<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta />
    <article-meta>
      <title-group>
        <article-title>The Use of Modern Information Technology in Medical and Health Institutions of Truskavets Resort Mykola Odrekhivskyy[0000-0003-3165-4384]1, Volodymyr Pasichnyk[0000-0003-3007-2462]2,</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Department of Management</string-name>
        </contrib>
        <contrib contrib-type="author">
          <string-name>International Business</string-name>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Lviv Polytechnic National University</string-name>
          <email>nek.lviv@gmail.com</email>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Ukraine odr</string-name>
        </contrib>
        <contrib contrib-type="author">
          <string-name>@ukr.net</string-name>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>Information Systems and Networks Department, Lviv Polytechnic National University</institution>
          ,
          <addr-line>Lviv</addr-line>
          <country country="UA">Ukraine</country>
        </aff>
      </contrib-group>
      <fpage>0000</fpage>
      <lpage>0003</lpage>
      <abstract>
        <p>When organizing a national network of health centers, organization of market relations of health centers with the population, enterprises and organizations, there was a need to study this problem on a new basis, to develop scientifically justified terms for patients' stay in health, depending on the nature of the organism's susceptibility to a particular disease, resource and health conditions, health stages, patient age, and other metrics. All this leads to the application of individual approach to each patient, which is impossible without using of high technologies of healing, which are based on new high intelligent information systems. The methods and means of realization of information technology, which helps to increase the efficiency of the processes of rehabilitation in sanatorium-resort establishments, are presented. The given information technology contributes to the effective implementation of the healthimproving processes of sanatorium-resort establishments in the city-resort of Truskavets. Testing of information technology is carried out at diagnosis and recovery by means of mineral water "Naftusya".</p>
      </abstract>
      <kwd-group>
        <kwd>Information Technology</kwd>
        <kwd>Sanatorium-resort Establishments</kwd>
        <kwd>Health Care System</kwd>
        <kwd>Diagnosis and Recovery</kwd>
        <kwd>Modeling</kwd>
        <kwd>Mineral Water "Naftusya"</kwd>
      </kwd-group>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>1 Introduction</title>
      <p>The rapid development of information technologies, systematic recommendations,
created the necessary prerequisites for the development of processes of
intellectualization of decision-making processes in the medical field. Decision-making,
in its turn, has come to be seen as a highly intellectual process that has led to the
collaboration of specialists in various fields of knowledge (medicine, psychology,
economics, informatics, law, etc.) to create intelligent decision support systems in
management, and to enable the implementation of information management
technologies, in particular technologies management of patients' healing processes.</p>
      <p>Information technologies can be effectively used in the health-improving process of
sanatorium-resort institutions of Ukraine. This will improve the efficiency of the
recreation, treatment and rehabilitation of patients, as they ensure the efficiency of the
processes of collecting and processing statistical information, the study of individual
characteristics of patients, diagnosing health conditions and diseases, predicting the
course of diseases and determining algorithms for improving the health and wellness
of patients, selection health resorts.</p>
    </sec>
    <sec id="sec-2">
      <title>2 State of the Problem</title>
      <p>
        The works of Eman Abukhousa, Jameela Al-Jaroodi, Sanja Lazarova-Molnar, Nader
Mohamed[
        <xref ref-type="bibr" rid="ref1">1</xref>
        ], Inas S. Khayal1, Amro M. Farid[
        <xref ref-type="bibr" rid="ref2">2</xref>
        ] X. Zhong [
        <xref ref-type="bibr" rid="ref3">3</xref>
        ], Kiran Dewangan, Mina
Mishra [
        <xref ref-type="bibr" rid="ref4">4</xref>
        ] are dedicated to application of information technologies in health care
system. The use of information technology is one of the most promising areas of health
care development today, in particular in the provision of health services in health resorts
and resorts. Health information technologies are designed to facilitate the accumulation
and processing of large amounts of information, provide early identification of medical
problems and make effective decisions to address them in a non-medicated manner and
generate recommendations for the prevention of recurrence.
