Conference PaperPDF Available

Continuous Assessment of Gait Velocity in Parkinson's Disease from Unobtrusive Measurements

Authors:

Abstract and Figures

The ability to assess the neurological state of patients with neurodegenerative diseases on a continuous basis is an important component of future care for these chronically ill patients. In this paper we describe a set of algorithms to infer gait velocity and its variability using data from an unobtrusive sensor network by incorporating a simple dynamic description of a patient's movements within his or her residence. The sensors include a combination of passive motion detectors and active radio frequency identification tags. The dynamic model is a simple 4 state hidden Markov model. We investigated the ability of this model to assess gait velocity and its variability using data from a six month pilot study of several patients with early stage Parkinson's disease
Content may be subject to copyright.
Abstract— The ability to assess the neurological state of
patients with neurodegenerative diseases on a continuous basis
is an important component of future care for these chronically
ill patients. In this paper we describe a set of algorithms to
infer gait velocity and its variability using data from an
unobtrusive sensor network by incorporating a simple dynamic
description of a patient’s movements within his or her
residence. The sensors include a combination of passive motion
detectors and active radio frequency identification tags. The
dynamic model is a simple 4 state hidden Markov model. We
investigated the ability of this model to assess gait velocity and
its variability using data from a six month pilot study of several
patients with early stage Parkinson’s disease.
I. INTRODUCTION
HE ability to assess the sensory, motor and cognitive
functionality of an individual is an important problem in
caring for individuals with chronic diseases, as well as for
the healthy elders. Current methods relying on observations,
e.g., Unified Parkinson’s Disease Rating Scale (UPDRS),
Clinical Dementia Rating (CDR) as well as those relying on
neuropsychological testing are inherently highly variable,
costly, and to some extent depend on the testers’ capabilities
and training. As such, they are administered infrequently,
require multiple administrations to assess long-term change,
and are generally difficult to use to assess the instantaneous
state of the patient.
Yet, in many situations it would be desirable to assess the
functions related to the neurological state of the patient on a
continuous basis. For example, in the care of patients with
Parkinson’s disease (PD), the instantaneous aspects of gait
velocity may be a useful measure for the determination of
the administration of drugs, such as Levodopa. Also,
continuous measurement of motor function would be a large
improvement over current techniques of estimating impact
This work was supported in part by grants from NIH, NSF, and the
Kinetics Foundations to Oregon Health and Science University.
M. Pavel is in Biomedical Engineering and Medical Informatics at
Oregon Health and Science University (OHSU) Tamara Hayes is Assistant
Professor in Biomedical Engineering at OHSU,
Deniz Erdogmus is Assistant Professor in Biomedical Engineering and
Computer Science and Electrical Engineering at OHSU
Ann Tsay is Research Associate in Biomedical Engineering at OHSU,
Nicole Larimer Research Assistant in Biomedical Engineering at OHSU,
Holly Jimison is Associate Professor in Medical Informatics and
Biomedical Engineering at OHSU
John Nutt is a Professor in Neurology at OHSU.
of symptomatic therapies on motor function throughout the
day using diaries filled out by study subjects. Further,
continuous longitudinal measurements would be mare
accurate way to estimate the effects of treatments that are
hypothesized to alter the progression of a motor disorder.
Our approach to the problem of assessment is based on a
combination of neural informatics and sensor technology.
Neural Informatics is a collection of computer-based
methods that address issues at the intersection of neural
engineering, neuroscience and clinical practice. The
methods include modeling clinically relevant aspects of
neurological states of both individuals and populations. In
our preliminary studies as well as those from other
laboratories, the variability of the various metrics appears to
be as important as the average values. For example,
variability in mobility measures, such as gait velocity or
stride length, have been shown to correlate with age, and
with dementias, such as those associated with Alzheimer’s
Disease [1]. Motor pattern generating mechanisms and gait
velocity appear to be useful predictors of future cognitive
decline [2, 3]. The goal of our approach is to replace the
occasional sampling of cognitive and motor function using
clinic-based control tests with continuous observations in
the patients’ natural environments. A system that can assess
aspects of mobility on a continuous basis can, of course, be
used to assess the variability of these measures.
In this paper, we describe an approach to the unobtrusive
measurement of gait velocity and its variability based on
continuous monitoring of the PD patients in their homes. In
particular we extend our prior work [6] by incorporating a
simple dynamic model of the movements of the individuals
in their dwellings.
