet containing the novel algorithm. The presented algorithm has been licensed to ICON Health & Fitness Inc. for their line of wearables under the brand iFit.

Accurate walking and running speed estimation using wrist inertial data.

In this work, we present an accelerometry-based device for robust running speed estimation integrated into a watch-like device. The estimation is based on inertial data processing, which consists in applying a leg-and-arm dynamic motion model to 3D accelerometer signals. This motion model requires a calibration procedure that can be done either on a known distance or on a constant speed period. The protocol includes walking and running speeds between 1.8km/h and 19.8km/h. Preliminary results based on eleven subjects are characterized by unbiased estimations with 2(nd) and 3(rd) quartiles of the relative error dispersion in the interval ±5%. These results are comparable to accuracies obtained with classical foot pod devices.

Physical activity profiling: Activity-specific step counting and energy expenditure models using 3D wrist acceleration.

In this paper, we present the evaluation of a new physical activity profiling system embedded in a wrist-located device. We propose a step counting and an energy expenditure (EE) method, and evaluate their accuracy against gold standard references. To this end, we used an actimetry sensor on the waist and an indirect calorimetry monitoring device on a population of 13 subjects to obtain step count and metabolic equivalent task (kcal/kg/h) referenced values. The subjects followed a protocol that spanned a given set of activities (lying, standing, walking, running) at a wide range of intensities. The performance of the EE model was characterized by a root-mean-square error (RMSE) of 1.22±0.34kcal/min, and step-count model at regular walking/running speeds by 0.71±0.06step/10sec.

Estudio de confiabilidad interexamen de la hemoglobina glicosilada para el diagnostico de la Diabetes Mellitus / Inter examination reliability study of the glycosylated hemoglobin in the diagnosis of Diabetes Mellitus

Pregunta de investigación: ¿cuál es la confiabilidad interexamen de la hemoglobina glucosilada para diagnosticar en forma precoz a los pacientes portadores de diabetes mellitus?. Objetivos: 1.- Determinar la variabilidad interexamen entre dos ó mas pruebas de hemoglobina glicosilada en un mismo sujeto. 2.- Conocer si algunas variables pueden alterar la prueba de hemoglobina glucosilada en un mismo sueto. Diseño: Estudio de confiabilidad interexamen. Ambiente: Hospital Obrero No 1 de la CNS, servicio de Medicina Interna y pacientes diabéticos internados y atendidos en consulta externa. Pacientes: casos consecutivos. Métodos: Pacientes con y sin diabetes fueron estudiados en tres ooportunidades distintas, usando el mismo método de hemoglobina glicosilada. Entre el grupo de pacientes diabéticos se estudiaron personas con todos los nieles de severidad de la enfermedad. En cada paciente se estudiaron una serie de covariables. Los datos se estudiaron con análisis de correlación, estadísticas de asociación y coeficiente de correlación intraclase. Resultados: El coeficiente de correlación intraclase muestra resultados substanciales a casi perfecto. No se encontraron covariables que influyan en la estabilidad del examen. Conclusiones: La hemoglobina glicosilada se mantiene estable en mediciones repetidas. Este hecho refuerza la utilidad de su uso en el diagnóstico y manejo de la diabetes.(au)