      </p>
      <p>The aim of the research is to analyze methods and tools for the implementation of
information technology, which contributes to the improvement of the efficiency of the
healing processes in spa resorts. When implemented in the practice of health institutions
provide diagnosis of patients' health, primary and secondary diagnosis of diseases,
analysis of health status, the choice of optimal methods of recovery, evaluation,
analysis and prediction of the effectiveness of recovery, scientific and economic
substantiation of recovery processes, accumulation and processing of medical data and
knowledge about diseases, their possible course and formation of health complexes.
Such information technology involves the creation of a referral system, in the database
and knowledge of which physicians of many specialties, who act as experts,
accumulate, and which provides the generation of recommendations that assist in the
decision-making processes of physicians in difficult situations.</p>
    </sec>
    <sec id="sec-3">
      <title>3 The Main Part of the Research</title>
      <p>
        The proposed information technology is implemented using a recommendation system,
which should provide the definition of different physiological systems of the body, if
necessary, differentiate them, generate and test the hypotheses of pathological
conditions, predict the disease [
        <xref ref-type="bibr" rid="ref5 ref6">5,6</xref>
        ], determine and predict changes in the dynamics,
recommend the type and scheme treatment or rehabilitation taking into account the
indications and contraindications, other factors (age, severity of the condition, the
degree of damage to various physiological systems, disconnection of pathological
conditions, compatibility and cumulativeness of medicines or wellness products, etc.),
extrapolate the patient's condition based on the effect of treatment, adjust the treatment
and health during the spa course. That is, the recommendation system has many tasks,
including: determining the state of the object; unbalance detection; finding out and
eliminating their causes; predict the evolution of an entity's states, and more[
        <xref ref-type="bibr" rid="ref7">7</xref>
        ].
      </p>
      <p>The following factors were taken into account when creating the proposed
information technology:






not all management goals can be expressed in quantitative terms, and some of the
parameters that affect the management process cannot establish the exact,
empirically determined, quantitative relationships;
the process of achieving the goal is multi-step and the content of each step cannot
be uniquely defined;
an object evolves over time, its structure and functions change, which leads to the
evolution of the control process itself;
the elements that are part of the structure of the management object have an active
nature and their behavior may be contrary to the management objectives;
objects have a hierarchical structure, for each level of which may be its optimal
solution;
the elements of the system are united by a large number of different types and
types of communications.</p>
      <p>Information technology contributes to the effective implementation of the
healthimproving processes of sanatorium-resort establishments in the city-resort of
Truskavets. This information technology is focused on the collection, processing and
analysis of diagnostic information on urological and gastroenterological pathologies,
diabetes and radiation diseases, conditions of patients, according to which they can be
attributed to the risk groups of these diseases. Testing of information technology is
carried out in the diagnosis and recovery with the help of mineral water "Naftusia"
diabetic patients and persons at risk of this disease. Realization of information
technologies of recovery occurs according to the scheme presented in Fig. 1.
