=Paper=
{{Paper
|id=Vol-1213/paper7
|storemode=property
|title=Employing time-series forecasting to historical medical data: an application towards early prognosis within elderly health monitoring environments
|pdfUrl=https://ceur-ws.org/Vol-1213/paper7.pdf
|volume=Vol-1213
|dblpUrl=https://dblp.org/rec/conf/ecai/BillisB14
}}
==Employing time-series forecasting to historical medical data: an application towards early prognosis within elderly health monitoring environments==
https://ceur-ws.org/Vol-1213/paper7.pdf
Employing time-series forecasting to historical medical
data: an application towards early prognosis within
elderly health monitoring environments
Antonis S. Billis1 and Panagiotis D. Bamidis1
1
Medical Physics Laboratory, Medical School, Faculty of Health Sciences, Aristotle University
of Thessaloniki
Abstract. This work describes a first attempt to apply time-series forecasting
analysis to health historical data in order to perform prediction of early patho-
logical signs within telehealth applications, such as the Ambient Assisted Liv-
ing environments for the elderly. A benchmark of state-of-the-art learning
methods were applied to a set of artificial time-series data, simulating hyperten-
sive patient profiles, based on blood pressure measurements. Results provided a
fair proof of our initial hypothesis. Based on this first experimentation, our
plans are to further investigate these findings in real –life or lab settings with
seniors, thus proving the usefulness of time-series forecasting as a monitoring
tool and an early prognosis mechanism in telehealth systems.
Keywords: telehealth, smart home, ambient assisted living, support vector ma-
chine, ARIMA models, time series forecasting, neural networks
1 Introduction
Senior citizens suffer nowadays from a wide variety of chronic conditions that re-
duce their independency level and deteriorate their health status [1]. This often hap-
pens due to the fact that they do not receive timely health assessment. In most of the
cases this happens because any change is considered as part of the natural ageing
process; seniors also tend to omit admitting they have a problem, or even of their fear
of being institutionalized [2]. Early prediction of abnormal variation of health pa-
rameters may lead to early diagnosis of chronic diseases and subsequently to better
medical decision-making and planning.
In this respect technology has much to offer the elderly. Recent technological advanc-
es resulted in the equipping of home environments with a plethora of sensors that aim
to improve the seniors' quality of life and increase their independency by providing
alerts in case of emergencies while increasing their socialization [3]. These approach-
es provided significant results in cases of fall detection, inappropriate use of electrici-
ty devices, estimation of participant’s functionality, etc. [4]. However, they have
mainly focused on the detection of life-threatening acute events and they neglected
the significance of slow-varying trends that may influence the health status of senior
citizens [5] at a later time.
31
Time series analysis is a methodology that provides: i) pattern recognition of histori-
cal data (detection of frequent types of sequences) and .ii) forecasting of future values
based on historical trends. There are several time-series forecasting methods known to
the literature, such as exponential smoothing [6], Box-Jenkins seasonal ARIMA mod-
els [7] and neural networks [8].
In this paper, we aim to showcase the use of several state-of-the-art machine learning
algorithms, such as Gaussian Processes, Artificial Neural Networks (ANNs), Support
Vector Machines (SVMs) and Box-Jenkins ARIMA models, with a set of artificially
developed scenarios, relevant to patient models with high risk of hypertension. Our
hypothesis is that one can take advantage of existing time-series forecasting method-
ologies to identify health trends over time and predict early signs of health deteriora-
tion, based on historical sets of health measurements and events.
The ARIMA model has advantages in its well-known statistical properties and ef-
fective (linear) modeling process. However, it may not work well in the presence of
nonlinear relationships. In contrast, support vector machines and artificial neural
networks time series models can capture the historical information by nonlinear func-
tions and thus could prove to be efficient time series forecasting methods because of
their flexible nonlinear mapping ability and tolerance to complexity in forecasting
data.
2 Materials and Methods
In order to benchmark the forecasting methods a number of artificial scenarios
were created. These concerned the simulation of day-to-day variation of diastolic
blood pressure. Blood pressure is a prerequisite to monitoring seniors’ physical health
status progress or deterioration. This clinical parameter is very important since by
monitoring it over a period of time it is possible to identify future risky health situa-
tions, such as hypertension. These situations may subsequently lead to a plethora of
health problems, such as a sudden stroke episode or cardiovascular disease. Based on
norms, an individual is hypertensive if he or she experiences repeatedly an elevated
blood pressure exceeding 140 (systolic) and over 90 mmHg (diastolic).
