Multidisciplinary Research in e-Health: Challenges and Thoughts

Ariella Richardson

, Haya Raz

, Gil Segev

and Sara Rosenblum

Lev Academic Center, Jerusalem, Israel

BGSegev Ltd. (segevlabs.org), Jerusalem, Israel

Haifa University, Israel

Keywords:

e-Health, Classiﬁcation, Decision Support Systems, Health Apps, Multidisciplinary Health Apps, Aging.

Abstract:

This paper attempts to shed some light on challenges encountered when researching e-Health, along with some

thoughts on addressing them. The nature of e-Health requires putting together groups of multidisciplinary re-

searchers. This complex, yet exciting, work environment presents several challenges that should be addressed

in order to enhance e-Health studies. Issues regarding the system design and acceptance create challenges

of their own and are discussed. Further challenges present themselves in aspects related to the data used for

e-Health, some speciﬁc problems in this domain are related to obtaining labeled data for study, privacy issues,

and dataset size. The paper also discusses the analysis of data and whether traditional expert experience is

used or machine learning and data mining methods are preferred. While there is no claim to solve all the

challenges raised, several directions on how to mitigate them and encourage research, in the fascinating area

of e-Health, are suggested.

1 INTRODUCTION

This paper presents a viewpoint on the challenges

faced while researching e-Health. It describes expe-

riences had while researching health related systems

in a multidisciplinary environment. The aim of the

paper is to create discussion and provoke thought on

the challenges researchers face in these domains, and

hopefully by this shed light on directions to be taken

for future studies.

Different types of e-Health systems exist, such as

decision support systems, see (Kawamoto et al., 2005;

Shibl et al., 2013) for a vast survey. Other systems are

aimed at monitoring and rehabilitation such as (Seo

et al., 2015; Zhang et al., 2015; Micallef et al., 2016)

or bridging the distance between the patients to medi-

cal assistance (Nam et al., 2014; Mitchell et al., 2011;

Demaerschalk et al., 2012). While some systems are

speciﬁc to a condition (Richardson et al., 2008; Wey-

mann et al., 2016; Bourouis et al., 2014; Artikis et al.,

2012; Richardson et al., 2019), others try to present a

holistic diagnosis based on various information such

as combining various electronic medical records (El-

Sappagh and El-Masri, 2014) or adding sensor analy-

sis (Richardson et al., 2019; Peleg et al., 2017).

In many areas of research, studies are often per-

formed in very controlled domains, and within spe-

ciﬁc disciplines. In contrast, e-Health requires the ex-

pertise of researchers from multiple areas. The com-

bined nature of these studies presents many of the ini-

tial challenges faced by researchers in e-Health.

The paper describes some of the challenges that

arise from the multidisciplinary nature of the studies,

and point to some of the key aspects creating the com-

plex environment. Some discussion on this can also

be found in (Gr

onqvist et al., 2017; Pagliari, 2007).

Perhaps, the ﬁrst issue that the parties encounter is the

different background knowledge of the various partic-

ipants. This is often followed by differences in the

technical terminology used and might also surface in

the form of differences in research methods and plat-

forms for publication. All of these issues must be ad-

dressed and handled in order for studies of this nature

to succeed while keeping all collaborating parties ac-

tive and contributing.

Unfortunately, even when research teams succeed

in developing e-Health systems, many remain unused.

Sometimes the systems simply don’t do what they

were meant to do and are therefore rejected. But, even

functional systems are often unused. Sometimes it is

the practitioners refusing to adopt the new technol-

ogy, other times it is the patients. The paper points

to the main reasons that systems are not accepted by

practitioners or patients.

250

Richardson, A., Raz, H., Segev, G. and Rosenblum, S.

Multidisciplinary Research in e-Health: Challenges and Thoughts.

