Estimation of spatio-temporal parameters of gait from magneto-inertial measurement units: multicenter validation among Parkinson, mildly cognitively impaired and healthy older adults.

BACKGROUND: The use of miniaturized magneto-inertial measurement units (MIMUs) allows for an objective evaluation of gait and a quantitative assessment of clinical outcomes. Spatial and temporal parameters are generally recognized as key metrics for characterizing gait. Although several methods for their estimate have been proposed, a thorough error analysis across different pathologies, multiple clinical centers and on large sample size is still missing. The aim of this study was to apply a previously presented method for the estimate of spatio-temporal parameters, named Trusted Events and Acceleration Direct and Reverse Integration along the direction of Progression (TEADRIP), on a large cohort (236 patients) including Parkinson, mildly cognitively impaired and healthy older adults collected in four clinical centers. Data were collected during straight-line gait, at normal and fast walking speed, by attaching two MIMUs just above the ankles. The parameters stride, step, stance and swing durations, as well as stride length and gait velocity, were estimated for each gait cycle. The TEADRIP performance was validated against data from an instrumented mat. RESULTS: Limits of agreements computed between the TEADRIP estimates and the reference values from the instrumented mat were - 27 to 27 ms for Stride Time, - 68 to 44 ms for Stance Time, - 31 to 31 ms for Step Time and - 67 to 52 mm for Stride Length. For each clinical center, the mean absolute errors averaged across subjects for the estimation of temporal parameters ranged between 1 and 4%, being on average less than 3% (< 30 ms). Stride length mean absolute errors were on average 2% (≈ 25 mm). Error comparisons across centers did not show any significant difference. Significant error differences were found exclusively for stride and step durations between healthy elderly and Parkinsonian subjects, and for the stride length between walking speeds. CONCLUSIONS: The TEADRIP method was effectively validated on a large number of healthy and pathological subjects recorded in four different clinical centers. Results showed that the spatio-temporal parameters estimation errors were consistent with those previously found on smaller population samples in a single center. The combination of robustness and range of applicability suggests the use of the TEADRIP as a suitable MIMU-based method for gait spatio-temporal parameter estimate in the routine clinical use. The present paper was awarded the "SIAMOC Best Methodological Paper 2017".

A Machine Learning Framework for Gait Classification Using Inertial Sensors: Application to Elderly, Post-Stroke and Huntington's Disease Patients.

Machine learning methods have been widely used for gait assessment through the estimation of spatio-temporal parameters. As a further step, the objective of this work is to propose and validate a general probabilistic modeling approach for the classification of different pathological gaits. Specifically, the presented methodology was tested on gait data recorded on two pathological populations (Huntington's disease and post-stroke subjects) and healthy elderly controls using data from inertial measurement units placed at shank and waist. By extracting features from group-specific Hidden Markov Models (HMMs) and signal information in time and frequency domain, a Support Vector Machines classifier (SVM) was designed and validated. The 90.5% of subjects was assigned to the right group after leave-one-subject-out cross validation and majority voting. The long-term goal we point to is the gait assessment in everyday life to early detect gait alterations.

Estimation of step-by-step spatio-temporal parameters of normal and impaired gait using shank-mounted magneto-inertial sensors: application to elderly, hemiparetic, parkinsonian and choreic gait.

BACKGROUND: The step-by-step determination of the spatio-temporal parameters of gait is clinically relevant since it provides an estimation of the variability of specific gait patterns associated with frequent geriatric syndromes. In recent years, several methods, based on the use of magneto-inertial units (MIMUs), have been developed for the step-by-step estimation of the gait temporal parameters. However, most of them were applied to the gait of healthy subjects and/or of a single pathologic population. Moreover, spatial parameters in pathologic populations have been rarely estimated step-by-step using MIMUs. The validity of clinically suitable MIMU-based methods for the estimation of spatio-temporal parameters is therefore still an open issue. The aim of this study was to propose and validate a method for the determination of both temporal and spatial parameters that could be applied to normal and heavily compromised gait patterns. METHODS: Two MIMUs were attached above each subject's ankles. An instrumented gait mat was used as gold standard. Gait data were acquired from ten hemiparetic subjects, ten choreic subjects, ten subjects with Parkinson's disease and ten healthy older adults walking at two different gait speeds. The method detects gait events (GEs) taking advantage of the cyclic nature of gait and exploiting some lower limb invariant kinematic characteristics. A combination of a MIMU axes realignment along the direction of progression and of an optimally filtered direct and reverse integration is used to determine the stride length. RESULTS: Over the 4,514 gait cycles analyzed, neither missed nor extra GEs were generated. The errors in identifying both initial and final contact at comfortable speed ranged between 0 and 11 ms for the different groups analyzed. The stride length was estimated for all subjects with less than 3% error. CONCLUSIONS: The proposed method is apparently extremely robust since gait speed did not substantially affect its performance and both missed and extra GEs were avoided. The spatio-temporal parameters estimates showed smaller errors than those reported in previous studies and a similar level of precision and accuracy for both healthy and pathologic gait patterns. The combination of robustness, precision and accuracy suggests that the proposed method is suitable for routine clinical use.