The test data set consists of ten cases that reflect high risk profiles of seniors. The
scenarios are produced randomly using a normal distribution with a mean diastolic
blood pressure value nearly at the physiological margin of 80 mmHg and standard
variation varying from 1 to 3.
The synthetic data were formed based on a priori knowledge derived from interna-
tional norms, thus corresponding to hypertensive patient profiles. Specifically, the
instances were modeled as a Gaussian process with a standard mean value and varia-
bility. The larger the variability the nosier the time-series is. The algorithms were
tested under small, medium and high variability rates, so to provide cases of gradual
forecast difficulty.
In order to perform time-series forecasting we have used well known machine
learning methods and employed their existing implementations within publicly avail-
able AI suites such as WEKA [10] and Phicast [9]. More specifically, from the
WEKA suite the following learning methods have been applied: GaussianProcesses
(kernel: RBFKernel with gamma parameter set to default value 0.01), SMOreg (ker-
32
nel: RBFKernel with gamma parameter set to default value 0.01) and finally
MultilayerPerceptron (all parameters set to the default values). The parameters of the
ARIMA model were selected as follows: p=1, d=1, q=1, resulting to a ARIMA(1,1,1)
model.
3 Experimentation and results
The experiments compare predicted values with test data provided by the random
artificial scenarios. Initial scenarios were split to two sets: one training set used for
learning, which consisted of 50 instances and a second one which served as the test
set for the evaluation of the forecasting methods. All instances represent measure-
ments taken ideally on a daily basis.
Two experiments were conducted. Firstly, the ARIMA method alone was em-
ployed to forecast future value ranges and then the rest methods were applied to the
same data sets to predict single future values. In the first case the metric used for the
evaluation of the method is the accuracy of the prediction calculated as percentage of
the correctly predicted ranges that the actual value was included and the total amount
of the test set. In the second case, the following standard metrics are calculated: the
Mean Absolute Error (MAE) and the Root Mean Squared Error (RMSE).
An indicative result of the ARIMA prediction algorithm is depicted below (Fig. 1).
Average prediction accuracy resulted to 91.2%.
Fig. 1. Forecast Range vs Actual Values of Diastolic Data (95% prediction intervals)
Table 1 summarizes the evaluation results of the forecasting learning methods As
shown GaussianProcesses learning algorithm provides the least error-prone analysis
among the three. Neural Nets provided the worst forecasting results.
Table 1. Benchmark results of the tested forecasting algorithms
Learning Method Mean Absolute Error (MAE) Root Mean Squared
Error (RMSE)
GaussianProcess 1.798633 2.292558
SVM 2.005342 2.523508
Neural Network 6.061283 7.126667
4 Discussion
In this paper, time-series forecasting was employed to identify early pathological
symptoms based on historical measurements. The clinical utility of forecasting (e.g.
33
vital signs) is of major importance in order to avoid hospitalization and alleviate the
socioeconomical burden for caring, while it may improve significantly life quality of
senior citizens.
Box-Jenkins ARIMA forecasting provides relatively accurate short-term forecasts
regarding future ranges of the monitored variable (blood pressure). SVMs and
GaussianProcessess can provide relatively fair near-future predictions. Preliminary
results on artificial data partially support our initial hypothesis. However, there are
several issues that set limits to the aforementioned results.
AI techniques were applied just in univariate time-series, whereas in most real-life
health problems that elderly people suffer from, tend to be multifactorial. This means
that forecasting a single parameter may not provide sufficient indications of early
disease, since it needs to be investigated under its temporal relation with associative
factors/parameters. Another limitation when it comes to real-life applications is that
these methods require a larger amount of data than may be available within smart
home environments; especially where a small set of unobtrusive sensors will be avail-
able. Also sensor failure may lead to missing data. In order to overcome, such prob-
lems several data imputation techniques may be applied [11].
Future plans of this research include among others: the setup of pilots, where actual
sensors will be placed within a lab setting [13] and several seniors will be recruited to
perform daily life activities for a long enough period so to gather enough historical
data.
The forecasting output will be adaptive in terms of the size of the temporal window
in order to facilitate the expert to estimate the possibility of both short-term events
and long-term future trends. Furthermore, each actual/predicted instance will be
mapped to normal or abnormal class and the classification accuracy will be calculated
based on whether forecasting methods can predict the onset of a pathological condi-
tion at an early stage.