The collection of diagnostic information is based on the results of laboratory,
instrumental, radiological, radio-indicator and electrophysiological studies. The
collected information about the patients' health status is recorded in the appropriate
examination cards, with further formation in the computer memory of formalized
medical history frames and their accumulation in the database (electronic archive of
medical histories).</p>
      <p>From the survey map, where the medical parameters under study are located in the
order in which the doctors examine the patients, the specific values of the medical signs
are recorded in a formalized medical history. Information on medical features, such as
their affiliation with a particular classification group or diagnosis, determines the health
status of patients, that is, their pathological, healthy or pre-pathological condition
(intermediate between health and disease). When entering the values of medical signs
in the pathological range is supplementing the signs of the patient's condition, otherwise
extrapolation of the patient's condition and the choice of the optimal method of
recovery.</p>
      <p>Situation supplemented by the situation is recorded in an electronic medical history,
which also collects data from formalized medical history and all information generated
by the object system and used to solve various tasks in the medical-diagnostic process.</p>
      <p>Disease diagnosis is made by activating diagnostic rules that include signs or
different combinations of signs, sometimes even contradictory ones, in order to be
diagnosed in different situations. It also includes data that does not provide basic
information but which can increase the accuracy of the diagnosis.</p>
      <p>In the diagnostic rules, the sequence of situational structures reflecting the clinic,
biochemistry and pathophysiology of the disease is presented in the form of "and - or"
graphs. Any of the defined conditions is a node of the pathology tree. Extensive areas
of therapy, such as kidney, liver, gastrointestinal, cardiovascular, and endocrine
systems can be selected to construct this tree. Within each of these sectors, subclasses
are distinguished on the basis of the pathogenetic mechanism.</p>
      <p>For example, the kidney injury subclasses are kidney failure, kidney inflammation,
kidney stone disease, nephrosis, and kidney infarction, similarly can be divided into
subclasses of endocrine glands, such as the pancreas, as discussed below. These
subclasses are further divided into more specific diagnoses by type, type, severity,
phase, severity, and so on.</p>
      <p>In the process of diagnosis, we propose to use computer simulation of the inference
procedure, that is, the conclusions are attributed to qualitative estimates, such as the
truth of the diagnosed condition (true, quasi-true, false), differentiation of severity
(light, medium, heavy, etc.). The diagnostic process can be expressed as a growing
pyramidal network, the configuration of which may change during operation. This
change is based on causation, so the pathological process can be represented in the form
of a causal network, the nodes of which are pathological states, and the arcs determine
the time relations, the nature of the relationships, the cause-to-effect relationship and
the weight of these ties. This makes it possible to support decision-making about
patients' health conditions and treatment methods based on recommendations generated
by the expert system.</p>
      <p>The decision on the patient's health status in general, or any body, is made on the
basis of simulation results, which is used to study structures, functions and processes at
different levels of living organism organization: atomic-molecular, subcellular,
celltissue, organ- systemic, organismal, biocenotic. To carry out these studies, we propose
to use: functional models that reproduce a certain relationship between known and
unknown quantities; models represented by a system of many-unknown equations,
which requires their study of computer hardware and related software;
optimizationtype models represented by systems of equations or inequalities for unknown quantities,
the aim of which is to find the solution that would give the optimal value of a given
indicator; simulation models used for analyzing biosystems as complex systems,
characterized by accurate reproduction of a biological process or phenomenon, require
special calculations by computer technology; systems and complexes of interdependent
models of the above types. That is, mathematical models are proposed for the study of
complex physiological processes, the study of the interaction of organism systems in
normal and pathology, in the study of epidemic processes, in clinical immunology,
pharmacokinetics, for the calculation of clinically relevant indicators in the processing
of signals and images, for the description of the diagnosis and imaging. and prediction,
which is usually done using differential calculus, elements of linear algebra, and theory
of random processes. In order to evaluate and predict patients' states to make optimal
decisions about these conditions and to manage them through the use of decision
support systems, we propose to use models based on mathematical methods of Markov
process theory.</p>
      <p>The evaluation of the truth of the diagnosis is dynamic, it is formed in the process of
working of the model of diagnosis, it is used in the calculation of the transitive force of
causation, the reliability of the predicted pathological conditions or the probability of
their hypotheses. This helps doctors find out the causes and effects of illnesses, as
moving up and down a tree of conclusions to identify the cause-and-effect chains based
on the transitive nature of cause-and-effect relationships.</p>
      <p>The analysis of the states in dynamics can be performed using the following groups
of qualitative linguistic assessments:</p>
      <sec id="sec-3-1">
        <title>a) "bad", "unsatisfactory", "satisfactory", "good", "very good"; b) “substantially below normal”, “below normal”, “normal”, “above normal”, “substantially above normal”; c) "improvement", "no change", "deterioration" and others.</title>
