Perspectives of Information-based Methods in Medicine:

An Outlook for Mental Health Care

Jan Kalina

and Jana Zv

arov

1,2

Institute of Computer Science CAS, Prague, Czech Republic

First Faculty of Medicine, Charles University in Prague, Prague, Czech Republic

Keywords:

Information-based Medicine, Psychiatry, Telemedicine, Molecular Genetics, Cognitive Neuroscience.

Abstract:

Information-based medicine represents a concept characterizing the future ideal of medical practice overcom-

ing the limitations of the popular concept of evidence-based medicine. The potential of information-based

medicine is catalyzed by recent development of new technologies and basic research allowing to acquire

a new medical knowledge relevant for an individual patient. The paper is focused on the specialty ﬁeld of

psychiatry. We discuss the challenges for the development of information-based psychiatry from the point of

view of medical informatics together with its speciﬁc barriers and constraints. We discuss the development of

telemedicine tools for psychiatric care, so far making mainly a disappointing experience. Medical informatics

will also play the role in making results of basic research available to the psychiatrist at the point of care. Re-

search results e.g. in molecular genetics or cognitive neuroscience will require to collect and analyze massive

data on an individual patient. If these data are properly combined from various sources and analyzed, they

represent an enormous potential for bringing a new psychiatric knowledge closer to an individual patient. This

may contribute to improving the availability of psychiatric care and bringing its desirable destigmatization and

humanization.

1 INTRODUCTION

The concept of evidence-based medicine (EBM) is

widely accepted as a unifying idea describing the

ideal practice of medicine. In our opinion, current

clinical practice is gradually undergoing improve-

ments towards more advanced ideals described by the

concept of information-based medicine. This vision

of future medicine emerges from the currently popu-

lar concept of evidence-based medicine and goes far

beyond it.

The original concept of evidence-based medicine

(Guyatt et al., 1992) is currently understood as a thor-

ough, unique, and critical use of the best and most

topical proofs in the process of decision making about

the diagnosis, therapy, and prognosis for individual

patients. The practice of evidence-based medicine in-

tegrates the individual clinical expertise of physicians

with the best objective proofs coming from a system-

atically performed research (Sackett et al., 1996). It

includes searching and systematic critical evaluation

of publications with results of clinical research, anal-

ysis of activities, risk analysis, economic analysis of

costs, or analysis of ethical and legal consequences

of using a given approach (Eddy, 1990). Principles

of evidence-based medicine also requires physicians

to demonstrate their capability to use the newest re-

search results and exploit them in their everyday clin-

ical practice.

Within the framework of evidence-based medi-

cine, it is the clinical evidence (i.e. acquired by clini-

cal research) which is understood as the main source

of clinical knowledge. Clinical trials remain to be the

main source of clinical knowledge. However, they

have serious disadvantages, e.g. artiﬁcial conditions

or averaged results obtained by statistical methods for

an averaged (virtual) patient, without taking his/her

individual situation into account (Eddy, 1990). Fur-

ther, properly designed clinical trials with small sam-

ple sizes have been argued to be suitable by propo-

nents of personalized health care (Evans and Ildstad,

2001), i.e. focused on small groups of speciﬁc pa-

tients. In reality, there is however a tendency for clin-

ical trials to be bigger and more expensive.

Current clinical practice is constantly enriched by

quickly emerging new results of basic research. Thus,

the clinical practice converges to an ideal state which

we characterize by the concept of information-based

medicine (Borang

ıu and Purcarea, 2008). This future

Kalina, J. and Zvárová, J.

Perspectives of Information-based Methods in Medicine: An Outlook for Mental Health Care.

DOI: 10.5220/0005771603650370

In Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2016) - Volume 5: HEALTHINF, pages 365-370

ISBN: 978-989-758-170-0

365

ideal of medicine, although difﬁcult be clearly deﬁned

and lying still far ahead, represents a new perspec-

tive paradigm in medicine, going beyond the current

concept of EBM (Guyatt et al., 1992; Sackett et al.,

1996) and overcoming its limitations. The concept

describes the effort to transform the evidence for the

(imaginary) averaged patient towards a real individ-

ual patient based on his/her individual data with clini-

cal as well genetic or metabolic parameters measured

by new technology. It requires to extract information

from massive data sets.

This paper has the following structure. Section 2

presents our expectations that the information-based

medicine will develop also in the area of psychiatry.