DOI: 10.5220/0009517502500255

In Proceedings of the 6th International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AWE 2020), pages 250-255

ISBN: 978-989-758-420-6

As most e-Health systems use data sources of var-

ious kinds, the paper introduces some of the key is-

sues in these domains. The ﬁrst and most important is

obtaining data for study, since without data e-Health

systems are hard to realize. Another key issue is the

privacy of the data which is extra sensitive because of

the type of data used. Other challenges relate to ob-

taining labeled data, the dataset size and the size of

the research groups involved. Some discussion on is-

sues regarding the use of data in e-Health can be also

be found in (Kuo et al., 2014).

The question of what type of analysis to perform

on the data that is used for modeling the system,

or throughout system use raises another set of chal-

lenges. Sometimes expert experience is used in the

system and the question becomes who is an expert and

how to update the system along with growing knowl-

edge. Other alternatives are using statistical analy-

sis or perhaps most common today is the integration

of machine learning and data mining methods into e-

Health systems. Challenges regarding how to preform

this integration are discussed.

Finally, some thoughts on how to contribute to

future studies on e-Health are proposed, including

thoughts on education, and relevant research plat-

forms.

2 MULTIDISCIPLINARY

RESEARCH CHALLENGES

The ﬁrst and perhaps most important challenge that

arises when discussing e-Health is who are the col-

laborating researchers? In the past it was probably

the technology community that thought of applying

known technology and algorithms to the health do-

main, as these methods were unknown to the medi-

cal community. However, as technology developed

and has become a part of everyday life, there is per-

haps a shift to initiation coming from the health ﬁeld

(Pagliari, 2007).

Systems developed by engineers without medical

support are possibly lacking from the health perspec-

tive. These systems were often developed with very

limited knowledge regarding the health domain that

the technology/algorithm was supposedly designed

towards. The was often an underlying assumption that

the ’ﬁne details’ could be ironed out in the future in

the industry. Unfortunately, for many problems this

is not the case, making many studies inapplicable to

real world problems. Furthermore, the ’ﬁne details’

are often what make the problem interesting from an

academic perspective as well. These aspects of the

problem at hand are sometimes incentives to the de-

velopment of new methods algorithms and technolo-

gies.

In contrast to systems initiated by engineers, prac-

titioners are often unaware of available technology or

how to apply it to their problems. Sometimes practi-

tioners lack the understanding of how technology may

be able to assist them and their patients. Other times a

notion of unrealistic ’science ﬁction’ ideas may exist.

Therefore, there is no doubt that e-Health requires

multidisciplinary study that combines knowledge and

methods from various ﬁelds. (Heeks, 2006; Pagliari,

2007; Van Velsen et al., 2013). These may be com-

puter scientists, engineers, doctors and other health

practitioners etc. The joined study becomes a spiral

process where each discipline shares knowledge with

collaborators, enriching them, and enabling them to

proceed to the next level of understanding. In turn,

this often raises deeper issues in each domain, result-

ing in further knowledge been shared between domain

experts. This process repeats itself in an iterative fash-

ion.

While it is clear that multidisciplinary research

is necessary for e-Health, it also creates great chal-

lenges. Different research areas are sometimes worlds

apart and coming together is often a complicated task.

Some of the challenges encountered in multidisci-

plinary study are gaps in:

• Background knowledge

• Terminology

• Research methods and publication

Perhaps, the ﬁrst problem researchers encounter

when addressing multidisciplinary studies is obtain-

ing enough knowledge in the domains outside their

area of expertise. Some degree of understanding of

what tools and methods exist in other domains is crit-

ical to providing a joint solution to a problem. While

the expert from each domain is assumed to have suf-

ﬁcient background and understanding of his area, a

discussion on a joint solution requires learning about

research performed outside the area of expertise.

This brings on the second challenge - terminol-

ogy. Different areas have different sets of terminol-

ogy conventions. Sometimes learning a new set of

terms is as ”simple” as learning new deﬁnitions. Of-

ten, similar terms are used to describe different con-

cepts across areas. This makes understanding each

other even more confusing. The process of learning

about other domains and terms is a continuous pro-

cess that more often than not continues throughout the

whole research process. Further discussion on termi-

nology is also addressed in (Pagliari, 2007)

Aside from understanding each others language

and concepts, conventions regarding research meth-

Multidisciplinary Research in e-Health: Challenges and Thoughts

251

ods and later publication vary across ﬁelds and disci-

plines. Medical scientists use different study setups

to computer scientists. Experimental setups may dif-

fer as do conventions of reporting research studies.

