Alejandro Rodríguez-Molinero

Human Centred Design Considerations for Connected Health Devices for the Older Adult

Connected health devices are generally designed for unsupervised use, by non-healthcare professionals, facilitating independent control of the individuals own healthcare. Older adults are major users of such devices and are a population significantly increasing in size. This group presents challenges due to the wide spectrum of capabilities and attitudes towards technology. The fit between capabilities of the user and demands of the device can be optimised in a process called Human Centred Design. Here we review examples of some connected health devices chosen by random selection, assess older adult known capabilities and attitudes and finally make analytical recommendations for design approaches and design specifications.

Home detection of freezing of gait using support vector machines through a single waist-worn triaxial accelerometer

Among Parkinson’s disease (PD) symptoms, freezing of gait (FoG) is one of the most debilitating. To assess FoG, current clinical practice mostly employs repeated evaluations over weeks and months based on questionnaires, which may not accurately map the severity of this symptom. The use of a non-invasive system to monitor the activities of daily living (ADL) and the PD symptoms experienced by patients throughout the day could provide a more accurate and objective evaluation of FoG in order to better understand the evolution of the disease and allow for a more informed decision-making process in making adjustments to the patient’s treatment plan. This paper presents a new algorithm to detect FoG with a machine learning approach based on Support Vector Machines (SVM) and a single tri-axial accelerometer worn at the waist. The method is evaluated through the acceleration signals in an outpatient setting gathered from 21 PD patients at their home and evaluated under two different conditions: first, a generic model is tested by using a leave-one-out approach and, second, a personalised model that also uses part of the dataset from each patient. Results show a significant improvement in the accuracy of the personalised model compared to the generic model, showing enhancement in the specificity and sensitivity geometric mean (GM) of 7.2%. Furthermore, the SVM approach adopted has been compared to the most comprehensive FoG detection method currently in use (referred to as MBFA in this paper). Results of our novel generic method provide an enhancement of 11.2% in the GM compared to the MBFA generic model and, in the case of the personalised model, a 10% of improvement with respect to the MBFA personalised model. Thus, our results show that a machine learning approach can be used to monitor FoG during the daily life of PD patients and, furthermore, personalised models for FoG detection can be used to improve monitoring accuracy.

Validation of a Portable Device for Mapping Motor and Gait Disturbances in Parkinson’s Disease

Background Patients with severe idiopathic Parkinson’s disease experience motor fluctuations, which are often difficult to control. Accurate mapping of such motor fluctuations could help improve patients’ treatment. Objective The objective of the study was to focus on developing and validating an automatic detector of motor fluctuations. The device is small, wearable, and detects the motor phase while the patients walk in their daily activities. Methods Algorithms for detection of motor fluctuations were developed on the basis of experimental data from 20 patients who were asked to wear the detector while performing different daily life activities, both in controlled (laboratory) and noncontrolled environments. Patients with motor fluctuations completed the experimental protocol twice: (1) once in the ON, and (2) once in the OFF phase. The validity of the algorithms was tested on 15 different patients who were asked to wear the detector for several hours while performing daily activities in their habitual environments. In order to assess the validity of detector measurements, the results of the algorithms were compared with data collected by trained observers who were accompanying the patients all the time. Results The motor fluctuation detector showed a mean sensitivity of 0.96 (median 1; interquartile range, IQR, 0.93-1) and specificity of 0.94 (median 0.96; IQR, 0.90-1). Conclusions ON/OFF motor fluctuations in Parkinsons patients can be detected with a single sensor, which can be worn in everyday life.

Normal Respiratory Rate and Peripheral Blood Oxygen Saturation in the Elderly Population

