VIRTUAL MEDICAL DOCTOR SYSTEMS

Status Progress Report on Virtual Medical Doctor System (VDS)

Interaction Interface

Hamido Fujita, Jun Hakura and Masaki Kurematsu

Iwate Prefectural University, Iwate, 020-0193, Japan

Keywords: Emotional reasoning, Human user interaction, Intelligent interface, Facial analysis, Ego gram.

Abstract: Human computer Interaction based on emotional modelling is investigated and reported in this paper.

Human personality is analyzed based on ego-gram analysis and accordingly human "SELF" emotional

model is created. We have created as one part a computerized model which reflects a human user (in this

paper Diagnostician model) impeded as a computer based reasoning model and through it, an emotional

interaction between that model and the real human user is established. The interaction is based on a screen

mask attached to manikin head resemble the diagnostician, that through it the system can act to speak (i.e.,

mimicking diagnostician) with the patient user. In this paper the interaction scenarios and reasoning of the

virtual medical doctor or diagnostician are based on transactional analysis concept. We have implemented

the system and empirically, examined it, as experiment in public space for revision and evaluation. The

paper is reporting on the project outline, the usage of physiological issue in human reasoning through the

virtual system is developed.

1 INTRODUCTION

Recently there have been extensive move to towards

changing the way health care is delivered, financed

and regulated (Smith, 2000) Medical innovations

have become an important lever inquest of

improving efficiency. The main purpose is to

improve the efficiency so that more patients could

receive treatment more quickly without reducing the

quality of care (Mikkola, 2003). How to cope with a

rise in the need for the elderly care services is a

formidable issue facing all the industrialized

countries.

Unfortunately, Japan's health care system has not

been prepared enough to respond to the needs ahead.

Particularly Japan's home care services have heavily

been relying on voluntary labour of family members

with little social services available. The proportion

of the population 65 years and over has doubled

from 10% in 1985 to 20% in 2005, and is projected

to be 30% in 2023. (2006, NIPSSR).

In June 2006, the Diet (Japanese Congress) passed a

comprehensive package of reform to make the

delivery system more efficient. First, the average

length of stay in hospitals is to be decreased. To

achieve this goal, the number of long term care

Figure 1: Simple outline of the VDS.

(LTC) hospital beds will be reduced from the 2006

level of 380,000 to 150,000 by the end of fiscal year

2011 and converted to LTC Insurance facility beds

and assisted living (Leflar, 2005).

The system proposed in this paper participates in

helping physicians to manage the diagnosis

procedure using the same knowledge that physicians

have by copying (mimic) his/her style, mentality,

diagnosis routines and medicine recipes. It is not

replacing the physicians but it would participate to

utilize his/her knowledge for preliminary diagnosis

Fujita H., Hakura J. and Kurematsu M. (2010).

VIRTUAL MEDICAL DOCTOR SYSTEMS - Status Progress Report on Virtual Medical Doctor System (VDS) Interaction Interface.

In Proceedings of the Third International Conference on Health Informatics, pages 38-45

DOI: 10.5220/0002712000380045

 SciTePress

and health care services for patient for efficiency

purpose.

This paper contributes to present part of our

experimental work on building a virtual system

based or what we called as Virtual medical Doctor

System (for short VDS) to act as medicinal

diagnostician doctor, and interact with human

patient. The Worldwide, the prevalence of diabetes

is rising due to population growth, aging,

urbanization, and increasing prevalence of obesity,

and physical inactivity. We propose a system that

can participate in the care processes inside a medical

organization, by utilizing virtually the medical

doctor experience and knowledge for health care

services.

1.1 System Conceptual Outline

The VDS system is to work together with the

corresponding human medical doctor. So the system

(VDS) and the MD (Medical Doctor) are working

together in comprehensive coherency; the former is

complementary to the latter but not vice versa. The

former is to diagnose outpatient 1

and classify these

diagnosis into classes. Simple cases classes that the

VDS would take conclusion and set the diagnosis

procedure and accordingly take action (e.g., issue

drugs to the patient). The overall procedure is

supervised by the MD later on in a report. There are

other cases which the system concludes to have the

MD to participate in the final decision. In such cases,

the system sends the diagnosis reports to the MD

and provides an appointment to the patient in the

hospital queue. The system reads the queue data at

the management centre of the hospital reception.