The value of publication in conferences vs. journals

often becoming another obstacle to overcome. The

question of where to publish is sometimes confusing,

some ”pure” venues consider multidisciplinary stud-

ies to be inferior to other studies and while multidis-

ciplinary platforms are increasing they are still less

common than platforms for speciﬁed disciplines.

Despite the aforementioned challenges, many re-

searchers understand the importance of performing

research across domains, and even enjoy the chal-

lenges as they enable expansion of knowledge and en-

able exploring new solutions to interesting problems.

This leads to more and more research platforms be-

coming available, and perhaps even to some changes

in thoughts on how to educate the next generation of

researchers.

3 SYSTEM DESIGN AND

ACCEPTANCE

System design proves to be one of the great chal-

lenges in designing and studying e-Health systems.

The surplus of health related applications and systems

is unbelievable and growing, approximating 40,000

apps in 2013 (Boulos et al., 2014) and 165,000 in

2015 (Terry, 2015). The diversity of conditions that

are covered ranges from everyday diet apps (Recio-

Rodriguez et al., 2016) to critical oncology apps

(de Bruin et al., 2015) and touches on psychiatric

symptoms (Place et al., 2017). Many systems require

the users to actively interact with the application in

order to achieve medical feedback, for example (Seo

et al., 2015; Zhang et al., 2015; Nam et al., 2014),

while others attempt to provide meaningful informa-

tion, without requiring user actions for data collection

and input (Richardson et al., 2019).

However, many of these diverse and interesting

applications are never used. Some of the factors such

as slow adaptation of the traditional healthcare com-

munity, the lack of integration with electronic health

records etc. can be found in (Crockett and Eliason,

2016; Terry, 2015). The main challenges regarding

system development are:

• Design

• Acceptance by practitioners

• Acceptance by patients

As with the development of any system, proper

design is important. When it comes to e-Health this

may be even more important. Deﬁning the aim of the

system, the targeted users, what the scope is, what as-

pects of the system are critical and what should be left

out etc. Liability issues regarding the system must be

addressed. The issue of false alerts verses missing out

on a diagnosis or treatment need to be considered. To

improve on regular system design models (Van Velsen

et al., 2013) suggest a formalization for e-Health sys-

tem design and are recommended for further reading.

Challenges regarding acceptance can be split into

two categories. The ﬁrst is practitioner acceptance.

One of the main parameters found to affect accep-

tance was whether the system interfered with the reg-

ular work-ﬂow (Shibl et al., 2013). Systems that in-

terrupted with regular workﬂow were often rejected.

Surprisingly, ease of use was considered less impor-

tant. Practitioners also favor systems that display in-

formation automatically over search based systems

(Kawamoto et al., 2005), see (Shibl et al., 2013;

Kawamoto et al., 2005) for more details.

The second acceptance challenge relates to the

acceptance by patients. Adoption of health apps is

sometimes compounded by factors such as confu-

sion regarding which app to use. Introducing systems

to ageing communities sometimes creates extra chal-

lenges. Perhaps the most signiﬁcant is the relative

reluctance of older people to adopt new technology.

While one must beware of generalization, as some

mature adults are extremely comfortable with these

technologies, others are not. The reluctance to adopt

new technologies is often complicated by accessibly

issues such as text size, and button size, or even by

cognitive functioning require to use the system. All

these parameters and more, must be considered for

system design.

Despite these challenges, establishing patient self-

monitoring with tools such as mobile apps is impor-

tant for improving patient health (Dobkin and Dorsch,

2011; Writing et al., 2016).

