Mobile Crowd Sensing in Clinical and Psychological Trials – A Case Study
R¨
udiger Pryss, Manfred Reichert, Jochen Herrmann
Ulm University
Institute of Databases and Information Systems
ruediger[email protected],manfred.r[email protected],
Berthold Langguth, Winfried Schlee
University of Regensburg
Clinic and Policlinic for Psychiatry and Psychotherapy
Abstract—Many highly prevalent diseases (e.g., tinnitus,
migraine, chronic pain) are difficult to treat and universally
effective treatments are missing. Available treatments are only
effective in patient subgroups; i.e., medical doctors and patients
have to figure out which therapy might be helpful in the pa-
tient’s situation. Sufficiently large and qualitative longitudinal
data sets, however, would be desirable to facilitate evidence-
based treatment decisions for individual patients. On one hand,
traditional sensing techniques (i.e., clinical trials) have many
merits enabling evidence-based medicine. On the other, they
have inherent limitations. First, clinical trials are very cost-
and labour-intensive. Second, the traditional approach aims at
reducing ecological heterogeneity to enable the investigation of
homogeneous subsamples. Recently, a new paradigm emerged
that offers promising perspectives for collecting large amounts
of longitudinal patient data – Mobile Crowd Sensing. By utiliz-
ing smart mobile devices of a large number of patients, health
information can be gathered from large patient collections
as well as at many different time points and in various real
life environmental situations. In the TrackYourTinnitus project,
we implemented such a mobile crowd sensing platform to
reveal new medical aspects about tinnitus with a particular
focus on the variability of tinnitus over time depending on
the environmental situation. In this paper, the current project
status as well as first lessons learned from running the mobile
application for twelve months are presented. In turn, the lessons
learned are discussed in the context of the new perspectives
offered by mobile crowd sensing in the medical field.
Keywords-mobile crowd sensing, mobile healthcare applica-
tion, tinnitus, tinnitus variablity, clinical trial, psychological
trial
I. INTRODUCTION
With a prevalence rate of 10-15 % of the population,
Tinnitus is a frequent disorder that is difficult to treat
[1]. Major challenges constitute the fact that tinnitus is a
purely subjective sensation that can only be assessed by the
report of the individual patient, the existence of different
subtypes of tinnitus, which are distinct in their clinical
characteristics, their pathophysiology and their response to
specific therapeutic interventions [2], and the intraindivid-
ual variability of the conscious tinnitus perception over
time [3]. In order to address these challenges, we, as a
multidisciplinary research team of psychologists, physicians
and computer scientists, developed a mobile crowd sensing
[4] platform called TrackYourTinnitus1(TYT). It comprises
a website, a backend, and two mobile applications (iOS
and Android apps). The latter track the individual tinnitus
perception by providing two core features: First, patients
have to fill out a specific questionnaire adapted for being
used on smart mobile devices for assessing tinnitus per-
ception characteristics and tinnitus-related parameters during
the daily routine. Second, the smart mobile device records
the environmental sound level, while a patient fills out the
assessment questionnaire.
As the core feature of the TYT mobile crowd sensing
platform, patients are asked to complete tinnitus assessment
questionnaires at different times during the day on a random
basis (up to 5 notifications per day out of 1,440 possible
times). This procedure ensures that patients cannot foresee
the time of being asked and are involved in various daily
situations. Measuring tinnitus at different times of the day
under real-life conditions significantly enhances the ecolog-
ical validity of the clinical assessment.
In Section II, we report on the current status of the TYT
mobile crowd sensing platform. Section III discusses first
lessons learned. Section IV discusses related work and
Section V concludes with a summary and outlook.
II. PROJECT STATUS
Table I presents current project figures (April 2015).
During the twelve months the project has been running we
received 11,095 randomly applied questionnaires. The num-
ber of users increases up to 20 per week. In the beginning,
the apps and the website were only provided in German
language. After three months, we added an English version.
Currently, we realize Spanish, French, Polish and Portuguese
versions. Psychometric validation of questionnaires in these
languages has shown that results are comparable [5].
III. LESSONS LEARNED
Manifold lessons have been learned during the project.
The most important ones are briefly presented. First, in
some user data, we could recognize specific patterns, e.g.,
an interaction of perceived tinnitus loudness with current
1Further information can be found at: https://www.trackyourtinnitus.org
Category Value
Project start 4/2014
Registered users 822
User home countries 75
Reported problems and failures 10
Number of developed questionnaires 4
Programmers 1
Team size 5
Emerged requests for using platform 5
APP downloads iOS 1,045
APP downloads Android 673
Randomly processed questionnaires 11,095
Statistically processed questionnaires 1,583
Totally gathered answers 90,343
Table I: Project Figures
sound environment, current stress level, time of day, or level
of concentration. In turn, these patterns represent a possible
basis to guide patient behavior for in order to reduce tinnitus.
