RESUMEN
BACKGROUND: Monitoring natural behavior and activity routines of hemiparetic rehabilitation patients across the day can provide valuable progress information for therapists and patients and contribute to an optimized rehabilitation process. In particular, continuous patient monitoring could add type, frequency and duration of daily life activity routines and hence complement standard clinical scores that are assessed for particular tasks only. Machine learning methods have been applied to infer activity routines from sensor data. However, supervised methods require activity annotations to build recognition models and thus require extensive patient supervision. Discovery methods, including topic models could provide patient routine information and deal with variability in activity and movement performance across patients. Topic models have been used to discover characteristic activity routine patterns of healthy individuals using activity primitives recognized from supervised sensor data. Yet, the applicability of topic models for hemiparetic rehabilitation patients and techniques to derive activity primitives without supervision needs to be addressed. OBJECTIVES: We investigate, 1) whether a topic model-based activity routine discovery framework can infer activity routines of rehabilitation patients from wearable motion sensor data. 2) We compare the performance of our topic model-based activity routine discovery using rule-based and clustering-based activity vocabulary. METHODS: We analyze the activity routine discovery in a dataset recorded with 11 hemiparetic rehabilitation patients during up to ten full recording days per individual in an ambulatory daycare rehabilitation center using wearable motion sensors attached to both wrists and the non-affected thigh. We introduce and compare rule-based and clustering-based activity vocabulary to process statistical and frequency acceleration features to activity words. Activity words were used for activity routine pattern discovery using topic models based on Latent Dirichlet Allocation. Discovered activity routine patterns were then mapped to six categorized activity routines. RESULTS: Using the rule-based approach, activity routines could be discovered with an average accuracy of 76% across all patients. The rule-based approach outperformed clustering by 10% and showed less confusions for predicted activity routines. CONCLUSION: Topic models are suitable to discover daily life activity routines in hemiparetic rehabilitation patients without trained classifiers and activity annotations. Activity routines show characteristic patterns regarding activity primitives including body and extremity postures and movement. A patient-independent rule set can be derived. Including expert knowledge supports successful activity routine discovery over completely data-driven clustering.
Asunto(s)
Actividades Cotidianas , Monitoreo Ambulatorio/instrumentación , Paresia/rehabilitación , Adulto , Anciano , Femenino , Humanos , Masculino , Persona de Mediana Edad , Procesamiento de Señales Asistido por ComputadorRESUMEN
BACKGROUND: About 50% of the patients with advanced Parkinson's disease (PD) suffer from freezing of gait (FOG), which is a sudden and transient inability to walk. It often causes falls, interferes with daily activities and significantly impairs quality of life. Because gait deficits in PD patients are often resistant to pharmacologic treatment, effective non-pharmacologic treatments are of special interest. OBJECTIVES: The goal of our study is to evaluate the concept of a wearable device that can obtain real-time gait data, processes them and provides assistance based on pre-determined specifications. METHODS: We developed a real-time wearable FOG detection system that automatically provides a cueing sound when FOG is detected and which stays until the subject resumes walking. We evaluated our wearable assistive technology in a study with 10 PD patients. Over eight hours of data was recorded and a questionnaire was filled out by each patient. RESULTS: Two hundred and thirty-seven FOG events have been identified by professional physiotherapists in a post-hoc video analysis. The device detected the FOG events online with a sensitivity of 73.1% and a specificity of 81.6% on a 0.5 sec frame-based evaluation. CONCLUSIONS: With this study we show that online assistive feedback for PD patients is possible. We present and discuss the patients' and physiotherapists' perspectives on wearability and performance of the wearable assistant as well as their gait performance when using the assistant and point out the next research steps. Our results demonstrate the benefit of such a context-aware system and motivate further studies.