        <p>Analyzing the rate of change of these states is due to the intensity of transitions from
state to state, and with the help of linguistic variables, "insignificant", "significant",
"sharp" and others. It is advisable to draw conclusions about these assessments in the
presence of a diagnosis of disease information at certain points in time (for example: at
the beginning, middle and end of the healing or treatment period), formed on the basis
of ratios of different gradations of a large number of features. That is, at a high level,
in terms of abstraction, at the linguistic level, and with the use of appropriate
mathematical modeling tools.</p>
        <p>In our view, the most promising way to model the states of treatment objects is an
approach based on the generalized representation of this object as some
informationassociative network model. In this case, the behavior of the treatment object can be
described by the spatial-temporal distribution of its discrete states. The condition
description is a linguistic variable that indicates the elemental properties of the object
under study. Some element of this object at a fixed point (or interval) of time may be
represented by a status word in this case. Given the integrity of the treatment objects
and the appropriateness of their behavior, one can represent one or another of their
internal relationships and interactions by assigning associative calculus to a
corresponding set of concepts that express the condition. In this way, the doctor is able
to describe the structure and behavior of the treatment object at a conceptual level,
listing the properties and structure of the object, giving causal relationships between its
elements. Such a representation can be automatically formalized and transformed into
a machine image of some mathematical model - deterministic or stochastic.</p>
        <p>The implementation of this approach, when the conceptual representation of an
object is recognized as a Markov chain of states, allows to use the theory of Markov
chains by means of constructing on the basis of qualitative estimates of the states of the
corresponding quantitative indicators of the change of these states in dynamics for the
analysis of medical systems. This can solve the problem of evaluating the effectiveness
of the healing effect of natural factors of healing, such as Naftus mineral water, taking
into account the holistic and differentiated response of body systems. It is proposed to
implement a comprehensive approach to the organization of computational experiment,
which would include expert assessments and modeling of the dynamics of biological
processes.</p>
        <p>To achieve this, we proceeded from the following prerequisites:



a living organism is a complex hierarchical structure;
the therapeutic effect of mineral waters or other natural healing factors is
considered as an external influence factor;
the living organism to such influence responds to the reactions of organs
and systems of different levels of its organization. This includes
mechanisms of regulation that seek to bring the system to a state of dynamic
equilibrium, which corresponds to the level of therapeutic action of a health
factor.</p>
        <p>
          The therapeutic effect of any health factor is complex in nature and causes changes at
the level of biophysical, biochemical, physiological and other processes, the
mathematical description of which on a classical basis is quite complex. Given the fact
that the development of biological processes in many cases has a boundary character,
all the diversity of processes can be described as a set of states, the transitions between
which are random [
          <xref ref-type="bibr" rid="ref8">8</xref>
          ].
        </p>
        <p>
          Thus, the modeling of biological processes in the healing action of natural health
factors, it is advisable to start by solving the following tasks: development of an
adequate mathematical model of the dynamic properties of the therapeutic effect of
health factors; development of an informational model of dynamics of action of health
factors. This approach was used by us in modeling the state of the endocrine system of
the organism, which in this case it is advisable to present in the form of a four-level
hierarchical structure (Fig. 2) [
          <xref ref-type="bibr" rid="ref10 ref9">9, 10</xref>
          ]. The element of the first level of the hierarchy here
is the central nervous system (the main element of the system). At the second level,
there are endocrine glands, such as the pancreas, adrenal medulla, parathyroid glands,
and hypothalamus.
        </p>
        <p>The hypothalamus secretes nine hormones that control the pituitary gland, a gland
located at the third level of the hierarchy. The anterior part of the pituitary gland
produces three effector hormones that act directly on the organs and four tropes that
control the fourth level glands: adrenal cortex, thyroid, and gonads.</p>
        <p>When exposed to external factors, the response of the endocrine system is to
consistently alter the elementary physiological functions and regimes at the
corresponding levels of its structure. The first level of reaction will, accordingly, be
those structures that are the first to respond to the influence factor. The states of these
structures of the endocrine system are identified with the states of the formal elements
of the hierarchical structure. Each element can have N states.</p>
        <p>At the initial moment (before external influence) each state (Si) is characterized by
some probability P (Si). The impact effect is recorded as the transition of each element
to a new state. This process is completed by establishing a new probability distribution
of the state of elements favorable to the body.</p>
        <p>
          Processes that are represented as a hierarchical structure can be described using
Markov process theory. That is, the description of the j-th element of the i-th level of
the hierarchy can be performed using the Kolmogorov differential equation system (1)
[
          <xref ref-type="bibr" rid="ref11">11</xref>
          ].