II. UNOBTRUSIVE MEASUREMENT OF GAIT VELOCITY
The system for the unobtrusive measurement of gait
comprises two components that will be described in the
following two sections: A) a sensor system for sensing and
collecting the raw data, and B) a set of algorithms that
estimate the parameters of interests from the raw data.
A. Sensor System
One of the most important requirements of the sensor and
assessment system is its unobtrusive or minimally intrusive
nature [6] as well as its economical feasibility. In order to
develop a system that is minimally intrusive, we have been
Continuous Assessment of Gait Velocity in Parkinson’s Disease from
Unobtrusive Measurements
Misha Pavel, Member, IEEE, Tamara Hayes, Member, IEEE, Ishan Tsay,
Deniz Erdogmus, Member, IEEE, Anindya Paul, Member, IEEE,
Nicole Larimer, Holly Jimison, Member, IEEE, John Nutt
T
Proceedings of the 3rd International
IEEE EMBS Conference on Neural Engineering
Kohala Coast, Hawaii, USA, May 2-5, 2007
SaE1.6
1-4244-0792-3/07/$20.00©2007 IEEE. 700
investigating approaches that would be affordable by a large
number of patients and their families. For example, we have
been investigating systems based on passive infrared sensors
(PIR) and contact switches that would be deployed in a
similar manner as are the components used in many security
systems.
The general architecture installed in a typical home is
shown in Fig. 1. When a sensor detects the presence of a
moving human body at the normal body temperature and the
motion signal exceeds a fixed threshold, it fires. There are
various details that control the firing, such as the refractory
period of the sensor following a firing, but a discussion of
these is beyond the scope of this paper. In general, the
inference of the gait velocity is based on the time that it
takes to traverse from one part of the patient’s home to
another – this approach, in conjunction with semi-Markov
models was described previously in an article by Pavel et al.
in 2006 [7].
In some dwellings it is possible to make the
measurements of speed of walking more directly by taking
advantage of the layout. In particular, if the residence has a
hall or a corridor, we would place three modified PIR
detectors the hall in a row as shown in Fig. 1. The PIR
motion detectors placed in the “test area”, i.e., the hall, were
modified to restrict their field of view to 4o. The PIR
monitoring system is using a simple wireless communication
network in order to collect the data. The main data relevant
to monitoring mobility consist of records of PIR motion
detectors firing events.
In dwellings with multiple residents, it is necessary to
identify the particular individual associated with different
events recorded from the PIR motion detectors. In this
study, we used a commercially available RFID location
tracking system for this purpose (HomeFree, Inc). Each
individual residing in the same residence wore a small RFID
device in the form of a watch that emits periodically – every
4 seconds – a signal received by three or more base stations.
B. Inference Algorithms
The unobtrusive nature of the sensor system is inherently
plagued with considerable uncertainties arising from the fact
that the measured phenomenon, e.g. gait velocity is only
indirectly related to the sensed data. In order to compensate
for this, we base our inference on a fusion of information
from a set of passive infrared detectors, contact switches and
active radio frequency identification (RFID) system.
As noted above, the incorporation of the RFID system is
essential for inference in dwellings with multiple residents.
Such was the case in a recent pilot study of a small number
of patients with Parkinson’s disease and their spouses that
served as control subjects.
The measurement of speed of walking in the test area is a
trivial problem whenever an observation consists of the
three detectors firing in one of two temporal orders
consistent with a particular direction of the movement. In
those cases, the time between the first and the third detector
events is taken as the time to walk the distance between
detectors. The difficult problem is to infer the identity of the
walking individual.
Our original notion was that the received signal strength
indicator (RSSI) would provide sufficient information to
determine the locations of each individual. However, this
was not possible due to the variability of the RSSI signal
and its lack of monotonicity with the distance. In our prior
work [6], this problem was addressed by static modeling of
the RSSI distribution over the dwelling, and the use of the
expectation-maximization (EM) algorithm to best estimate
the individual associated with the motion detector events
[9,10]. Despite its fairly successful deployment, further
improvements could be achieved by adding constraints due
to the sequential dependencies – dynamics – of the moving
individuals.
The general approach is to determine the likelihood of
each individual resident being in the test area – a similar
approach to [6] – combined with a dynamic model based on
the assumption that the movements of an individual could be
described by a simple hidden Markov model (HMM) shown
in Fig. 2.
In particular, the HMM developed for the inference was
assumed to consist of 4 unobservable states described by
Fig. 1. Example of a part of a residence with a
number of PIR sensors, RFID receiver stations and
the test area.
Else
where
Test
Area
Left Right
Else
where
Test
Area
Left Right
Fig. 2 Hidden Markov model representing the
dynamics of the patient in his residence.