4 DATA RELATED CHALLENGES

In the domain of e-Health most studies require data

for designing the system, validating it or testing it.

The types of data used and the ways in which they are

used is diverse. For example, data might be obtained

from patients and then used to study medical condi-

tions. Systems that use machine learning often use

the data to build their classiﬁcation models. Some-

times data is used to evaluate e-Health tools. Some

key issues regarding the type of data are:

• Obtaining data for study

• Privacy

ICT4AWE 2020 - 6th International Conference on Information and Communication Technologies for Ageing Well and e-Health

252

• Labeled data

• Dataset size

Obtaining data for health studies can be a nontriv-

ial issue. In order to collect data one needs to have

access to a group of subjects with a certain underlying

health issue. These subjects must agree and commit

to data collection. Patients are often hesitant about

sharing their personal data and even after agreement

to contribute, often fail to cooperate over the lengthy

time periods that are often needed for data collection.

For obvious reasons data concerning the health of

patients must be kept under strict privacy conditions.

Issues regarding privacy are often the key reasons to

medical data being unobtainable to researchers.

To complicate matters further, it is very difﬁcult to

obtain labeled data. Labeled data is critical to many

machine learning algorithms. In health domains la-

beled data is usually the tagging of the condition be-

ing studied. But, while unlabeled data is compara-

tively easy to obtain, labeling the data usually requires

manual labeling by trained practitioners. this makes

labeled data much harder to collect, since the labeling

process is time consuming and thus expensive. On top

of this, since labeling is performed by human experts

it may be disputable or inexact. This might result in

disputable results regarding modeling or testing that

are based on the labeling.

There is the question of the dataset size. While

the world is abuzz with ”Big Data” and some med-

ical data is obtainable in large quantities, it is often

difﬁcult to use these datasets for studies. The require-

ments regarding controlled studies that require data

obtained under speciﬁc conditions and/or the need for

labeled data make obtaining large datasets very difﬁ-

cult. A contributing factor is sometimes the research

group size. Big health organizations and research

groups, often have the upper hand regarding access

to data as opposed to smaller groups. This often re-

sults in studies using comparatively small datasets for

research, limiting the choice of tools for data mining,

and perhaps even sometimes inhibiting the validity of

the studies.

5 ANALYSIS CHALLENGES

While some e-Health systems are simply computer-

ized listings with search capabilities, that are impor-

tant in themselves, it is common for systems to use

some analysis. The analysis is sometimes a set of

rules deﬁned by practitioners. However, it is becom-

ing increasingly common, and perhaps almost manda-

tory to include some kind of automated analysis from

ﬁelds such as machine learning. Some possible anal-

ysis methods are:

• Expert experience

• Statistical analysis

• Machine learning

Expert (Practitioners) experience may be present

in different ways. If the system is a Decision Sup-

port System, then the expert considers the output

from the system and them combines it with his prior

knowledge. Alternatively, systems sometimes inte-

grate expert knowledge (perhaps from multiple ex-

perts) within the system decision process. In this the

case there is a vulnerability to differences in opin-

ions between practitioners. A broad survey of Clin-

ical Decision Support Systems along with a detailed

discussion explaining the need for such systems can

be found in (Castaneda et al., 2015).

Standard statistical analysis is often of great use to

building health systems, and evaluating data such as

in (Rosenblum et al., 2003; Rosenblum, 2006). How-

ever it is guided by the analysts assumptions on the

interesting features in the data.

Using methods from machine learning is becom-

ing increasingly common for example: (Artikis et al.,

2012; Richardson et al., 2019; Richardson et al.,

2019) and has great potential. The challenges of using

a machine learning component are vast. The ﬁrst, as

mentioned earlier, is obtaining data for building ma-

chine learning models with. The size of the dataset

greatly impacts the choice of the chosen algorithm.

While neural nets are becoming the most common

way to analyze data, they require large sets of labeled

data, these are often unavailable for health domains.