Asunto(s)
Sistemas de Computación , Señales (Psicología) , Limitación de la Movilidad , Enfermedad de Parkinson/rehabilitación , Procesamiento de Señales Asistido por Computador/instrumentación , Terapia Asistida por Computador/instrumentación , Caminata , Anciano , Atención Ambulatoria , Femenino , Humanos , Masculino , Persona de Mediana EdadRESUMEN
OBJECTIVES: The aging of the population creates pressure on the healthcare systems in various ways. A massive increase of chronic disease conditions and age-related illness are predicted as the dominant forces driving the future health care. The objective of this paper is to present future research demands in pervasive healthcare with the goal to meet the healthcare challenges by paving the way for a pervasive, user-centered and preventive healthcare model. METHODS: This paper presents recent methodological approaches and proposes future research topics in three areas: i) pervasive, continuous and reliable long-term monitoring systems; ii) prevention through pervasive technology as a key element to maintain lifelong wellness; and iii) design and evaluation methods for ubiquitous, patient-centric technologies. RESULTS: Pervasive technology has been identified as a strong asset for achieving the vision of user-centered preventive healthcare. In order to make this vision a reality, new strategies for design, development and evaluation of technology have to find a common denominator and consequently interoperate. Moreover, the potential of pervasive healthcare technologies offers new opportunities beyond traditional disease treatment and may play a major role in prevention, e.g. motivate healthy behavior and disease prevention throughout all stages of life. In this sense, open challenges in future research have to be addressed such as the variability of health indicators between individuals and the manner in which relevant health indicators are provided to the users in order to maximize their motivation to mitigate or prevent unhealthy behaviors. Additionally, collecting evidence that pervasive technology improves health is seen as one of the toughest challenges. Promising approaches are recently introduced, such as "clinical proof-of-concept" and balanced observational studies. CONCLUSIONS: The paper concludes that pervasive healthcare will enable a paradigm shift from the established centralized healthcare model to a pervasive, user-centered and preventive overall lifestyle health management. In order to provide these new opportunities everywhere, anytime and to anyone, future research in the fields of pervasive sensing, pervasive prevention and evaluation of pervasive technology is inevitably needed.
Asunto(s)
Enfermedad Crónica/epidemiología , Enfermedad Crónica/prevención & control , Diagnóstico por Computador/tendencias , Necesidades y Demandas de Servicios de Salud/tendencias , Investigación sobre Servicios de Salud/tendencias , Monitoreo Ambulatorio/tendencias , Dinámica Poblacional , Servicios Preventivos de Salud/tendencias , Procesamiento de Señales Asistido por Computador , Anciano , Predicción , Accesibilidad a los Servicios de Salud/tendencias , Humanos , Cuidados a Largo Plazo , Aplicaciones de la Informática Médica , Computación en Informática Médica/tendencias , Atención Dirigida al PacienteRESUMEN
OBJECTIVES: In this work the effect of quasi-stationary movements on the electrodermal activity (EDA) after a startle event has been investigated and evaluated. In previous EDA research there is a discrepancy between the use of controlled environment studies and daily life surveys. This paper aims to address this by expanding the knowledge about EDA in real life applications. METHODS: A minimally obtrusive body-worn measurement device was designed and produced that simultaneously records EDA and finger movements. During this study, five subjects walked at different speeds and listened to startling sound events. The EDA response to these startle events was analyzed for different walking speeds using crosscorrelograms and cumulative frequency plots. RESULTS: The measured response to the startle event is consistent with the signal characteristics described in the literature. The results show that the faster a person is walking the more the signal property of the phasic part of the EDA is approaching a uniform distribution. However, even at a walking speed of 6 km/h the effect of the startle event is statistically still visible in the EDA (p < 0.05). CONCLUSIONS: The presented work offers a good understanding of the EDA while walking at different speeds. Although the artefacts evoked by walking cannot be determined directly, information on the movement can be useful. Depending on the walking speed a measurement about the reliability of peak detection could be introduced.