And assign the patient to the queue. If the Doctor

found the assignment is appropriate (check mark

OK) then the system learned that the decision is

appropriate, however, by certain feedback from the

doctor the system can learn from the doctor’s

feedback. We provide a window at the doctor office

to fill a sheet of evaluation to enforce the learning

procedure for the system. Such evaluation sheet

would provide a learning mechanism to increase the

reasoning procedure for the diagnosis. However

such knowledge management would be based (i.e.,

mimic) on Medical Doctor A, therefore, it would be

stored in knowledge management on the top of the

management system. So when another doctor is

doing the outpatient diagnosis then the profile of

decision making related to that Doctor would be

used (i.e., recalled). So there is a general diagnosis

and on top of it there are diagnosis categorized on

physicians actual practices.

The paper is showing the state of art in making a

system that can interact with human user based on

new concept named as mental cloning mentioned in

(Fujita 2009). The cloning is based on analysis of

human medical doctor (HMD). The analysis is

projected using his/her observed styles as a person

and also as expert in medical diagnosis related

practices. So there are different style of categorized

knowledge reflecting such representation and related

reasoning.

As shown in Fig.1. The system would to create

a virtual face (i.e., screen mask) of an actual doctor

that through it the patient communicates with pre-

assigned virtual version of that medical doctor.

Figure 2: The VDS outline.

Physical doctor face is a mask copied and

attached on manikin.

Inside it there is a projector that reflects the 3

dimensional generated images on the mask screen

that reflects the actual facial real-time created

images of the medical doctor namely, Doctor A (Fig.

1). These animated facial image synchronized with a

spoken language in the same style of the actual

physical doctor is created. The style mimics the

actual doctor emotional expression as well his/her

diagnosis style. Also the MD speaks in natural

accent with emotions based on the patient mental

mode, estimated by the patient profile (age, gender,

ego data), and his/her situation automatically

measured by data resembles (blood pressure, body

weight, body temperature, and thermal analyzer).

These devices (equipments) are assembled to a

patient desk chair that the patient would sit on, and

automatically these measurements are collected and

transferred through serial connection to the virtual

VIRTUAL MEDICAL DOCTOR SYSTEMS - Status Progress Report on Virtual Medical Doctor System (VDS)

Interaction Interface

doctor system. These data are all measured and send

online to the VDS together with the mental status

(situation) of the user (patient), with estimated ego

state retrieved from the databases.

This system is been built by a support from Ministry

of Interiors affairs and communications of Japan

under SCOPE project. The security rules are

specified through an interface by the hospital staff

depends on patient portfolio related status.

We need to emphasis here that the diagnosis and

treatment done by the VDS is based on the actual

diagnosis and guidelines specified by the actual

doctor based scenarios that we have collected in

advance and specified in the system using Arden

Syntax which is open standards and representation

of medical knowledge. The Doctor A diagnosis

guidelines are represented as a collection of medical

logic modules (MLMs). Each MLM represents a

single decision that is grouped into three categories:

Maintenance, library, and knowledge. The

maintenance and library categories describe the

MLM’s paramedic issues, keywords.

The knowledge category describes the logic of

the MLM. We are investigating to use ASBRU for

knowledge diagnosis based on Doctor A and

generalizing them into diagnosis guidelines

representation of schemata at various levels of

details. This is the role of inference engine. We

would explain briefly, this in Sec. 4. On more details,

please refer to other paper in this proceedings

elaborating on the inference issues.

2 VIRTUAL DOCTOR SYSTEM

In our project computer systems (machine)

understand our emotion and interact with us based

on internal psychological reasoning and type of

information. The mind can be viewed as community

of selves (Horowitz, 1985). A state of mind is a

relatively coherent pattern a composite of diverse

forms of experience and expression that appear

almost simultaneously. These states of mind are

accompanied by characteristic expressive behaviors,

tone of voice, facial expression, and also other

invariants, like type of color, type of current

employment, and other invariants that collectively

estimate the emotional state of the patient.