Another challenge that is especially important

in health domains is the question of explainabil-

ity. Explainability refers to the ability of the user

(practitioner/patient) to understand how the system

works, or makes decisions (Rosenfeld and Richard-

son, 2019). It seems that in health domains this re-

quirement is even stronger than in some other do-

mains. The reason may be the reluctance of practi-

tioners to trust systems where they do not fully un-

derstand the thought process. A survey of how ex-

plainable different types of algorithms are appears in

(Rosenfeld and Richardson, 2019) and is of possible

interest to readers addressing this challenge.

6 LOOKING FORWARD

This paper is by no means a complete list of all chal-

lenges that might be encountered while touching on

e-Health. Rather, it raises discussion on some of these

Multidisciplinary Research in e-Health: Challenges and Thoughts

253

challenges. This wouldn’t be complete without some

thoughts regarding what might be done in the future

in order to help resolve these challenges or at least

assist e-Health researchers in addressing them.

One of the most signiﬁcant ways to address the

complexity of multidisciplinary work is to introduce

it at earlier stages of academic education. The un-

dergraduate level might be the right time to begin

this process. Encouraging courses taught by lectur-

ers from several discipline might be a good step.

Even better is to encourage projects that require co-

operation between students from different disciplines.

This would give the students, tomorrows researchers,

the experience that they need in handling multidisci-

plinary discussions and cooperation techniques.

Building platforms for multidisciplinary study

such as that described by (Gr

onqvist et al., 2017) will

enable both understanding of these challenges and

hopefully also possible solutions. Together with plat-

forms for the presentation of multidisciplinary stud-

ies, such as conferences and journals. These plat-

forms are already becoming more common, and will

enable the discussion of studies in these areas within

the relevant framework in a fashion that is presentable

to researchers with a variety of backgrounds.

Regarding the availability of data with the restric-

tions discussed, this is a sensitive issue, as data is

difﬁcult to obtain and often sensitive to freely dis-

tribute. Deﬁning standards for depersonalizing data

along with the support of data repositories might

prove beneﬁcial. Other ideas remain for further in-

vestigation.

Perhaps the most important point to consider

when looking forward is that despite the challenges

mentioned and perhaps because of them, Studying e-

Health is a very rewarding task. The excitement de-

rived from learning new methods, terms and domains

provides interest to researchers from all areas. The

need to mold and reﬁne familiar research methods

in order to bridge the gaps between areas, enables

the development of new and perhaps improved tech-

niques. Challenges are what make research interest-

ing, and will hopefully continue to advance the sci-

ence in this domain and others.

REFERENCES

Artikis, A., Bamidis, P. D., Billis, A., Bratsas, C.,

Frantzidis, C., Karkaletsis, V., Klados, M., Konstan-

tinidis, E., Konstantopoulos, S., Kosmopoulos, D.,

et al. (2012). Supporting tele-health and ai-based

clinical decision making with sensor data fusion and

semantic interpretation: The useﬁl case study. In

International workshop on artiﬁcial intelligence and

NetMedicine, page 21.

Boulos, M. N. K., Brewer, A. C., Karimkhani, C., Buller,

D. B., and Dellavalle, R. P. (2014). Mobile medical

and health apps: state of the art, concerns, regula-

tory control and certiﬁcation. Online journal of public

health informatics, 5(3):229.

Bourouis, A., Feham, M., Hossain, M. A., and Zhang, L.

(2014). An intelligent mobile based decision support

system for retinal disease diagnosis. Decision Support

Systems, 59:341–350.

Castaneda, C., Nalley, K., Mannion, C., Bhattacharyya, P.,

Blake, P., Pecora, A., Goy, A., and Suh, K. S. (2015).

Clinical decision support systems for improving di-

agnostic accuracy and achieving precision medicine.

Journal of clinical bioinformatics, 5(1):4.