where i = 1, 2,…, N is the order number of the hierarchy level; N is the number of
hierarchy levels; j = 1, 2,…, Mi is the order number of the element of the i-th level of
the hierarchy; Mi is the number of elements of the i-th level of the hierarchy; l=1,2,…,
Lj is the order number of the state, j is the element, and the i-th level of the hierarchy;
Lj is the number of states of the j-th element; i-the probability of the l-th state, the j-th
element, the i-th level of the hierarchy;   , , , +1 is intensity of transition of the system
under study from state l to state l+1, j-th element, i-th level of hierarchy.
The study of the endocrine system in statics in order to predict its states and states of
its components when t→∞ and dP/dt=0 can be performed on the basis of the solution
of the system of algebraic equations (2) obtained for the j-th element i-th level of the
hierarchical structure by transforming the system of differential equations (1).
This approach to modeling the endocrine system was tested by us when modeling the
effect of mineral water "Naftusia" on the endocrine part of the pancreas. According to
the classification given in [
          <xref ref-type="bibr" rid="ref10 ref12 ref8">8,10,12</xref>
          ], the pancreas can be in one of five major conditions
characterized by physiological glucose tolerance. This classification makes it possible
to represent the main phenotypes of glucose tolerance by a graph of states (Fig. 3).
(1)
(2)
where S1 is a state with increased glucose tolerance;
S2 is a condition in which tolerance is not compromised;
        </p>
      </sec>
      <sec id="sec-3-2">
        <title>S3 is a state with borderline glucose tolerance;</title>
        <p>S4 is a condition with a potential impaired glucose tolerance;
S5 is diabetes mellitus;
λij is intensities of transitions from the i-th to the j-th state, i, j = 1, 2, ..., 5; i ≠ j.
This graph can be described by the Kolmogorov system of differential equations (3).
(3)
This makes it possible to investigate the pancreas of patients with respect to glucose
tolerance in a dynamic mode, and to study the same states in a steady state it is
necessary to transform the system of differential equations (3) into a system of algebraic
equations (4).
(4)
The results of the analyzes obtained by the methods of examination of the state of
glucose tolerance through the subsystem of the collection of diagnostic information are
recorded in the machine history, on the basis of which the state of the patient's tolerance
to glucose is determined. All patient data are entered into the machine archives of case
histories to further investigate large patient samples in order to determine the intensities
of transitions from one state to another for glucose tolerance for each patient and the
intensities of transitions of patients from one classification group to another during their
classification. The resulting transition intensities are used as coefficients of the above
differential and algebraic equations, which allows for the tracking of the probability of
glucose tolerance states of each patient and each classification group of patients in
dynamic and in-patient modes.</p>
        <p>Analyzing the results of studies on the likelihood of glucose tolerance in patients and
their classification groups, it is possible to draw conclusions about the choice of the
optimal methods of recovery and their effectiveness. This method of computer
diagnostics and prognosis of patients with regard to the incidence of diabetes mellitus
or belonging to the risk group of this disease was the basis for the development of
appropriate software for the intellectual technology of health in the conditions of the
resort of Truskavets, which makes it possible to study the effect of mineral water
"Naftusya »On the condition of tolu-rarity to glucose of patients in their recovery.</p>
        <p>
          Testing of this recommendation system was carried out using clinical data of a
selected group of patients with diabetes, which were examined at the beginning of the
sanatorium and spa health and before its completion. The studies were performed on
the basis of a standard pyruvate glucose tolerance test [
          <xref ref-type="bibr" rid="ref10 ref12">10, 12</xref>
          ]. A total of 104 patients
were examined, who were divided into classification groups as follows:
        </p>
      </sec>
      <sec id="sec-3-3">
        <title>1. Hyperinsulinism - 88 people;</title>
        <p>2. Normal glucose tolerance - 6 people;
3. Border glucose tolerance - 8 people;
4. Potential impairment of glucose tolerance - 2 persons;
5. Diabetes mellitus - 0 patients.</p>
        <p>After the sanatorium and spa rehabilitation, this group of patients was again examined
with the help of a pyruvate test, and they were thus divided into classification groups:</p>
      </sec>
      <sec id="sec-3-4">
        <title>1. Hyperinsulinism - 77 people; 2. Normal glucose tolerance - 13 people; 3. Border glucose tolerance - 13 people; 4. Potential impairment of glucose tolerance - 1 person.</title>
        <p>
          To evaluate, analyze and predict the effect of Naftusia mineral water on the pancreas
of Langerhans using the developed software, the states of the pancreas are presented in
the form of a graph of the states shown in Fig. 4.