Older Adults' and Clinicians' Perspectives on a Smart Health Platform for the Aging Population: Design and Evaluation Study.

BACKGROUND: Over recent years, interest in the development of smart health technologies aimed at supporting independent living for older populations has increased. The integration of innovative technologies, such as the Internet of Things, wearable technologies, artificial intelligence, and ambient-assisted living applications, represents a valuable solution for this scope. Designing such an integrated system requires addressing several aspects (eg, equipment selection, data management, analytics, costs, and users' needs) and involving different areas of expertise (eg, medical science, service design, biomedical and computer engineering). OBJECTIVE: The objective of this study is 2-fold; we aimed to design the functionalities of a smart health platform addressing 5 chronic conditions prevalent in the older population (ie, hearing loss, cardiovascular diseases, cognitive impairments, mental health problems, and balance disorders) by considering both older adults' and clinicians' perspectives and to evaluate the identified smart health platform functionalities with a small group of older adults. METHODS: Overall, 24 older adults (aged >65 years) and 118 clinicians were interviewed through focus group activities and web-based questionnaires to elicit the smart health platform requirements. Considering the elicited requirements, the main functionalities of smart health platform were designed. Then, a focus group involving 6 older adults was conducted to evaluate the proposed solution in terms of usefulness, credibility, desirability, and learnability. RESULTS: Eight main functionalities were identified and assessed-cognitive training and hearing training (usefulness: 6/6, 100%; credibility: 6/6, 100%; desirability: 6/6, 100%; learnability: 6/6, 100%), monitoring of physiological parameters (usefulness: 6/6, 100%; credibility: 6/6, 100%; desirability: 6/6, 100%; learnability: 5/6, 83%), physical training (usefulness: 6/6, 100%; credibility: 6/6, 100%; desirability: 5/6, 83%; learnability: 2/6, 33%), psychoeducational intervention (usefulness: 6/6, 100%; credibility: 6/6, 100%; desirability: 4/6, 67%; learnability: 2/6, 33%), mood monitoring (usefulness: 4/6, 67%; credibility: 4/6, 67%; desirability: 3/6, 50%; learnability: 5/6, 50%), diet plan (usefulness: 5/6, 83%; credibility: 4/6, 67%; desirability: 1/6, 17%; learnability: 2/6, 33%), and environment monitoring and adjustment (usefulness: 1/6, 17%; credibility: 1/6, 17%; desirability: 0/6, 0%; learnability: 0/6, 0%). Most of them were highly appreciated by older participants, with the only exception being environment monitoring and adjustment. The results showed that the proposed functionalities met the needs and expectations of users (eg, improved self-management of patients' disease and enhanced patient safety). However, some aspects need to be addressed (eg, technical and privacy issues). CONCLUSIONS: The presented smart health platform functionalities seem to be able to meet older adults' needs and desires to enhance their self-awareness and self-management of their medical condition, encourage healthy and independent living, and provide evidence-based support for clinicians' decision-making. Further research with a larger and more heterogeneous pool of stakeholders in terms of demographics and clinical conditions is needed to assess system acceptability and overall user experience in free-living conditions.

Improving Health Monitoring With Adaptive Data Movement in Fog Computing.

Pervasive sensing is increasing our ability to monitor the status of patients not only when they are hospitalized but also during home recovery. As a result, lots of data are collected and are available for multiple purposes. If operations can take advantage of timely and detailed data, the huge amount of data collected can also be useful for analytics. However, these data may be unusable for two reasons: data quality and performance problems. First, if the quality of the collected values is low, the processing activities could produce insignificant results. Second, if the system does not guarantee adequate performance, the results may not be delivered at the right time. The goal of this document is to propose a data utility model that considers the impact of the quality of the data sources (e.g., collected data, biographical data, and clinical history) on the expected results and allows for improvement of the performance through utility-driven data management in a Fog environment. Regarding data quality, our approach aims to consider it as a context-dependent problem: a given dataset can be considered useful for one application and inadequate for another application. For this reason, we suggest a context-dependent quality assessment considering dimensions such as accuracy, completeness, consistency, and timeliness, and we argue that different applications have different quality requirements to consider. The management of data in Fog computing also requires particular attention to quality of service requirements. For this reason, we include QoS aspects in the data utility model, such as availability, response time, and latency. Based on the proposed data utility model, we present an approach based on a goal model capable of identifying when one or more dimensions of quality of service or data quality are violated and of suggesting which is the best action to be taken to address this violation. The proposed approach is evaluated with a real and appropriately anonymized dataset, obtained as part of the experimental procedure of a research project in which a device with a set of sensors (inertial, temperature, humidity, and light sensors) is used to collect motion and environmental data associated with the daily physical activities of healthy young volunteers.