Further sections discuss the role of medical informat-

ics in the development of information-based medicine

in the psychiatric ﬁeld, which we call information-

based psychiatry. We discuss its potential and ben-

eﬁts but also unrealistic expectations or speciﬁc bar-

riers slowing down or complicating the development

of information-based psychiatry. Telemedicine as

one of e-health tools contributing to the development

of information-based psychiatry is discussed in Sec-

tion 3. Moreover, expected fundamental results of

the basic research in molecular genetics or cognitive

neuroscience will contribute to the development of

information-based psychiatry as well, as discussed in

Sections 4 and 5. Finally, Section 6 concludes the pa-

per.

2 INFORMATION-BASED

PSYCHIATRY

This section is devoted to the specialty ﬁeld of psychi-

atry and uncovers sources leading to the development

of information-based psychiatry.

Constantly, we can witness a gradual transform

of psychiatry, which is enabled by a vast num-

ber of technological tools recently introduced for

psychiatric care, including telemedicine applications

such as decision support systems (Thornton, 2013).

Information-based psychiatry will have to exploit

available theoretical knowledge acquired in these

tasks of basic (fundamental) research and to draw

conclusions from measurements acquired for an in-

dividual patient, bringing the possibility of efﬁcient

therapy of psychiatric diseases.

Still, only a few results of the basic research

(e.g. in neuroscience or molecular genetics) strongly

contribute to bringing new sources of medical knowl-

edge closer to an individual patient (Hanson and

Levin, 2013; Lech et al., 2014). While intensive atten-

tion is paid to the research of genetic or neurophysi-

ological causes of diseases and mechanisms leading

to their development, the causes of some common

psychiatric diseases remain to be unknown. For ex-

ample, various sorts of psychosis are known to be

caused by biochemical malfunctions of neurotrans-

mitters in the brain, but the exact causes themselves

have not been discovered yet. To give another exam-

ple, Alzheimer disease cannot be currently cured due

to the unknown cause. Other diseases are cured with

sedatives bringing apathy and somnolence, but not re-

moving the cause of the mental disease.

Currently, important sources of data or psychi-

atric knowledge (together with particular examples)

include the following ones.

• Data measured by e-health tools for patient moni-

toring (e.g. non-stop wearable sensors);

• Signals (e.g. analysis of EEG or detection of de-

pression due to voice changes in a speech record

(Chen et al., 2005));

• Functional magnetic resonance imaging (fMRI)

or other brain images (e.g. study of irreversible

physical changes in the brain due to Alzheimer’s

disease or diagnosis of schizophrenia from a facial

image (Dentico et al., 2014));

• Text in natural language (e.g. automatic analy-

sis of unstructured medical reports in the elec-

tronic health record or analysis of computerized

databases);

• Molecular genetic data (e.g. genetic predisposi-

tion to bipolar disorder or mood disorders);

• Voice analysis (e.g. detection of schizophrenia re-

lapse in smartphones applications);

• Social network analysis (e.g. diagnosis of a de-

pression relapse or automatic mood detection of

facebook users;

• Biochemical or biophysical models of the brain

exploiting differential equations;

• Time series (e.g. pharmacokinetical model for

ethanol in the brain of an alcoholic);

• Connection between genes and fMRI brain im-

ages (e.g. genes responsible for the genetic dis-

position for schizophrenia (Liu et al., 2009)).

The fast improvement of technology and rise of

big data of various types and formats from unthink-

able sources have a potential to contribute to clini-

cal usage and thus to a transform of psychiatry. Im-

provements in the effectiveness of therapy and patient

safety are expected exploiting new knowledge ob-

tained from a patient’s data. This may allow to bring

the process of decision making closer to an individual

patient and also to make the therapy efﬁcient, com-

pared to the current state when the therapy of common

diseases aims only at easing the suffering of patients.

For all these reasons, the paradigm of evidence-based

psychiatry should be replaced by deeper ideas going

HEALTHINF 2016 - 9th International Conference on Health Informatics

366

beyond the vision of evidence-based psychiatry. In

any case, the information within information-based

psychiatry should be handled in a holistic approach

(Zv

arov

a, 2014), combining also economic and en-

vironmental aspects of data, information and knowl-

edge.