Crockett, D. and Eliason, B. (2016). What is data mining in

healthcare. Insights: Health Catalyst.

de Bruin, J. S., Schuh, C., Seeling, W., Luger, E., Gall, M.,

utterer, E., Kornek, G., Ludvik, B., Hoppichler, F.,

and Schindler, K. (2015). Assessing the feasibility

of a mobile health-supported clinical decision support

system for nutritional triage in oncology outpatients

using arden syntax. Artiﬁcial intelligence in medicine.

Demaerschalk, B. M., Vegunta, S., Vargas, B. B., Wu, Q.,

Channer, D. D., and Hentz, J. G. (2012). Reliability

of real-time video smartphone for assessing national

institutes of health stroke scale scores in acute stroke

patients. Stroke, 43(12):3271–3277.

Dobkin, B. H. and Dorsch, A. (2011). The promise of

mhealth: daily activity monitoring and outcome as-

sessments by wearable sensors. Neurorehabilitation

and neural repair, 25(9):788–798.

El-Sappagh, S. H. and El-Masri, S. (2014). A distributed

clinical decision support system architecture. Journal

of King Saud University-Computer and Information

Sciences, 26(1):69–78.

onqvist, H., Olsson, E. M. G., Johansson, B., Held, C.,

ostr

om, J., Norberg, A. L., Hov

en, E., Sanderman,

R., van Achterberg, T., and von Essen, L. (2017). Fif-

teen challenges in establishing a multidisciplinary re-

search program on ehealth research in a university set-

ting: a case study. Journal of medical Internet re-

search, 19(5):e173.

Heeks, R. (2006). Health information systems: Failure, suc-

cess and improvisation. International journal of med-

ical informatics, 75(2):125–137.

Kawamoto, K., Houlihan, C. A., Balas, E. A., and Lobach,

D. F. (2005). Improving clinical practice using clin-

ical decision support systems: a systematic review

of trials to identify features critical to success. Bmj,

330(7494):765.

Kuo, M.-H., Sahama, T., Kushniruk, A. W., Borycki, E. M.,

and Grunwell, D. K. (2014). Health big data ana-

lytics: current perspectives, challenges and potential

solutions. International Journal of Big Data Intelli-

gence, 1(1-2):114–126.

Micallef, N., Baillie, L., and Uzor, S. (2016). Time to ex-

ercise!: an aide-memoire stroke app for post-stroke

ICT4AWE 2020 - 6th International Conference on Information and Communication Technologies for Ageing Well and e-Health

254

arm rehabilitation. In Proceedings of the 18th Inter-

national Conference on Human-Computer Interaction

with Mobile Devices and Services, pages 112–123.

ACM.

Mitchell, J. R., Sharma, P., Modi, J., Simpson, M., Thomas,

M., Hill, M. D., and Goyal, M. (2011). A smartphone

client-server teleradiology system for primary diagno-

sis of acute stroke. Journal of medical Internet re-

search, 13(2).

Nam, H. S., Heo, J., Kim, J., Kim, Y. D., Song, T. J., Park,

E., and Heo, J. H. (2014). Development of smartphone

application that aids stroke screening and identifying

nearby acute stroke care hospitals. Yonsei medical

journal, 55(1):25–29.

Pagliari, C. (2007). Design and evaluation in ehealth: chal-

lenges and implications for an interdisciplinary ﬁeld.

Journal of medical Internet research, 9(2):e15.

Peleg, M., Shahar, Y., Quaglini, S., Broens, T., Budasu,

R., Fung, N., Fux, A., Garc

ıa-S

aez, G., Goldstein,

A., Gonz

alez-Ferrer, A., et al. (2017). Assessment of

a personalized and distributed patient guidance sys-

tem. International journal of medical informatics,

101:108–130.

Place, S., Blanch-Hartigan, D., Rubin, C., Gorrostieta, C.,

Mead, C., Kane, J., Marx, B. P., Feast, J., Deckers-

bach, T., et al. (2017). Behavioral indicators on a

mobile sensing platform predict clinically validated

psychiatric symptoms of mood and anxiety disorders.

Journal of medical Internet research, 19(3).