Analyzing the results of the study of the dynamics and statics of glucose tolerance states
obtained by solution using the developed software based on the fourth-order numerical
Runge-Kutta method for solving the differential equation system and Gaussian
numerical method for solving systems of algebraic equations [
          <xref ref-type="bibr" rid="ref8">8</xref>
          ] and depicted in Fig.
5, showed that the greatest value here is the probability of the state P (S2), which in
steady state can acquire a value equal to 0.375.
        </p>
        <p>The values of the probabilities of the other states in the statics were distributed as
follows: P (S1) = 0.144; P (S3) = 0.337; P (S4) = 0.144, which leads to the following
conclusion: the low-mineralized Naftusia water stabilizes the release of inulin by the
pancreas with minor impaired glucose tolerance.</p>
        <p>Therefore, in the conditions of the resort of Truskavets, patients at risk of diabetes
mellitus or diabetic patients with minor impaired glucose tolerance can be effectively
recovered. That is, Naftusia water can be used, on the one hand, as an effective means
of preventing diabetes, and on the other, as a means of restoring the health of patients.</p>
        <p>Thus, Naftusya contributes to the effective development of the rehabilitation and
recreational components of the wellness process in Truskavets.</p>
        <p>Appraisal of the proposed mathematical and software evaluation, analysis and
prediction of patients 'conditions for the purpose of further decision-making about
patients' health conditions and methods of their healing, lead to the conclusion that this
approach to the organization of intelligent healing technologies promotes rapid
diagnosis, the choice of the optimal treatment complexes and, accordingly, the effective
healing of patients by using exclusively natural medical factors. It is advisable to
extrapolate the states here on the basis of deductive, inductive and abductive inferences,
evaluating alternative solutions, using the values of cause and effect, and linking
individual diagnoses into a single system for the whole organism. Therefore, the
recommand system should include special tools that are included in the source language
and provide standardization of outgoing messages. The optimal range of treatment
measures and remedies is determined by manipulating machine history data. Therefore,
machine history must store all patient information from outside and generated by
technology.</p>
        <p>The description of therapeutic measures is advisable to be in the form of a tree of
signs and pathological conditions, so they should include the following characteristics:
form of recovery (clinical treatment: inpatient, outpatient; rehabilitation; recreation),
object (organs and systems of the body), therapeutic agents, display - their mechanism
of action, daily dose, duration, frequency and conditions of reception, their antagonists,
side effects, compatibility with other agents, cumulativeness, etc. As the therapeutic
measures in the conditions of the resort should focus mainly on natural healing factors:
internal mineral water intake, therapeutic baths, hydropathy, ozokeritotherapy,
physiotherapy, diet therapy, phytotherapy, physical therapy, therapeutic massage,
psychotherapy, psychotherapy, psychotherapy use a multilevel language of knowledge
representation, because the procedure of recommendation of the treatment complex
must take into account different variations of data values at different levels of the
knowledge hierarchy It is important to make ambiguous decisions.