3 TELEMEDICINE

Numerous telemedicine tools are currently being de-

veloped for psychiatry, exploiting modern e-health

technologies for distant diagnosis, therapy and prog-

nosis. Telepsychiatry enables to offer the psychiatric

care also to patients with substance abuse problems,

who would otherwise dare to search for a classical

therapy. Telepsychiatric or telemental health services

become popular in the United States, where they con-

tribute to transforming the psychiatric care (Deslich

et al., 2013) and help to increase access to mental

health care. Telemedicine tools have the potential to

be used in intensive attention as well as psychiatric as-

sessment. They include videoconsultations between

a psychiatrist and patient or mobile apps for smart-

phones. The aim of this section is to describe the

beneﬁcial impact and drawbacks of decision support

systems in psychiatry.

Decision support systems (DSS) as telemedicine

tools with the aim to offer assistance with clinical

decision-making processes are generally believed to

have a strong potential to improve health care across

all clinical ﬁelds. Because a correct and effective use

of the information has become the basis for the clini-

cal decision making, they contain a statistical compo-

nent combining information from different informa-

tion components and comparing the risk correspond-

ing to different alternatives (van Bemmel et al., 1996;

arov

a et al., 2009).

General advantages of decision support systems in

various clinical ﬁelds can be summarized as follows.

• Potential for improving the quality of provided

care and for generating economic beneﬁts by re-

ducing ﬁnancial costs and saving human resources

(Kalina and Zv

arov

a, 2013),

• More comfort for the physician, a reduction of

stress and more time for the patient,

• The possibility to exploit the level of knowledge

according to the latest research developments in

medicine,

• Useful assistance for a less experienced physician

in a complicated medical case,

• Reduction of the patient risk by reducing the

medication-related errors, reminding the physi-

cian not to omit important diagnostic examina-

tions, warning about side effects or informing the

physician about recent clinical knowledge.

In psychiatry, however, decision support systems

have not become extensively used tools. Various at-

tempts for decision support systems for the diagno-

sis (Bergman and Fors, 2008) and rarely for ther-

apy (Trivedi et al., 2009) have lead to frustrations.

Sometimes, it is claimed that the limitations of de-

cision support systems rest in the technology but

not in the medicine (Deslich et al., 2013). How-

ever, we claim that there are also limitations intrin-

sic in the substance of psychiatry, e.g. due to con-

troversy in classifying psychiatric diseases (Thornton,

2013), vague psychiatric guidelines, or heterogeneity

of symptoms and signs.

4 MOLECULAR GENETICS

Numerous psychiatric disorders including bipolar dis-

order or schizophrenia are largely affected by hered-

ity. The genetic disposition represents a hidden poten-

tial, but it is now evident that there will be a long way

to investigate the hereditary effect on the diseases and

to use the research results to develop a personalized

treatment. The molecular genetic research itself ap-

pears to be only at the beginning of investigating the

genetic causes of common psychiatric diseases. The

aim of this section is to discuss the limitations of the

currently performed molecular genetic studies in the

psychiatry domain and the role of medical informat-

ics in bridging the gap between molecular genetics

and clinical psychiatry.

So far, the beneﬁt of currently available genetic

examinations is very limited, which has been repeat-

edly denoted as frustrating and disappointing (Lohoff,

2010). Psychiatric genetics aiming at using molecu-

lar genetic knowledge in psychiatric care performed

no signiﬁcant progress and the heredity remained to

a large extent unexplained. Only few genes sus-

pect for being connected to psychiatric disorders have

been identiﬁed, but still the discriminative accuracy of

these genes is unlikely to be helpful for clinical util-

ity, although the genes may formally yield statistically

signiﬁcant results (Pirooznia et al., 2012).

The genetic research has not met the enthusiastic

anticipations of psychiatrists yet. We divide the rea-

sons to two groups, common for the whole medicine

and speciﬁc for psychiatry.

• General limitations of molecular genetics studies

– General limitations of the technology of gene

expression studies, genome-wide association

studies (sequencing the DNA) (Daber et al.,

Perspectives of Information-based Methods in Medicine: An Outlook for Mental Health Care

367

2013) or enrichment analysis searching for ex-

plaining the biological meaning of a group of

genes (Schizophrenia Working Group of the

Psychiatric Genomics Consortium, 2014).

– Insufﬁcient validation of the results (Hasman

et al., 2011); this is probably the main problem

and the core of the so-called crisis of genomic

medicine (Marshall, 2011).

– Too expensive measurements (even nowadays).