701
locations in relation to the test area, namely:
1. Left of the test area
2. Right of test area
3. At the test area
4. Other – Elsewhere
The transition probabilities jk
p
between each pair of states
are constrained by the direction of the patient’s movement as
sensed by the PIR motion detector sequences – left to right
and vice versa and the general topology of the HMM is
shown in Fig. 2. The transition probabilities were
determined using the occupancy of the different parts of the
dwelling assessed by the cumulative number of motion
detector events in each part of the house. Table 1 lists an
example of the transition probabilities used in conjunction
with the house diagram shown in Fig. 1.
TABLE 1
EXAMPLE OF TRANSITION PROBABILITIES
Left Test Right Other
Left 0.20 0.60 0.00 0.20
Test 0.30 0.20 0.50 0.00
Right 0.00 0.33 0.33 0.33
Other 0.25 0.00 0.25 0.50
The notation to describe the inference algorithm is similar
to that used in [6]. The observable outputs, R in each state
are vectors of the RSSI values recorded by each receiver or
base station in the residence. The probability density of the
observable RSSI are given by
()
|
i
f
Rq, where q is the state
in the HMM and i is the individual. These probability
density functions were estimated using a Gaussian mixture
model (GMM) with parameters estimated using the
expectation-maximization approach, from calibration data
gathered during the initial installation of the sensor system.
The calibration RSSI data were obtained by collecting RSSI
data from each “significant” location in the patient’s
dwelling, as identified by the patient or the spouse. For the
purpose of this study, each resident is associated with a
particular HMM and these individual HMMs are treated as
statistically independent.
III. RESULTS
The data collected in the pilot study from 6 houses were
used to examine the applicability of this approach. In this
presentation we illustrate the approach on the data from one
Fig. 3. Example of results from one house with a Parkinson’s patient (lower graph) and a control subject (upper
graph). The abscissa is the date of each observation and the ordinate is the time it takes to walk along the test area.
The three different sets of data correspond to the 20, 50, and 80 percentiles of walking times. The missing data
indicate that the corresponding individual was not in the residence. The data are computed using 7 day moving
id
702
of the houses. The data from the patients’ dwellings were
processed whereby the events form the motion detectors in
the test area were used to identify all the instances when the
three detectors fired in one of the temporal orders
corresponding to rightward or leftward motion (ignoring
partial sequences). For each time t associated with the first
detector event, the sequence of RSSI samples was used
()()()
() ( ) ( ) ( )
{3, 2, ,
,,2,3}
Rt Rt Rt
Rt Rt Rt Rt
=−Δ −Δ −Δ
+Δ + Δ + Δ
R
to determine the most likely sequence of states consistent
with the observed RSSI. The likelihood of any particular
sequence of states
{}
12 7
,,... ,
iqq q=Q for the i-th individual
is given by
() { }
()
()
()
1
6
31 ,1 1
3
1
Pr |
||,
ii
qi t kk i k
tk
k
fR q p fR q
λ
π
−+ =
+Δ −
=
=
=
RRQ
where q
π
is the prior probability of the state 1
qand ,1kk
p
+
is
the transition probability from state k to state k+1. Using
Viterbi search, the inference algorithm found, for each
individual, the most likely sequence of states *
i
Q given the
RSSI observations. Since the identity of the walking
individual is not known with certainty, the overall
distribution )(tg of the observed times to walk is a mixture
of the distributions associated with each individual,
() ()
1
,
N
ii
i
g
tgt
α
=
=
where i
is the probability that the observation is associated
with the i-th individual. Conversely, given the probability
that a particular measurement is associated with the i-th
individual, it is possible to estimate the expected value and
the variance of the time to walk distribution for that
individual using the probabilities derived from the HMM. In
particular, using a Bayesian estimation procedure with
uniform priors, the estimate of the expected value for the
time to walk for the i-th individual is given by:
[]
()
,iitit
t
ET w T=R
Where ,it
T is the walking time measurement, wi is a weight
determined as follows: wi is zero if *
i
Qdoes not contain test
q
and
()
()
it
i
j
t
j
w
λ
λ
=
R
R
for all sequences that contain the state test
q, corresponding
to the test area. In other words, the weight is determined by
the relative likelihood of each individual walking in the test
area.
An example of the results from one house occupied by a
Parkinson’s patient and his spouse is shown in Fig. 3. The
distribution of walking times for the i-th individual was
computed using the probability estimates that a given
measurement came from the i-th individual. The triangles
correspond to the median estimates. The data indicate higher
variability of the walking times of the Parkinson’s patient..