For different biosystems, the list of possible combinations of data on the presence and
absence of damage should consist of a number of elements, which predetermines
models of generative type to be used in the diagnosis of conditions of the organism
models that allow to build different pathologies on the basis of the input data and not
select them from the specified list. This approach is possible due to the fact that the
structure of the knowledge base must be formed from the knowledge of anatomy,
normal and pathological physiology, description of clinical forms of the disease course.
In this case, it is advisable to separate the model from the diagnostic model and in the
presence of input data, it is advisable that the models work separately. Collaborative
work should be possible provided that the output of the first model is fully consistent
with the input of the other, and decisions on the choice of optimal healing techniques
should be made on the basis of decisions about the state of the organism.</p>
        <p>The main methods and principles (criteria, tasks) of optimizing the technology of
health, focused on improving the health and economic efficiency in the conditions of
the resorts, include: optimization of technology in terms of timing, choice of health
complexes, health and health fools, innovations to diagnose and predict patients' health
are relevant here; optimization of processes of adaptation of patients to conditions of
the external environment of the resort on the basis of rhythmological characteristics of
organisms.</p>
      </sec>
    </sec>
    <sec id="sec-4">
      <title>Conclusions</title>
      <p>
        Thus, the scientific and practical results of the optimization of health technologies in
resort conditions should be the methodology of optimizing innovations, determining
the optimal terms of recreation, rehabilitation and treatment, the appointment of health
complexes. Analyzing research and publications, starting with work [
        <xref ref-type="bibr" rid="ref2">2</xref>
        ], in which the
solution of this problem for spa resorts as institutions of post-clinical rehabilitation was
initiated, says that the current optimal terms of recovery are determined not by scientific
means, but by the duration of the period vacation. However, when organizing a national
network of health resorts, organizing market relations of health resorts with the
population, enterprises and organizations, when it comes to the health care of healthy
or practically healthy people, there was a need to study this problem on a new basis, to
develop scientifically valid terms of stay patients on health, depending on the nature of
the body's predisposition to a particular disease, resource and health conditions, stages
of the course of health, age of the patient and other indicators. All this leads to the
application of individual approach to each patient, which is impossible without the use
of high technologies of healing, which are based on new highly intelligent information
systems as means of artificial intelligence.
      </p>
    </sec>
  </body>
  <back>
    <ref-list>
      <ref id="ref1">
        <mixed-citation>
          1. Simulation and
          <article-title>Modeling Efforts to Support Decision Making in Healthcare Supply Chain Management</article-title>
          , https://www.ncbi.nlm.nih.gov/pubmed/24683333, last accessed
          <year>2019</year>
          /08/11.
        </mixed-citation>
      </ref>
      <ref id="ref2">
        <mixed-citation>
          2.
          <string-name>
            <given-names>A</given-names>
            <surname>Dynamic System</surname>
          </string-name>
          <article-title>Model for Personalized Healthcare Delivery and Managed Individual Health Outcomes</article-title>
          , https://arxiv.org/pdf/
          <year>1910</year>
          .09104.pdf,
          <source>last accessed</source>
          <year>2019</year>
          /08/11.
        </mixed-citation>
      </ref>
      <ref id="ref3">
        <mixed-citation>
          3.
          <string-name>
            <surname>Zhong</surname>
            ,
            <given-names>X.</given-names>
          </string-name>
          :
          <article-title>From production systems to health care delivery systems: a retrospective look on similarities, difficulties and opportunities</article-title>
          .
          <source>International Journal of Production Research</source>
          <volume>55</volume>
          (
          <issue>14</issue>
          ),
          <fpage>1</fpage>
          -
          <lpage>15</lpage>
          (
          <year>2017</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref4">
        <mixed-citation>
          4.
          <article-title>Internet of Things for Healthcare: A Review</article-title>
          , https://www.researchgate.net/publication/323855758_Internet_
          <article-title>of_Things_for_Healthcare_ A_Review, last accessed</article-title>
          <year>2019</year>
          /08/11.