To the Editor: Age-specific normal limits for a number of vital signs and physiological parameters have not been established in the elderly population. The limits for younger adults are not always applicable because of ageassociated physiological changes and the increase of interindividual differences with age. Regarding the respiratory system, there are few data on normal respiratory rate at rest (RR) and peripheral pulse oximetry values (SpO2), which are major parameters in clinical practice and easy to measure, and become altered quickly in respiratory and cardiac diseases. (Increased respiratory rate is often the only visible sign of a respiratory infection.) This was a cross-sectional study of 791 noninstitutionalized individuals aged 65 and older living in Spain to establish the limits of normal RR and SpO2 in the elderly population. The sample was collected using multistaged probabilistic sampling and stratified according to sex, size of place of residence (rural, urban, or big city), and geographic location with a nonproportional age stratum (523 subjects aged ≥80). A sample of 576 participants was considered necessary to estimate RR and SpO2 with 5% error and a design effect of 1.5. Survey data were collected between 2007 and 2009. The survey was carefully designed to reduce nonsampling errors, the survey takers received specific training, and the field work was thoroughly supervised. RR and the SpO2 were measured with the participant in a seated position after a rest of at least 10 minutes. SpO2 was measured using a pulse oximeter (9500; Nonin Medical, Plymouth, MN), and RR was measured by directly observing thoracic movements for a 30-second period. As a distraction maneuver, the survey takers pretended to measure the radial pulse, so that participants would not be aware that their respiratory rate was being measured. All information about participants’ medical background was collected as control variables. Two consecutive analyses were conducted. First, all participants with pathologies that proved to affect RR or SpO2 independently in multivariable models were excluded. A subsequent more-restricted analysis was performed by excluding all individuals who had any clinical factor showing significant influence in bivariate analyses. Participants with dyspnea during the examination were excluded from all calculations. Normal RR limits were represented according to percentiles that delimit 95% of the sample (2.5–97.5) and percentiles that delimit 99% of the sample (0.5–99.5). Limits of SpO2 were represented according to the first and fifth percentiles. Calculations were weighted according to age, sex, and size of place of residence. History of chronic obstructive pulmonary disease (COPD) was the only variable that independently influenced RR and SpO2 in the multivariate models. Once individuals with COPD were excluded, the RR distribution appeared bell-shaped, with 0.67 kurtosis and 0.43 asymmetry, and was significantly different from the theoretical normal distribution according to the Kolmogorov contrast test. Percentiles 2.5 and 97.5 were 12 respirations per minute (rpm) (95% CI = 10–12 rpm) and 28 rpm (95% CI = 28–32 rpm), respectively. Percentiles 0.5 and 99.5

A human-centered design methodology to enhance the usability, human factors, and user experience of connected health systems: a three-phase methodology

Background Design processes such as human-centered design, which involve the end user throughout the product development and testing process, can be crucial in ensuring that the product meets the needs and capabilities of the user, particularly in terms of safety and user experience. The structured and iterative nature of human-centered design can often present a challenge when design teams are faced with the necessary, rapid, product development life cycles associated with the competitive connected health industry. Objective We wanted to derive a structured methodology that followed the principles of human-centered design that would allow designers and developers to ensure that the needs of the user are taken into account throughout the design process, while maintaining a rapid pace of development. In this paper, we present the methodology and its rationale before outlining how it was applied to assess and enhance the usability, human factors, and user experience of a connected health system known as the Wireless Insole for Independent and Safe Elderly Living (WIISEL) system, a system designed to continuously assess fall risk by measuring gait and balance parameters associated with fall risk. Methods We derived a three-phase methodology. In Phase 1 we emphasized the construction of a use case document. This document can be used to detail the context of use of the system by utilizing storyboarding, paper prototypes, and mock-ups in conjunction with user interviews to gather insightful user feedback on different proposed concepts. In Phase 2 we emphasized the use of expert usability inspections such as heuristic evaluations and cognitive walkthroughs with small multidisciplinary groups to review the prototypes born out of the Phase 1 feedback. Finally, in Phase 3 we emphasized classical user testing with target end users, using various metrics to measure the user experience and improve the final prototypes. Results We report a successful implementation of the methodology for the design and development of a system for detecting and predicting falls in older adults. We describe in detail what testing and evaluation activities we carried out to effectively test the system and overcome usability and human factors problems. Conclusions We feel this methodology can be applied to a wide variety of connected health devices and systems. We consider this a methodology that can be scaled to different-sized projects accordingly.

Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer

BACKGROUND After several years of treatment, patients with Parkinsons disease (PD) tend to have, as a side effect of the medication, dyskinesias. Close monitoring may benefit patients by enabling doctors to tailor a personalised medication regimen. Moreover, dyskinesia monitoring can help neurologists make more informed decisions in patients care. OBJECTIVE To design and validate an algorithm able to be embedded into a system that PD patients could wear during their activities of daily living with the purpose of registering the occurrence of dyskinesia in real conditions. MATERIALS AND METHODS Data from an accelerometer positioned in the waist are collected at the patients home and are annotated by experienced clinicians. Data collection is divided into two parts: a main database gathered from 92 patients used to partially train and to evaluate the algorithms based on a leave-one-out approach and, on the other hand, a second database from 10 patients which have been used to also train a part of the detection algorithm. RESULTS Results show that, depending on the severity and location of dyskinesia, specificities and sensitivities higher than 90% are achieved using a leave-one-out methodology. Although mild dyskinesias presented on the limbs are detected with 95% specificity and 39% sensitivity, the most important types of dyskinesia (any strong dyskinesia and trunk mild dyskinesia) are assessed with 95% specificity and 93% sensitivity. CONCLUSION The presented algorithmic method and wearable device have been successfully validated in monitoring the occurrence of strong dyskinesias and mild trunk dyskinesias during activities of daily living.