– Too big data to be analyzed reliably by cur-

rently available data mining methods (Kalina,

2014).

• Criticism of recent studies in psychiatry

– Current studies were overly simplistic (Pirooz-

nia et al., 2012).

– Current studies do not take complex biological

processes such as metabolic pathways into ac-

count. Such processes are however distributed

across an entire network of genes being only

subtle at the level of individual genes (Subra-

manian and Simon, 2010).

– Even if the effects of several gene loci were cu-

mulated, the associations among genes may be

more complex than a simple model for the cu-

mulation.

– Controversy of currently available predictive

genetics in psychiatry. For example, a genetic

test for bipolar disorder is offered by commer-

cial companies which is criticized by numer-

ous experts for not being sufﬁciently validated

(Mitchell et al., 2010).

• Speciﬁc limitations of psychiatry

– Commonly, there is no single genetic vari-

ant responsible for the disease (Lohoff, 2010),

the genetic dispositions is highly polygenic,

i.e. caused by a large number of genes with

a small contribution to the total genetic risk (El-

legood et al., 2015).

– Some gene variants are rare (Schizophrenia

Working Group of the Psychiatric Genomics

Consortium, 2014), thus requiring very large

genetic studies (Lohoff, 2010).

– A predisposition may not necessarily lead to the

development of the disease, but life style and

environmental factors play their role.

– The disease may actually develop as a mere

consequence of being diagnosed.

5 COGNITIVE NEUROSCIENCES

Understanding the brain will be crucial for the de-

velopment of information-based psychiatry. It is be-

lieved that many of the following research tasks may

be solved by means of fMRI, which already now of-

fers numerous available techniques to help physicians

to diagnose and treat medical conditions of the brain.

The role of medical informatics within this research

is documented by the fact that it has been designated

as one of six main platforms of the Europe-wide Hu-

man Brain Project. While some experts are critical to

the possibility to understand the brain on a purely bio-

logical basis (Zahourek, 2008), available more holis-

tic approaches can be characterized as rather alterna-

tive from the point of view of current cognitive neu-

roscience, which is involved in the following primary

research aims:

• Searching for a suitable model for the human

brain. Earlier models of the brain had a ﬁxed

point of view according to the organization of

the central nervous system. Such models exploit

the knowledge of speciﬁc functions of individual

parts of the brain. Nowadays, dynamics models

of the brain are found more appropriate, which

are based on large-scale distributed and interac-

tive networks (Duffau, 2011).

• Using fMRI to predict whether a depressed patient

will respond to treatment.

• Using fMRI images as predictors of conversion to

dementia (Whelan and Garavan, 2015).

• The reasons of biochemical malfunctions in the

brain are not discovered and we cannot expect

a single precursor for their explanation.

• An early diagnosis of schizophrenia based on

fMRI of the brain, which is as a highly heritable

disease of unknown cause (Schizophrenia Work-

ing Group of the Psychiatric Genomics Consor-

tium, 2014).

• Investigating principles of spontaneous brain ac-

tivity and especially connection between pairs of

brain parts in the resting state (i.e. resting-state

brain networks). This hot topic in current neu-

roscience contains the open problems of under-

standing of the brain processes at various activ-

ities or searching for a method for an effective

monitoring of the brain. It is believed that mod-

iﬁcations of the resting-state brain networks are

characteristic for schizophrenic patients.

• Robust alternatives to current methods for the

analysis of fMRI images. Neuroimaging is known

to be highly sensitive to outliers due to measure-

ment errors and complicated structure of acquir-

ing the images. Robust procedures resistant to the

presence of noise in the images have been pro-

posed based on M-estimation (Wager et al., 2005),

while more robust alternatives to severely outly-

ing measurements (Kalina, 2012) would be desir-

able.

HEALTHINF 2016 - 9th International Conference on Health Informatics

368

6 CONCLUSIONS

This paper presents our view of the ideals of

information-based medicine, far extending the cur-

rent ideals of evidence-based medicine. We believe

that the concept of information-based medicine has

a potential to become a popular buzzword in the fu-

ture. In general, information-based approaches have

spread already beyond medicine, e.g. to the concept

of information-based policy in political and human

sciences (Prakash and Potoski, 2012), where they re-

place the concept evidence-based policy.