Second, in principle, users are motivated to participate due
to their health impairment. However, more incentives must
be provided to increase user motivation. Most randomly
answered questionnaires were processed by only a small
group of the registered users. We investigated all gathered
data of this group and first results indicate that they severely
suffer from their tinnitus. This experience of a severely
suffering subgroup with high motivation to use the app
clearly indicates the need for innovative forms of diagnostic
assessment and therapeutic management of tinnitus. Hence,
at this early stage, the developed mobile crowd sensing
platform has primarily attracted severely affected tinnitus
patients. For motivating patients who are less severely im-
paired, additional features will be required to increase the
benefit of the app for this patient group.
Third, the requests from other research groups have encour-
aged us to implement features that can be used to customize
the platform to specific needs. Note that these requests
emerged from medical research groups indicating the open-
ness of the medical community to innovative technologies
for patient assessment. If legal and formal aspects (e.g., data
security) can be resolved, the further development towards
a large multi-centric as well as multinational data pool can
be envisioned.
IV. RELATED WORK
Note that mobile crowd sensing technology is still rarely
used in a clinical context. This might be related to legal and
data privacy issues [6], but also to the general resistance
of health systems to adopt innovative data information
technologies. For example, a large amount of patient data
is still paper-based. However, it can be expected that digital
data processing technologies as well as big data technologies
may revolutionize clinical research and clinical practice.
Recently, various mobile applications have been developed
for psychological studies [7]. In order to fully capitalize
their potential, the pure adaption of existing questionnaires
for mobile use will be outperformed by novel concepts for
information collection [8].
In summary, in many different life domains the feasibility of
mobile crowd sensing has been already proven. The medical
field, albeit a theoretically highly promising application for
crowd sensing approaches, seems to be still neglected.
V. OUTLOOK AND SUMMARY
This paper introduced the TYT mobile crowd sensing
platform. We presented the current project status and lessons
learned. First results indicate that patients are actually moti-
vated to use the platform, especially those severely suffering
from tinnitus. Still more incentives and features are required
to increase user motivation and hence to gather more valu-
able data on the different subtypes of tinnitus. Currently, we
are working on two aspects. First, we statistically evaluate
collected data to obtain new insights into the variablity
of tinnitus. Second, we are working on the development
of a sensor framework as well as feedback algorithms to
automatically evaluate patient data. Altogether, using mobile
crowd sensing and its application for psychological and
medical trials offers promising perspectives.
REFERENCES
[1] B. Langguth, “A review of tinnitus symptoms beyond’ringing
in the ears’: a call to action,” Current Medical Research &
Opinion, vol. 27, no. 8, pp. 1635–1643, 2011.
[2] M. Landgrebe, F. Zeman, M. Koller, Y. Eberl, M. Mohr,
J. Reiter, S. Staudinger, G. Hajak, and B. Langguth, “The
tinnitus research initiative (tri) database: a new approach for
delineation of tinnitus subtypes and generation of predictors
for treatment outcome,” BMC medical informatics and decision
making, vol. 10, no. 1, p. 42, 2010.
[3] W. Schlee, J. Herrmann, R. Pryss, M. Reichert, and
B. Langguth, “How dynamic is the continuous tinnitus per-
cept?” in 11th Int’l Tinnitus Seminar, May 2014.
[4] N. Lane, E. Miluzzo, H. Lu, D. Peebles, T. Choudhury, and
A. Campbell, “A survey of mobile phone sensing,” IEEE
Communications Magazine, vol. 48, no. 9, pp. 140–150, 2010.
[5] D. Zeman, “Data issues of the multilingual translation matrix,”
in Proc of the 7th WS on Statistical Machine Translation.
Association for Computational Linguistics, 2012, pp. 395–400.
[6] D. Christin, A. Reinhardt, S. Kanhere, and M. Hollick, “A
survey on privacy in mobile participatory sensing applications,”
Journal of Systems and Software, vol. 84, no. 11, pp. 1928–
1946, 2011.
[7] J. Schobel, R. Pryss, and M. Reichert, “Using smart mobile
devices for collecting structured data in clinical trials: Results
from a large-scale case study,” in IEEE 28th Int’l Symposium
on Computer-Based Medical Systems (CBMS), 2015.
[8] J. Schobel, M. Schickler, R. Pryss, F. Maier, and M. Reichert,
“Towards Process-Driven Mobile Data Collection Applica-
tions: Requirements, Challenges, Lessons Learned,” in 10th
Int’l Conf on Web Information Systems and Technologies, April
2014, pp. 371–382.