Time series analysis of inertial-body signals for the extraction of dynamic properties from human gait

This paper presents an algorithm for the automatic estimation of spatio temporal gait properties from signals provided by inertial body sensors. The approach is based on time series analysis. Here, a minimum number of body sensor devices is used, which imposes limitations for the automatic extraction of relevant properties of the gait like step length and velocity. The human gait is represented as a dynamical system (DS), which internal states are hidden. Sensor information is interpreted as an observation of a particular trajectory of the DS, from wich a reconstruction space can be obtained. The reconstruction space is then transformed using standard principal components analysis (PCA). From the transformed space, reliable models to estimate step length and velocities are successfully constructed.

Analysis of Correlation between an Accelerometer-Based Algorithm for Detecting Parkinsonian Gait and UPDRS Subscales

Background Our group earlier developed a small monitoring device, which uses accelerometer measurements to accurately detect motor fluctuations in patients with Parkinson’s (On and Off state) based on an algorithm that characterizes gait through the frequency content of strides. To further validate the algorithm, we studied the correlation of its outputs with the motor section of the Unified Parkinson’s Disease Rating Scale part-III (UPDRS-III). Method Seventy-five patients suffering from Parkinson’s disease were asked to walk both in the Off and the On state while wearing the inertial sensor on the waist. Additionally, all patients were administered the motor section of the UPDRS in both motor phases. Tests were conducted at the patient’s home. Convergence between the algorithm and the scale was evaluated by using the Spearman’s correlation coefficient. Results Correlation with the UPDRS-III was moderate (rho −0.56; p < 0.001). Correlation between the algorithm outputs and the gait item in the UPDRS-III was good (rho −0.73; p < 0.001). The factorial analysis of the UPDRS-III has repeatedly shown that several of its items can be clustered under the so-called Factor 1: “axial function, balance, and gait.” The correlation between the algorithm outputs and this factor of the UPDRS-III was −0.67 (p < 0.01). Conclusion The correlation achieved by the algorithm with the UPDRS-III scale suggests that this algorithm might be a useful tool for monitoring patients with Parkinson’s disease and motor fluctuations.

Posture transition identification on PD patients through a SVM-based technique and a single waist-worn accelerometer

Identification of activities of daily living is essential in order to evaluate the quality of life both in the elderly and patients with mobility problems. Posture transitions (PT) are one of the most mechanically demanding activities in daily life and, thus, they can lead to falls in patients with mobility problems. This paper deals with PT recognition in Parkinsons disease (PD) patients by means of a triaxial accelerometer situated between the anterior and the left lateral part of the waist. Since sensors orientation is susceptible to change during long monitoring periods, a hierarchical structure of classifiers is proposed in order to identify PT while allowing such orientation changes. Results are presented based on signals obtained from 20 PD patients and 67 healthy people who wore an inertial sensor on different positions among the anterior and the left lateral part of the waist. The algorithm has been compared to a previous approach in which only the anterior-lateral location was analyzed improving the sensitivity while preserving specificity. Moreover, different supervised machine learning techniques have been evaluated in distinguishing PT. Results show that the location of the sensor slightly affects methods performance and, furthermore, PD motor state does not alter its accuracy. Posture transition identification is performed by means of a tri-axial accelerometer located in the waist.A hierarchical structure of classifiers allows to determine the human posture.SVM techniques have been used to set parameters of the algorithm.The algorithm allows different locations along waists left side.The algorithm is focused on Parkinsons disease patients.

A double closed loop to enhance the quality of life of Parkinson's Disease patients: REMPARK system.

This paper presents REMPARK system, a novel approach to deal with Parkinsons Disease (PD). REMPARK system comprises two closed loops of actuation onto PD. The first loop consists in a wearable system that, based on a belt-worn movement sensor, detects movement alterations that activate an auditory cueing system controlled by a smartphone in order to improve patients gait. The belt-worn sensor analyzes patients movement through real-time learning algorithms that were developed on the basis of a database previously collected from 93 PD patients. The second loop consists in disease management based on the data collected during long periods and that enables neurologists to tailor medication of their PD patients and follow the disease evolution. REMPARK system is going to be tested in 40 PD patients in Spain, Ireland, Italy and Israel. This paper describes the approach followed to obtain this system, its components, functionalities and trials in which the system will be validated.