        </mixed-citation>
      </ref>
      <ref id="ref5">
        <mixed-citation>
          5.
          <string-name>
            <surname>Tomashevskyi</surname>
            ,
            <given-names>V.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Yatsyshyn</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Pasichnyk</surname>
            ,
            <given-names>V.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Kunanets</surname>
            ,
            <given-names>N.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Rzheuskyi</surname>
            <given-names>A.</given-names>
          </string-name>
          :
          <article-title>Data warhouses of hybrid type: features of construction</article-title>
          .
          <source>Advances in Intelligent Systems and Computing ІІ (AISC) 938</source>
          ,
          <fpage>325</fpage>
          -
          <lpage>334</lpage>
          (
          <year>2019</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref6">
        <mixed-citation>
          6.
          <article-title>Mobile application for preliminary diagnosis of diseases</article-title>
          , http://ceur-ws.org/Vol2255/paper25.pdf,
          <source>last accessed</source>
          <year>2019</year>
          /08/11.
        </mixed-citation>
      </ref>
      <ref id="ref7">
        <mixed-citation>
          7.
          <string-name>
            <surname>Kazarian</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Kunanets</surname>
            ,
            <given-names>N.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Pasichnyk</surname>
            ,
            <given-names>V.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Veretennikova</surname>
            ,
            <given-names>N.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Rzheuskyi</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          <string-name>
            <surname>Leheza</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Kunanets</surname>
            <given-names>O.</given-names>
          </string-name>
          :
          <article-title>Complex information e-science system architecture based on cloud computing model</article-title>
          .
          <source>CEUR Workshop Proceedings</source>
          <volume>2362</volume>
          ,
          <fpage>366</fpage>
          -
          <lpage>377</lpage>
          (
          <year>2019</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref8">
        <mixed-citation>
          8.
          <string-name>
            <surname>Gela</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Odrekhivsky</surname>
            ,
            <given-names>M.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Soloviev</surname>
            ,
            <given-names>V.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Fedorkiv</surname>
            <given-names>I.</given-names>
          </string-name>
          :
          <article-title>The decision support system for the rehabilitation of patients with pathologies of the endocrine system</article-title>
          .
          <source>Cybernetics</source>
          and computer engineering. Medical cybernetics. Science. Dumka,
          <string-name>
            <surname>Kyiv</surname>
          </string-name>
          (
          <year>1994</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref9">
        <mixed-citation>
          9.
          <string-name>
            <surname>Chester-Jones</surname>
            ,
            <given-names>I.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Ingleton</surname>
            ,
            <given-names>P.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Phillips</surname>
          </string-name>
          , J.:
          <article-title>Fundamentals of comparative vertebrate endocrinology</article-title>
          .
          <source>Springer US</source>
          (
          <year>2013</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref10">
        <mixed-citation>
          10.
          <string-name>
            <surname>Hart Ian</surname>
            <given-names>R.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Newton</surname>
            <given-names>R.W.</given-names>
          </string-name>
          : Endocrinology. Springer Science &amp; Business
          <string-name>
            <surname>Media</surname>
          </string-name>
          (
          <year>2012</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref11">
        <mixed-citation>
          11.
          <string-name>
            <surname>Kolmogorov</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Zhurbenko</surname>
            ,
            <given-names>I.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Prokhorov</surname>
            <given-names>A.</given-names>
          </string-name>
          :
          <article-title>Introduction to probability theory</article-title>
          .
          <source>Moscow</source>
          (
          <year>2015</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref12">
        <mixed-citation>
          12.
          <string-name>
            <surname>Tomashevsky</surname>
          </string-name>
          , Ya.,
          <string-name>
            <surname>Tomashevska</surname>
            ,
            <given-names>O.</given-names>
          </string-name>
          :
          <article-title>Fundamentals of prophylactic endocrinology</article-title>
          .
          <source>Lviv</source>
          (
          <year>1992</year>
          ).
        </mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>