In psychiatry, just like as in other clinical ﬁelds,

the concept of information-based medicine expresses

the potential to use new sources of data and knowl-

edge to improve the everyday health care. The past

decades teach us that new knowledge becomes in-

troduced to standard psychiatric care slower com-

pared to other clinical ﬁelds. Still, new results of ba-

sic research together with e-health technologies have

an enormous potential to improve the health care

quality, patient safety as well as reduction of ex-

penses. These new results together with new tools

lead us to describing the vision of psychiatric care by

the concept of the information-based psychiatry. This

paper describes the role of medical informatics in the

process of development of information-based psychi-

atry.

However, we must be aware of speciﬁc features

of psychiatry which represent serious limitations, bar-

riers or drawbacks for the smooth development of

information-based psychiatry. This paper discusses

such speciﬁc features of psychiatry. We also discuss

the current state of the art of basic research in ﬁelds

important for the transform of psychiatry towards the

information-based psychiatry. Important tasks in the

process of development of information-based psychi-

atry include utilizing big data for an individual patient

and their combination with new knowledge acquired

by basic research. Other irreplaceable tasks include

computer applications on various levels from the low-

est ones (data storage and integration) up to using ad-

vanced tools of multivariate statistics and data mining

for analyzing big data.

All these aspects together with desirable organi-

zational changes of the psychiatric care are necessary

(but not sufﬁcient) tools endorsing the realization of

the ideals of the paradigm of information-based psy-

chiatry. Its potential is to combine data available from

various sources, to analyze them and to bring the re-

sults as a new psychiatric knowledge closer to the pa-

tient allowing an improved availability, destigmatiza-

tion and humanization of psychiatric care for an indi-

vidual patient.

ACKNOWLEDGEMENTS

The work was ﬁnancially supported by the Neuron

Fund for Support of Science.

REFERENCES

Bergman, L. G. and Fors, U. G. H. (2008). Decision support

in psychiatry–A comparison between the diagnostic

outcomes using a computerized decision support sys-

tem versus manual diagnosis. BMC Medical Informat-

ics and Decision Making, 8:1–10.

Borang

ıu, T. and Purcarea, V. (2008). The future of

healthcare–Information based medicine. Journal of

Medicine and Life, 1:233–237.

Chen, H., Fuller, S. S., Friedman, C., and Hersh, W. (2005).

Medical informatics: Knowledge management and

data mining in biomedicine. Springer, New York.

Daber, R., Sukhadia, S., and Morrissette, J. J. (2013).

Understanding the limitations of next generation se-

quencing informatics, an approach to clinical pipeline

validation using artiﬁcial data sets. Cancer Genetics,

206:441–448.

Dentico, D., Cheung, B. L., Chang, J.-Y., Guokas, J.,

Boly, M., Tononi, G., and van Veen, B. (2014). Re-

versal of cortical information ﬂow during visual im-

agery as compared to visual perception. NeuroImage,

100:237–243.

Deslich, S., Stec, B., Tomblin, S., and Coustasse, A.

(2013). Telepsychiatry in the 21st century: Trans-

forming healthcare with technology. Perspectives in

Health Information Management, 10.

Duffau, H., editor (2011). Brain mapping: From neu-

ral basis of cognition to surgical applications, Wien.

Springer.

Eddy, D. M. (1990). Practice policies: Where do they come

from? Journal of the American Medical Association,

263:1265–1275.

Ellegood et al., J. (2015). Clustering autism: Using neu-

roanatomical differences in 26 mouse models to gain

insight into the heterogeneity. Molecular Psychiatry,

20:188–215.

Evans, C. H. and Ildstad, S. T., editors (2001). Small

clinical trials: Issues and challenges, 2001. National

Academy Press.

Guyatt, G., Cairns, J., and Churchill et al., D. (1992).

Evidence-based medicine: A new approach to teach-

ing the practice of medicine. Journal of the American

Medical Association, 268:2420–2425.

Hanson, A. and Levin, B. L. (2013). Mental health infor-

matics. Oxford University Press, Oxford.

Hasman, A., Ammenwerth, E., Dickhaus, H., Knaup, P.,

Lovis, C., Mantas, J., Maojo, V., Martin-Sanchez,

F. J., Musen, M., Patel, V. L., Surjan, G., Talmon, J. L.,

and Sarkar, I. N. (2011). Biomedical informatics–a

conﬂuence of disciplines? Methods of Information in

Medicine, 50:508–524.