IV. CONCLUSION
We have developed a technique to reduce the uncertainty
associated with unobtrusive measurement of mobility with
multiple individuals in a single dwelling. We have
demonstrated that a simple 4 state HMM with minimal
training can incorporate the dynamic aspects of the
sequential data. Although the application of this approach to
the data from our pilot study appears to be promising, the
real evaluation of this approach would require a data set
with known ground truth. Alternatively, there are additional
enhancements of this approach that would improve the
inference; for example, including a coupling between the
HMMs corresponding to each individual would impose
additional constraints and probably improve the inference.
ACKNOWLEDGMENT
We thank Jeff Kaye for his leadership in the development
of related approaches in the monitoring of elders and John
Hunt for his engineering and technical expertise and advice.
REFERENCES
[1] P. L. Sheridan, J. Solomont, N. Kowall, and J. M. Hausdorff,
"Influence of executive function on locomotor function: divided
attention increases gait variability in Alzheimer's disease," J Am
Geriatr Soc, vol. 51, pp. 1633-7, 2003.
[2] R. Camicioli, D. Howieson, B. Oken, G. Sexton, and J. Kaye, "Motor
slowing precedes cognitive impairment in the oldest old," Neurology,
vol. 50, pp. 1496-8, 1998.
[3] R. Camicioli, M. M. Moore, G. Sexton, D. B. Howieson, and J. A.
Kaye, "Age-related brain changes associated with motor function in
healthy older people," J Am Geriatr Soc, vol. 47, pp. 330-4, 1999
[4] T. L. Hayes, M. Pavel, and J. A. Kaye, "An unobtrusive in-home
monitoring system for detection of key motor changes preceding
cognitive decline," presented at 26th Annual International Conference
of the IEEE Engineering in Medicine and Biology Society, San
Francisco, CA, 2004.
[5] T. Hayes, M. Pavel, P. K. Schallau, and A. M. Adami, "Unobtrusive
monitoring of health status in an aging population.," presented at 5th
International Conference on Ubiquitous Computing, Seattle,
Washington., 2003.
[6] T.L. Hayes, M. Pavel, A. Adami, N. Larimer, A. Tsay and J. Nut,
“Distributed healthcare: Simultaneous assessment of multiple
individuals, Pervasive Computing”, 6 (1), 36-43, 2007.
[7] M. Pavel, T. L. Hayes, A. Adami, H. B. Jimison, and J. Kaye,
"Unobtrusive assessment of mobility," presented at 28th Annual
International Conference of the IEEE Engineering in Medicine and
Biology Society, New York, NY, 2006.
[8] R. B. Postuma, , T. Arenovich, A. E. Lang, Does severity of
Parkinson's disease vary according to season? Movement Disorders,
Volume 20, Issue 4 ,2004,pp 476 – 479
[9] A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from
incomplete data via the EM algorithm," Journal of the Royal
Statistical Society, vol. 39, pp. 1-39, 1977.
[10] M. Jordan and R. Jacobs, "Hierarchical mixtures of experts and EM
algorithm," Neural Computation, vol. 5, pp. 181-214, 1994.
703
... The few studies that have attempted continuous, ambient measurement in the home have shown that the results can be correlated with, for example, cognitive decline [18]. However, the technology used in these studies does not lend itself to non-experimental deployment, as typically it involves multiple devices and fixed installation [12,16,17,19]. A wearable solution is a possibility, but among older people adherence to wearables can be low [20] or their use abandoned entirely [21]. ...
... Further trials with the device are required, with more participants measured over a longer period of time to increase the likelihood that some will experience healthrelated changes in walking speed. Nonetheless, this initial study suggests the sensor can generate data comparable with that of continuous home-based walking speed systems [12,16,17,19], but with a device of much smaller physical size, fewer operating constraints, greater ease of installation, and likely lower cost, all of which increase its potential to constitute part of a widely applicable and cost-effective service for the health and care sector in the near future. ...