Automatic classification of gait in children with early-onset ataxia or developmental coordination disorder and controls using inertial sensors.

Early-Onset Ataxia (EOA) and Developmental Coordination Disorder (DCD) are two conditions that affect coordination in children. Phenotypic identification of impaired coordination plays an important role in their diagnosis. Gait is one of the tests included in rating scales that can be used to assess motor coordination. A practical problem is that the resemblance between EOA and DCD symptoms can hamper their diagnosis. In this study we employed inertial sensors and a supervised classifier to obtain an automatic classification of the condition of participants. Data from shank and waist mounted inertial measurement units were used to extract features during gait in children diagnosed with EOA or DCD and age-matched controls. We defined a set of features from the recorded signals and we obtained the optimal features for classification using a backward sequential approach. We correctly classified 80.0%, 85.7%, and 70.0% of the control, DCD and EOA children, respectively. Overall, the automatic classifier correctly classified 78.4% of the participants, which is slightly better than the phenotypic assessment of gait by two pediatric neurologists (73.0%). These results demonstrate that automatic classification employing signals from inertial sensors obtained during gait maybe used as a support tool in the differential diagnosis of EOA and DCD. Furthermore, future extension of the classifier's test domains may help to further improve the diagnostic accuracy of pediatric coordination impairment. In this sense, this study may provide a first step towards incorporating a clinically objective and viable biomarker for identification of EOA and DCD.

Hidden Markov model-based strategy for gait segmentation using inertial sensors: Application to elderly, hemiparetic patients and Huntington's disease patients.

A solution to discriminate stance and swing in both healthy and abnormal gait using inertial sensors is proposed. The method is based on a two states hidden Markov model trained in a supervised way. The proposed method can generalize across different groups of subjects, without the need of parameters tuning. Leave-one-subject-out validation tests showed 20 ms and 16 ms errors on average in the determination of foot strike and toe off events across the three groups of subjects including 10 elderly, 10 hemiparetic patients and 10 Huntington's disease patients. The proposed methodology can be implemented online in portable devices to be used in clinical practice or in everyday personal health assessment.

Comparative assessment of different methods for the estimation of gait temporal parameters using a single inertial sensor: application to elderly, post-stroke, Parkinson's disease and Huntington's disease subjects.

The estimation of gait temporal parameters with inertial measurement units (IMU) is a research topic of interest in clinical gait analysis. Several methods, based on the use of a single IMU mounted at waist level, have been proposed for the estimate of these parameters showing satisfactory performance when applied to the gait of healthy subjects. However, the above mentioned methods were developed and validated on healthy subjects and their applicability in pathological gait conditions was not systematically explored. We tested the three best performing methods found in a previous comparative study on data acquired from 10 older adults, 10 hemiparetic, 10 Parkinson's disease and 10 Huntington's disease subjects. An instrumented gait mat was used as gold standard. When pathological populations were analyzed, missed or extra events were found for all methods and a global decrease of their performance was observed to different extents depending on the specific group analyzed. The results revealed that none of the tested methods outperformed the others in terms of accuracy of the gait parameters determination for all the populations except the Parkinson's disease subjects group for which one of the methods performed better than others. The hemiparetic subjects group was the most critical group to analyze (stride duration errors between 4-5 % and step duration errors between 8-13 % of the actual values across methods). Only one method provides estimates of the stance and swing durations which however should be interpreted with caution in pathological populations (stance duration errors between 6-14 %, swing duration errors between 10-32 % of the actual values across populations).

Accuracy, sensitivity and robustness of five different methods for the estimation of gait temporal parameters using a single inertial sensor mounted on the lower trunk.

In the last decade, various methods for the estimation of gait events and temporal parameters from the acceleration signals of a single inertial measurement unit (IMU) mounted at waist level have been proposed. Despite the growing interest for such methodologies, a thorough comparative analysis of methods with regards to number of extra and missed events, accuracy and robustness to IMU location is still missing in the literature. The aim of this work was to fill this gap. Five methods have been tested on single IMU data acquired from fourteen healthy subjects walking while being recorded by a stereo-photogrammetric system and two force platforms. The sensitivity in detecting initial and final contacts varied between 81% and 100% across methods, whereas the positive predictive values ranged between 94% and 100%. For all tested methods, stride and step time estimates were obtained; three of the selected methods also allowed estimation of stance, swing and double support time. Results showed that the accuracy in estimating step and stride durations was acceptable for all methods. Conversely, a statistical difference was found in the error in estimating stance, swing and double support time, due to the larger errors in the final contact determination. Except for one method, the IMU positioning on the lower trunk did not represent a critical factor for the estimation of gait temporal parameters. Results obtained in this study may not be applicable to pathologic gait.