Asunto(s)
Respuesta Galvánica de la Piel/fisiología , Movimiento/fisiología , Postura/fisiología , Reflejo de Sobresalto/fisiología , Transducción de Señal/fisiología , Caminata/fisiología , Aceleración , Artefactos , Emociones/fisiología , Dedos/inervación , Dedos/fisiología , Humanos , Proyectos Piloto , Descanso/fisiologíaRESUMEN
OBJECTIVES: Wearable systems can be broadly defined as mobile electronic devices that can be unobtrusively embedded in the user's outfit as part of the clothing or an accessory. In particular, unlike conventional mobile systems, they can be operational and accessed without or with very little hindrance to user activity. To this end they are able to model and recognize user activity, state, and the surrounding situation: a property, referred to as context sensitivity. Wearable systems range from micro sensors seamlessly integrated in textiles through consumer electronics embedded in fashionable clothes and computerized watches to belt worn PCs with a head mounted display. The wearable computing concept is part of a broader framework of ubiquitous computing that aims at invisibly enhancing our environment with smart electronic devices. The goal of the paper is to provide a broad overview of wearable technology and its implications for health related applications. METHODS: We begin by summarizing the vision behind wearable computing. We then describe a framework for wearable computing architecture and the main technological aspects. Finally we show how specific properties of wearable systems can be used in different health related application domains. RESULTS: Wearable computing is an emerging concept building upon the success of today's mobile computing and communication devices. Due to rapid technological progress it is currently making a transition from a pure research stage to practical applications. Many of those applications are in health related domains, in particular, health monitoring, mobile treatment and nursing. CONCLUSIONS: Within the next couple of years wearable systems and more general ubiquitous computing will introduce profound changes and new application types to health related systems. In particular they will prove useful in improving the quality and reducing the cost of caring for the aging population.
Asunto(s)
Redes de Comunicación de Computadores/instrumentación , Sistemas de Atención de Punto/tendencias , Procesamiento de Señales Asistido por Computador/instrumentación , Interfaz Usuario-Computador , Vestuario , Computadoras de Mano , Humanos , Monitoreo Fisiológico/instrumentación , Monitoreo Fisiológico/tendencias , Dispositivos de AutoayudaRESUMEN
We investigated the perception of brightness for red monochromatic laser light. For this purpose, a modified virtual retinal display (VRD) was constructed. The modification involved projecting the laser beam into the eye. In our VRD, the laser beam pivots in the nodal point of the eye (badal system). The displayed image therefore does not depend on the refractive state of the eye. Brightness perception was assessed by means of psychophysical experiments. The results of these experiments indicate that perception of brightness at 652 nm increases more rapidly with increasing physical stimulus than does the perception of white light (colour temperature 2'935 K). At a wavelength of 652 nm, an optical power of 79 nW is required to produce an image subtending 2 degrees of equal brightness, as is perceived with an image of about 2'900 cd/m2 subtending 2 degrees.
Asunto(s)
Percepción de Color/fisiología , Defectos de la Visión Cromática/diagnóstico , Sensibilidad de Contraste/fisiología , Retina/fisiopatología , Interfaz Usuario-Computador , Adulto , Defectos de la Visión Cromática/fisiopatología , Femenino , Humanos , Rayos Láser , Masculino , Estimulación Luminosa , Psicofísica , Valores de Referencia , Refracción Ocular/fisiologíaRESUMEN
A detailed analysis of homing in pigeons and small mammals has remained difficult because the paths of the animals could not be reconstructed precisely. Here, we describe a lightweight global position system (GPS) data logger (35 g including battery and casing; 40 x 68 x 18 mm) that records the flight of pigeons and the path of dogs with an accuracy of +/-12 m. With one battery, the logger runs in continuous mode (1 fix/s) for 3.5 h and in power-saving mode (1 fix/5 s) for about 16 h, and stores a maximum of 100,000 data points that are downloaded to a PC. A module of our public domain software WINTRACK permits a detailed numerical and graphical analysis of path geometry, phases of resting and moving, and path similarity. The device can be adapted to different species provided that satellite signals can be received reliably and that the loggers can be recovered. We expect it to be useful for testing hypotheses about pigeon homing, assessing natural spatial behavior and orientation of many species, and anticipate further miniaturization.
Asunto(s)
Conducta Animal/efectos de los fármacos , Columbidae/fisiología , Fenómenos de Retorno al Lugar Habitual , Psicología Experimental/instrumentación , Programas Informáticos , Telemetría/instrumentación , Animales , Interpretación Estadística de Datos , PerrosRESUMEN
Virtual reality (VR) based surgical simulator systems offer very elegant possibilities to both enrich and enhance traditional education in endoscopic surgery. However, while a wide range of VR simulator systems have been proposed and realized in the past few years, most of these systems are far from able to provide a reasonably realistic surgical environment. We explore the basic approaches to the current limits of realism and ultimately seek to extend these based on our description and analysis of the most important components of a VR-based endoscopic simulator. The feasibility of the proposed techniques is demonstrated on a first modular prototype system implementing the basic algorithms for VR-training in gynaecologic laparoscopy.