Article
Full-text available
BACKGROUND Walking speed predicts important clinical outcomes in older adults and is one of the most significant indicators of frailty. OBJECTIVE To test whether it is feasible to measure walking speed frequently and unobtrusively in the home. METHODS A longitudinal feasibility study was conducted comprising the installation and monitoring of continuous measurement walking speed sensors in twenty frail older adults’ homes for a period of twelve weeks (eighteen participants completed the study). Manual walking speed, frailty level and health status were measured at four-weekly intervals. Qualitative interviews were conducted at the end of the study to assess participants’ attitudes to the sensors and to the concept of continuous in-home walking speed measurement. RESULTS There was a high degree of variance to the number of walking speed measurements recorded by each participant’s sensor (median 1942.39, range 2-3617). Participants indicated acceptability of both the sensor within the home and the concept of in-home walking speed measurement. CONCLUSIONS Where regular measurement was achieved, the results indicate that walking speed might be better viewed as a distribution rather than a single figure, taking into account the natural variation to walking speed in daily life. This study demonstrates the feasibility of continuous ambient in-home walking speed monitoring of older adults with a low-cost, easily deployed device.
... Broadly the research was into different areas including the development of algorithms and techniques to diagnose or monitor the progression of disease, wearable devices and sensors and their role for PD diagnosis and monitoring, and the speech based solutions pertaining to PD. The algorithms or techniques were explored in reference [1][2][3][4]6,7]. The techniques or algorithms focused by these research papers include Probabilistic Neural Network (PNN) and its variants, rule based decision algorithm, weighted fuzzy membership functions, Artificial Neural Networks (ANNs) and Support Vector Machines (SVM), Evolutionary Algorithms (EL), and algorithms based on Hidden Markov Model (HMM) [1][2][3][4]6]. ...
... Pavel et al. studied patient's movements to know the characteristics of PD [7]. They proposed a set of algorithms that are used to assess the neurological state of the people with PD. ...
Article
Full-text available
Parkinson’s disease (PD) is the second highest neurodegenerative disease that impairs speech besides causing bodykinesia, postural instability, rigidity and tremor. From the present research works it is understood that the disease is the result of lack of dopamine in brain cells. However, its real cause is yet to be established satisfactorily. In this paper we review the present state of the art of the PD including the nature of disease, its characteristics, the treatment, algorithms or techniques available to diagnose or monitor the patients with the disease, sensors and wearable devices being used to help PD patients and physicians. We also explored many speech based solutions to the disease. The essence of our review is that this neurodegenerative disorder needs further research and development of wearable devices that can help patients to lead a normal life. In this paper we provide the summary of findings which leads to continue our research to develop a wearable device with state of the art software that can help PD patients to have better lives.
... New research using data collected in situ is needed to assess the ecological validity of existing findings and aid patients at risk of cognitive impairment. The advent of wearable monitoring devices and other unobtrusive remote sensors 50,51 allows for continuous collection of temporary dense human motor data opening a new avenue for research that may enable early detection of dementia 49 . ...
Preprint
Full-text available
Dementia is one of the key public challenges of this century, with the number of persons with dementia worldwide projected to reach 115 million by 2050. This review aimed to answer whether monitoring of motor performance alone and during a cognitively taxing task (dual-task) is sufficiently sensitive to distinguish between levels of cognitive function (normal function, mild cognitive impairment, dementia) and, thus, appropriate for dementia screening. In the reviewed 15 studies, cognitively healthy controls had a higher dual-task gait speed than persons with impaired cognition (9/12 studies). The difference between dual- and single-task gait speeds (dual-task cost) was lower in health controls (7/8 studies). Such differences were not detected between patients with mild cognitive impairment and Alzheimer's disease. There results suggest that monitoring of dual-task performance may be used in early dementia screening. Diversity in research designs, lack of established statistical and reporting standards prevent meta-analysis of data.
... In order to combat this, there has been increased focused on developing innovative proactive solutions that enable self-management and early intervention to alleviate the burden on healthcare providers and caregivers [3]. One proactive solution is to monitor people's behaviors and mobility during everyday life as opposed to performing controlled and reactive assessments in the context of a lab or specialist clinic [4,5]. ...
Article
Full-text available
Due to the increasing rates of chronic diseases and an aging population, the use of assistive devices for ambulation is expected to grow rapidly over the next several years. Instrumenting these devices has been proposed as a non-invasive way to proactively monitor changes in gait due to the presence of pain or a condition in outdoor and indoor environments. In this paper, we evaluated the effectiveness of a multi-sensor cane in detecting changes in gait due to the presence of simulated gait abnormalities, walking terrains, impaired vision, and incorrect cane lengths. The effectiveness of the instrumented cane was compared with the results obtained directly from a shank-mounted inertial measurement unit. Results from 30 healthy participants obtained while simulating gait abnormalities and walking over different terrains demonstrated the ability of the cane to reliably and effectively discriminate among these walking conditions. Moreover, the results obtained while walking with impaired vision and incorrect cane lengths indicate the ability of cane to detect changes in gait during these scenarios as well.