Recio-Rodriguez, J. I., Agudo-Conde, C., Martin-

Cantera, C., Gonz

alez-Viejo, M. N., Fernandez-

Alonso, M. D. C., Arietaleanizbeaskoa, M. S.,

Schmolling-Guinovart, Y., Maderuelo-Fernandez, J.-

A., Rodriguez-Sanchez, E., Gomez-Marcos, M. A.,

et al. (2016). Short-term effectiveness of a mobile

phone app for increasing physical activity and adher-

ence to the mediterranean diet in primary care: A ran-

domized controlled trial (evident ii study). Journal of

medical Internet research, 18(12).

Richardson, A., Kraus, S., Weiss, P. L., and Rosenblum,

S. (2008). COACH - cumulative online algorithm for

classiﬁcation of handwriting deﬁciencies. In IAAI’08

Proceedings of the 20th national conference on In-

novative applications of artiﬁcial intelligence, pages

1725–1730.

Richardson, A., Perl, A., Natan, S., and Segev, G. (2019).

A clinical decision support system based on an unob-

trusive mobile app. In 5th International Conference

on Information and Communication Technologies for

Ageing Well and e-Health, pages 167–173.

Richardson, A., Rosenblum, S., and Hassin-Baer, S. (2019).

Multidisciplinary teamwork in the design of dailycog

for evaluating mild cognitive impairment (mci) in

parkinson’s disease. In 2019 International Conference

on Virtual Rehabilitation (ICVR), pages 1–2.

Richardson, A., Shani Ben Ari, and Sinai, M., Atsmon, A.,

Conley, E. S., Gat, Y., and Segev, G. (2019). Mobile

applications for stroke: A survey and a speech clas-

siﬁcation approach. In 5th International Conference

on Information and Communication Technologies for

Ageing Well and e-Health, pages 159 – 166.

Rosenblum, S. (2006). The development and standardiza-

tion of the children activity scales (chas-p/t) for the

early identiﬁcation of children with developmental co-

ordination disorders. Child: Care, Health and Devel-

opment, 32(6):619–632.

Rosenblum, S., Parush, S., and Weiss, P. L. (2003). The

In Air phenomenon: temporal and spatial correlates

of the handwriting process. Perceptual Motor Skills,

96(3 pt 1):933–954.

Rosenfeld, A. and Richardson, A. (2019). Explainability in

human–agent systems. Autonomous Agents and Multi-

Agent Systems, 33(6):673–705.

Seo, W.-K., Kang, J., Jeon, M., Lee, K., Lee, S., Kim, J. H.,

Oh, K., and Koh, S.-B. (2015). Feasibility of using

a mobile application for the monitoring and manage-

ment of stroke-associated risk factors. Journal of Clin-

ical Neurology, 11(2):142–148.

Shibl, R., Lawley, M., and Debuse, J. (2013). Factors inﬂu-

encing decision support system acceptance. Decision

Support Systems, 54(2):953–961.

Terry, K. (2015). Number of health apps soars but use does

not always follow. Medscape Medical News.

Van Velsen, L., Wentzel, J., and Van Gemert-Pijnen, J. E.

(2013). Designing ehealth that matters via a multidis-

ciplinary requirements development approach. JMIR

research protocols, 2(1):e21.

Weymann, N., H

arter, M., and Dirmaier, J. (2016). Informa-

tion and decision support needs in patients with type

2 diabetes. Health informatics journal, 22(1):46–59.

Writing, G. M., Mozaffarian, D., Benjamin, E., Go, A., Ar-

nett, D., Blaha, M., Cushman, M., Das, S., de Fer-

ranti, S., Despr

es, J., et al. (2016). Heart disease and

stroke statistics-2016 update: A report from the amer-

ican heart association. Circulation, 133(4):e38.

Zhang, M. W., Yeo, L. L., and Ho, R. C. (2015). Harness-

ing smartphone technologies for stroke care, rehabili-

tation and beyond. BMJ innovations, 1(4):145–150.

Multidisciplinary Research in e-Health: Challenges and Thoughts

255