Perspectives of Information-based Methods in Medicine: An Outlook for Mental Health Care

369

Kalina, J. (2012). Implicitly weighted methods in robust

image analysis. Journal of Mathematical Imaging and

Vision, 44:449–462.

Kalina, J. (2014). Classiﬁcation methods for high-

dimensional genetic data. Biocybernetics and

Biomedical Engineering, 34:10–18.

Kalina, J. and Zv

arov

a, J. (2013). Decision support sys-

tems in the process of improving patient safety. In

Moumtzoglou, A. and Kastania, A., editors, Bioinfor-

matics: Concepts, Methodologies, Tools, and Appli-

cations, pages 1113–1125. IGI Global, Hershey.

Lech, M., Song, I., Yellowlees, P., and Diederich, J., ed-

itors (2014). Mental health informatics , New York.

Springer.

Liu, J., Pearlson, G., Windemuth, A., Ruano, G., Perrone-

Bizzozero, N., and Calhoun, V. (2009). Combining

fMRI and SNP data to investigate connections be-

tween brain function and genetics using parallel ICA.

Human Brain Mapping, 30:241–255.

Lohoff, F. W. (2010). Overview of the genetics of ma-

jor depressive disorder. Current Psychiatry Reports,

12:539–546.

Marshall, E. (2011). Human genome 10th anniversary:

Waiting for the revolution. Science, 331:526–529.

Mitchell, P., Meiser, B., Wilde, A., Fullerton, J., Donald, J.,

Wilhelm, K., and Schoﬁeld, P. (2010). Predictive and

diagnostic genetic testing in psychiatry. The Psychi-

atric Clinics of North America, 33:225–243.

Pirooznia, M., Seifuddin, F., Judy, J., Mahon, P., Bipolar

Genome Study (BiGS) Consortium, Potash, J., and

Zandi, P. (2012). Data mining approaches for genome-

wide association of mood disorders. Psychiatric Ge-

netics, 22:55–61.

Prakash, A. and Potoski, M. (2012). Voluntary environmen-

tal programs: A comparative perspective. Journal of

Policy Analysis and Management, 31:123–138.

Sackett, D., Rosenberg, W. M. C., Gray, M. J. A., Haynes,

B. R., and Richardson, W. S. (1996). Evidence based

medicine: What it is and what it isn’t. BMJ, 312:71–

72.

Schizophrenia Working Group of the Psychiatric Ge-

nomics Consortium (2014). Biological insights from

108 schizophrenia-associated genetic loci. Nature,

511:421–427.

Subramanian, J. and Simon, R. (2010). Gene expression-

based prognostic signatures in lung cancer: Ready for

clinical use? Journal of National Cancer Institute,

102:464–474.

Thornton, T. (2013). Clinical judgment, tacit knowledge,

and recognition in psychiatric diagnosis. Oxford

Handbooks Online, Oxford.

Trivedi, M. H., Daly, E. J., Kern, J. K., Grannemann, B. D.,

Sunderajan, P., and Claassen, C. A. (2009). Barri-

ers to implementation of a computerized decision sup-

port system for depression: An observational report

on lessons learned in real world clinical settings. BMC

Medical Informatics and Decision Making, 9:1–9.

van Bemmel, J. H., Helder, J. C., Sollet, P. C. G. M., and

ten Bergen, S. C. (1996). Handbook of medical infor-

matics. Bohn Staﬂeu van Loghum, Houten.

Wager, T. D., Keller, M. C., Lacey, S. C., and Jonides, J.

(2005). Increased sensitivity in neuroimaging analy-

ses using robust regression. NeuroImage, 26:99–113.

Whelan, R. and Garavan, H. (2015). When optimism hurts:

Inﬂated predictions in psychiatric neuroimaging. Bio-

logical Psychiatry, 75:746–748.

Zahourek, R. P. (2008). Integrative holism in psychiatric-

mental health nursing. Journal of Psychosocial Nurs-

ing and Mental Health Services, 46:31–37.

arov

a, J. (2014). Information-based holistic electronic

healthcare. International Journal on Biomedicine and

Healthcare, 2:2–8.

arov

a, J., Vesel

y, A., and Vajda, I. (2009). Data, infor-

mation and knowledge. In Berka, P., Rauch, J., and

Zighed, D., editors, Data mining and medical knowl-

edge management: Cases and applications standards,

pages 1–36. IGI Global, Hershey.

HEALTHINF 2016 - 9th International Conference on Health Informatics

370