... With a globally aging population, and the baby-boomer population entering retirement, projected fall rates and healthcare spending are projected to increase unsustainably [4,5]. In order to combat these growing costs, a growing emphasis has been placed on monitoring solutions capable of identifying changes in gait and stability prior to falls, facilitating early intervention and preventing added burden on healthcare system [6][7][8][9]. ...
Article
Full-text available
Individuals with mobility impairments related to age, injury, or disease, often require the help of an assistive device (AD) such as a cane to ambulate, increase safety, and improve overall stability. Instrumenting these devices has been proposed as a non-invasive way to proactively monitor an individual’s reliance on the AD while also obtaining information about behaviors and changes in gait. A critical first step in the analysis of these data, however, is the accurate processing and segmentation of the sensor data to extract relevant gait information. In this paper, we present a highly accurate multi-sensor-based gait segmentation algorithm that is robust to a variety of walking conditions using an AD. A matched filtering approach based on loading information is used in conjunction with an angular rate reversal and peak detection technique, to identify important gait events. The algorithm is tested over a variety of terrains using a hybrid sensorized cane, capable of measuring loading, mobility, and stability information. The reliability and accuracy of the proposed multi-sensor matched filter (MSMF) algorithm is compared with variations of the commonly employed gyroscope peak detection (GPD) algorithm. Results of an experiment with a group of 30 healthy participants walking over various terrains demonstrated the ability of the proposed segmentation algorithm to reliably and accurately segment gait events.
... The system proposed here can be trained to recognise specific patient activities and help researchers identify segments of the passive monitoring data that are most relevant for subsequent analysis. For example, consider patients being passively monitored using smartphones, where researchers wish to assess the effect of some medication on symptoms such as slowness of movement [65] or postural sway [7]. With very few labeled instances of the relevant behaviors, the system proposed here can learn to identify walking and balance behaviors from the continuous, passive sensor data, which will assist researchers into objectively testing their hypothesis. ...
Article
Full-text available
The use of wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the accuracy achievable with such technology is highly reliant on separating the useful from irrelevant sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety of practical challenges, such as recording unexpected user behaviors. These behaviors often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab and affect the accuracy of the subsequent data analysis and scientific conclusions. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data that are sufficiently reliable for further analysis. Combining both parametric and nonparametric signal processing and machine learning techniques, we demonstrate that across 100 subjects and 300 clinimetric tests from three different types of behavioral clinimetric protocols, the system shows an average segmentation accuracy of around 90%. By extracting reliable sensor data, it is possible to strip the data of confounding factors in the environment that may threaten reproducibility and replicability.
... An approach to the assessment of mobility based on passive infrared detectors was examined by Pavel et al. [24]. This system was also extended by active radio frequency identification tags to enable measurements when multiple persons are in the home [23]. Especially for the assessment of the mobility status, some different approaches already exist. ...
Conference Paper
Full-text available
Early detection of changes in mobility associated with functional decline can increase the therapeutic success by prolonging self-determined living. To get an unbiased and high frequently status of the physical performance of the persons at risk, unsupervised assessments of their functional abilities should ideally take place in their homes. Thus, we have developed a minimized unsupervised technical assessment of physical performance in domestic environments. By conducting an exploratory factor analysis, based on the results of 79 study participants with a minimum age of 70 years, we could clarify that common assessment items mainly represent three key parameters of functional performance "mobility and endurance", "strength" and "balance". Consequently, we identified a minimal set of assessment items that is suitable for home-assessments and that, since covering all three parameters, is able to generate clinical meaningful and relevant insights about the functional status. Regarding the parameter mobility, we developed a technical assessment of physical performance for domestic environments, which utilizes short distance walk times assessed via ambient presence sensors as an indicator for potential functional decline. In a field trial over ten months with 20 participants with a mean age of 84.25 years, we could confirm the general feasibility of our approach and the proposed system.
... The system proposed here can be trained to recognize specific patient activities and help researchers identify segments of the passive monitoring data which are most relevant for subsequent analysis. For example, consider patients being passively monitored using smartphones, where researchers wish to assess the effect of some medication on symptoms such as slowness of movement [73] or postural sway [7]. With very few labelled instances of the relevant behaviours, the system proposed here can learn to identify gait and balance behaviours from the continuous, passive sensor data which will assist the researchers into objectively testing their hypothesis. ...