Time-series forecasting could be ideally employed within the context of an ambient
assisted living environment, providing answers as whether we could detect transition
patterns indicative of future health deterioration or timely estimate chronic alterations
in the presence of outliers that may be either due to system (sensors) failure or to
acute events. Combining seniors’ health profile and time-series forecasting analysis,
an intelligent Ambient Assisted Living environment would be able to propose the
adoption of optimal lifestyle patterns according to the user’s needs (acting proactive-
ly). This strategy could combine various non-pharmacological interventions (affec-
tive/cognitive/exer-games), alterations to the diet and/or some simple advice regard-
ing a healthier lifestyle.
5 Conclusion
The reason that motivated us to use time-series forecasting methodologies is that
telehealth monitoring should be able to detect apart from rapid deterioration states or
life-threatening situations also slow-varying chronic conditions and provide early
prognosis. More specifically, cases such as the geriatric depression or cognitive de-
cline are characterized by a gradual impairment that may last for years and will be
hardly noticed by the seniors or their carers, except for late stages where the outcomes
34
of the disease remain irreversible [12]. Initial experiments with artificial data provid-
ed encouraging results. However, real-life experimentation will give us the chance to
further fine-tune existing prediction algorithms and evaluate time series forecasting
on the basis of its accuracy in the health monitoring field of use.
Acknowledgements. The work has been partially funded from the European Union's
Seventh Framework Programme (FP7/2007-2013) under grant agreement no 288532.
For more details, please see http://www.usefil.eu.
References
1. W. Lutz, B.C. O'Neill, and S. Scherbov, “Europe’s population at a turning point”, Science,
vo. 28, no. 299, pp. 1991-1992, 2003.
2. Hayes TL, Pavel M, Kaye JA. An unobtrusive in-home monitoring system for detection of
key motor changes preceding cognitive decline. Proc. of the 26th Annual Intl. Conf. of the
IEEE EMBS, pp. 2480-2483, San Francisco, CA. (2004)
3. M. Popescu, G. Chronis, R. Ohol, M. Skubic, and M. Rantz: An eldercare electronic health
record system for predictive health assessment. Paper presented at: Proceedings of the IEEE
13th International Conference on e-Health Networking, Applications and Services; Colum-
bia, MO; June 13-15, pp. 193-196, 2011.
4. Rantz MJ, Scott SD, Miller SJ, Skubic M, Phillips L, Alexander G, et al. Evaluation of
health alerts from an early illness warning system in independent living. Computers
Informatics Nursing. 31(6):274–280, 2013.
5. T. Hayes, M. Pavel, and J. Kaye, An approach for deriving continuous health assessment
indicators from in-home sensor data. In Technology and aging: Selected papers from the
2007 international conference on technology and aging, vol. 21, pp. 130–137, 2008
6. Winters, P. R. “Forecasting sales by exponentially weighted moving averages.” Manage-
ment Science, 6:324–342., 1960
7. Box GEP, Jenkins GM. Time Series Analysis: Forecasting and Control, 2nd edition. San
Francisco, CA: Holden Day, 1976
8. Cortez, P., Rocha, M., and Neves, J. “Time Series Forecasting by Evolutionary Neural Net-
works.” chapter III, Artificial Neural Networks in Real-Life Applications, Idea Group Pub-
lishing, USA, pages 47–70, 2005
9. Rob J. Hyndman, Anne B. Koehler, Ralph D. Snyder and Simone Grose. A state space
framework for automatic forecasting using exponential smoothing methods
http://www.elsevier.com/locate/ijforecast. (2002).
10. Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, Ian H.
Witten: The WEKA Data Mining Software: An Update; SIGKDD Explorations, Volume 11,
Issue 1, (2009).
11. Shuai Zhang, Sally I. McClean, Member, IEEE, and Bryan W. Scotney Probabilistic Learn-
ing From Incomplete Data for Recognition of Activities of Daily Living in Smart Homes,
IEEE Transactions On Information Technology In Biomedicine, Vol. 16, No. 3, 2012
12. Abellan van Kan, G., Rolland, Y., Nourhashémi, F., Coley, N., Andrieu, S., Vellas, B.,.
Cardiovascular disease risk factors and progression of Alzheimer’s disease. Dementia and
geriatric cognitive disorders 27, 240–6 (2009)
13. Artikis, A., Bamidis, P.D., Billis, A., Bratsas, C., Frantzidis, C., Karkaletsis, V., Klados, M.,
Konstantinidis, E., Konstantopoulos, S., Kosmopoulos, D., Papadopoulos, H., Perantonis, S.,
Petridis, S., Spyropoulos, C.S.: Supporting tele-health and AI-based clinical decision
making with sensor data fusion and semantic interpretation: The USEFIL case study.
International Workshop on Artificial Intelligence and NetMedicine. p. 21 (2012).
35