Article
Full-text available
The use of smartphone and wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the clinimetric accuracy achievable with such technology is highly reliant on separating the useful from irrelevant or confounded sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety of practical challenges, such as unavoidable and unexpected user behaviours. These behaviours often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab, and can affect the accuracy of the subsequent data analysis and scientific conclusions. At the same time, curating sensor data by hand after the collection process is inherently subjective, laborious and error-prone. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data which are sufficiently reliable for further analysis. Algorithms which are special cases of this framework for different sensor data types (e.g. accelerometer, digital audio) detect the extent to which the sensor data adheres to the assumptions of the test protocol for a variety of clinimetric tests. The approach is general enough to be applied to a large set of clinimetric tests and we demonstrate its performance on walking, balance and voice smartphone-based tests, designed to monitor the symptoms of Parkinson's disease.
Article
Full-text available
Objectives Validation of an infrared healthcare technology aimed at measuring gait speed in older adults. Design Validation study. Setting Geriatric Department Participants 90 patients from the Falls Unit of the Geriatrics Department for the validation assessment, and 5,328 patients of the Outpatient Clinic under usual care conditions for technology validation. Measurements Walking speed was measured manually with a stopwatch as part of the Short Physical Performance Battery (SPPB), using the GAITRite™ (first, second and mean of 5 walks) and with the Walkway system. Agreement was determined with the Bland-Altman method. Results Mean gait speed with the SPPB, GAITRite™ (first, second and mean of 5 walks) and Walkway were 0.68 m/s, 0.77 m/s, 0.81 m/s, 0.71 m/s, and 0.70 m/s respectively. Pearson correlations between the Walkway system and SPPB, GAITRite™ first walk, GAITRite™ second walk, and GAITRite™ mean of 5 walks were 0.822 (p < 0.001), 0.810 (p < 0.001), 0.824 (p < 0.001), and 0.811 (p < 0.001) respectively. The mean difference between the Walkway system and SPPB was 0.02 m/s and 95% of the values were between 0.29 and −0.26. Mean difference between Walkway system and GAITRite™ second walk gait speed was −0.11 and 95% values were between 0.17 and −0.38. Mean walking speed in 5382 outpatients was 0.65 m/s (range 0.13–1.43; 95%CI 0.6453–0.6568). No security problems or technical measurement errors were found using the Walkway system. Conclusions The Walkway system presented is a valid, easy-to-use, self-implemented device for walking speed measurement in usual clinical practice with older adults.
Article
Full-text available
Eighty-five healthy elderly subjects were prospectively evaluated for 3 years to determine motor differences between those who remain cognitively intact and those who developed cognitive impairment during prospective follow-up. The 18 subjects who developed cognitive impairment had slower finger tapping and took longer to walk 30 feet before or at the time of cognitive impairment. Coordination was more impaired and steps, but not balance, deteriorated more rapidly, independent of other variables.
Article
Full-text available
The existing paradigm of ongoing or posttreatment monitoring of patients through periodic but infrequent office visits has many limitations. Relying on self-report by the patient or their family is equally unreliable. We propose an alternative paradigm in which continuous, unobtrusive monitoring is used to observe changes in physical behavior over time. We highlight the use of this technique for monitoring motor activity that may be predictive of early cognitive changes in the elderly. Initial results using a system of low-cost wireless sensors are presented, together with a discussion of appropriate analyses and interpretation of such data. Using low-cost wireless sensor network coupled with algorithms to detect changes in relevant patterns of behavior, we are able to detect both acute and gradual changes that may indicate a need for medical intervention.
Article
Full-text available
This paper describes a model-based approach to the unobtrusive monitoring of elders in their home environment to assess their health, daily activities, and cognitive function. We present a semi-Markov model representation with automated learning to characterize individual elder's mobility in the home environment. The assessed mobility can be used to characterize the elder's speed of walking and can serve as one of the predictors of future cognitive functionality and the ability of elders to live independently in their home environment.
Article
Full-text available
The use of pervasive technologies to enable continuous patient monitoring and assessment in various setting outside of hospitals, lowering healthcare costs and allowing early detection of problems is discussed. A modified security system technology is a less obstructive alternative for home monitoring. Recent advances in wireless systems provide the basis for a realistic development and deployment of systems to support behavioral monitoring in multiperson homes. Statistical pattern-recognition and machine-learning algorithm integrate noisy and unreliable sensor data with the situation's context and dynamics. A hidden Markov Model can enhance the state estimation provided by modeling only the RSSI probabilities.
Article
S ummary A broadly applicable algorithm for computing maximum likelihood estimates from incomplete data is presented at various levels of generality. Theory showing the monotone behaviour of the likelihood and convergence of the algorithm is derived. Many examples are sketched, including missing value situations, applications to grouped, censored or truncated data, finite mixture models, variance component estimation, hyperparameter estimation, iteratively reweighted least squares and factor analysis.
Article
To identify the MRI imaging findings associated with motor changes in healthy older people. A cross-sectional study. A study of neurologic function in very healthy older people, the Oregon Brain Aging Study. Clinical and MRI data were examined in 50 very healthy older subjects (mean age = 85.1, SD = 7.2 years). Clinical measures (finger tapping, hand opening and closing, steps and time to walk 30 feet and timed standing on one foot) were dependent variables in multiple regression analyses using age and the following MRI measures as independent variables: total brain volume (TBV)/intracranial volume; ventricular volume/TBV; periventricular high signal/TBV; deep high signal/TBV. The number of steps and the time to walk 30 feet were each associated with periventricular high signal (steps: r = .58, P < .001; time: r = .60, P < .001) and ventricular volume (steps: r = .54, P < .001; time: r = .58, P < .001). These associations remained significant after adjusting for age. None of the other clinical variables was associated with the MRI volumes. Gait measures were associated significantly with periventricular high signal and ventricular volume. These CNS changes contribute to the cause of these important markers of aging.
Article
To evaluate how cognitive function and divided attention affect gait in Alzheimer's disease (AD). Cross-sectional intervention study with subjects serving as their own controls. Inpatient unit and outpatient clinic for patients with dementia located at a Veterans Affairs Medical Center. Twenty-eight patients diagnosed with probable AD. Performance of a cognitive task (repeating random digits) while walking. Neuropsychological measures including clock drawing, verbal fluency, and digit span were obtained along with the Clinical Dementia Rating and Mini-Mental State Examination, the measures of dementia severity. Gait speed and stride-to-stride variability of gait rhythm were measured, once during normal walking and once during dual-task walking. During usual walking, subjects walked slowly and with greater gait variability than older adults without AD. Gait speed was significantly reduced (P<.012) and gait variability increased with dual-task walking (P<.007). The effect on gait variability was larger than the effect on gait speed (P<.015). Executive and neuropsychological function were significantly (P<.02) associated with the increased gait variability that occurred when walking with divided attention but not with gait speed or usual, single-task walking measures of gait. Divided attention markedly impairs the ability of patients with AD to regulate the stride-to-stride variations in gait timing. This susceptibility to distraction and its effect on stride time variability, a measure of gait unsteadiness, could partially explain the predilection to falling observed in patients with dementia. The results also support the concept that persons with AD have significant impairments in the cognitive domain of attention and that locomotor function relies upon cognitive, especially executive, function.
Article
In temperate climates, many factors that may influence function in Parkinson's disease (PD) vary according to season. We examined whether severity of PD, as measured by the Unified Parkinson's Disease Rating Scale (UPDRS), varied with the season of evaluation. We found no evidence for seasonal fluctuation in the UPDRS scores, suggesting that, although considerable day-to-day variation may exist in PD, there is little monthly or seasonal variation.
Conference Paper
We present a tree-structured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are generalized linear models (GLIMs). Learning is treated as a maximum likelihood problem; in particular, we present an expectation-maximization (EM) algorithm for adjusting the parameters of the architecture. We also develop an online learning algorithm in which the parameters are updated incrementally. Comparative simulation results are presented in the robot dynamics domain.
Conference Paper
The problem of training a mixture of experts architecture can be treated as a maximum likelihood estimation problem. Both Jacobs et al. (1991) and Jordan and Jacobs (1992) derived learning algorithms by computing the gradient of the log likelihood for their respective architectures. Empirical tests revealed that although the gradient approach succeeded in finding reasonable parameter values in particular problems, the convergence rate was not significantly better than that obtained by using gradient methods in multi-layered neural network architectures. The gradient approach did not appear to take advantage of the modularity of the architecture. An alternative to the gradient approach was proposed by Jordan and Jacobs (1994), who introduced an expectation-maximization (EM) algorithm for mixture of experts architectures. EM is a general technique for maximum likelihood estimation that can often yield simple and elegant algorithms. For mixture of experts architectures, the EM algorithm decouples the estimation process in a manner that fits well with the modular structure of the architecture. Moreover, Jordan and Jacobs (1994) observed a significant speedup over gradient techniques. The author looks at the performance of the hierarchical mixture of experts (HME) architecture trained with EM and a matched backpropagation network on the problem of learning the forward dynamics of a four-joint robot arm. The HME algorithm runs two orders of magnitude faster than backpropagation on this large-scale robot dynamics problem