The objective of the system is to have hollow

gram that interacts with the patient based on the

mental cloning of the subject person through the

hollow gram (i.e., HMD), and accordingly we can

have the human user (patient) to interact with the

system based on facial based analysis The whole

system outline is shown in Fig.2.

The user age and gender is estimated using a tool

developed with OKI Co. The tool can estimate the

gender and the age of the user. Also, at the moment

our system simultaneously has a touch panel that the

patient can enter his/her other personality related

information through icons based interface on a

screen beside his/her desk. The system

measures/collects the user personality based on a

concept we called it universal templates (Fujita,

2008) that is used to estimate the user profile based

on the collected data. The user information related to

his/her, set of invariants that specified, by answering

questionnaires related to his favourite colours,

hobbies and type of employment (Hakura, 2009).

The interaction is based on projection of the system

(Medical Doctor) on a person onto oneself.

The reasoning between the patient and VDS, is

based on projection on a patient onto doctor’s self.

From this prospective as the doctor is expertise

person, she/he is projecting someone (i.e., patient)

onto him/her self, bounded by the circular space,

specified by the interaction space between the

system (VDS) and the patient. It is a reflective

interaction based on projection between the subject

(patient) and the object is (VDS), by sharing the

experience of the system projected into the patient

related states. For that purpose, we have used

modular approach. Emotional module, inference

module and other modules that all synchronously,

are interacting with the user based on patient

projection for diagnosis purposes. We have

psychologically cloned the user main “self”, based

on the user physiological analysis, and modelling.

Mental cloning ( Fujita, 2009) is aconcept specifying

the type of harmony and the connection between the

subject user mentality and other object. The subject

of the user type mentality purposes specify the type

of engagement that the object should have for

successful interaction. The specialization of such

engagement; in the context of mental cloning

typifies the style of mental reasoning in the object

(VDS) as the subject (patient) progresses and

behaves.

Figure 3: The five ego states.

Parent Ego state

Child Ego state

Adult Ego State

Adapted Child

Ego State

Critical Parnet

Ego State

Nurturing Parnet

Ego state

Free Child

Ego state

HEALTHINF 2010 - International Conference on Health Informatics

The synchronic view (high degree of emotional

representation to the environment) of self is also

presented. The example of the mental user cloning

we used was for Medical doctor mentality analysis

and technical background on how to do diagnosis on

people. These introjections are to specify the

physiological view of both the work outcome and

mentality of the object physical doctor.

2.1 Ego Gram based Transactional

Analysis based Model

Transactional analysis is a development approach of

self perception and its impact. The theory discovered

first by (Eric Berne, 1971) and it stated that much

can be discovered about an individual by analyzing

the type of interactions (transactions) engaged in.

TA (Transactional Analysis) suggested that we each

had an Inner Parent, an Inner Child, and an Inner

Adult personality parts that collectively determined

our feelings, beliefs, and behaviour. The

Transactional analysis life position is a function of

the performance of a person and the attention

received from other party (VDS System). The

assumption is that all people want attention

preferably positive (praise, encouragement). But if

positive attention is not given, negative attention is

selected. Self perception is an essential issue

specifying attributes related to behaviour.

Acceptance of self, ability to accept and relate to

others in positive prospective is a desirable outcome.

It is essential to foster a positive view of self for

Figure 4: The system implementation outline.

CP NP A FC A C

Label

HMDEgogram

Affliation

Figure 5: Ego gram of Doctor A.

each user. (Dusay, 72) narrowed the large number of

potential ego states to five: Nurturing Parent,

Critical Parent, Adult, Adapted Child, and Natural

Child. TA

Figure 6: The mental cloning based system components.

Figure 7: The facia extraction of user patient states.

Figure 8: States transitions between patient and doctor.

MD self state

U: User (patient) self state

N: number of appearance

CP AC

VIRTUAL MEDICAL DOCTOR SYSTEMS - Status Progress Report on Virtual Medical Doctor System (VDS)

Interaction Interface

conceptualizes personality in terms of five

functional ego states: Critical Parent (CP), Nurturing

Parent (NP), Adult (A), Free Child (FC), and

Adapted Child (AC). These five ego states have

been widely researched with varying degrees of

scientific rigor. A number of researchers have

attempted to demonstrate reliability and construct

validity for these ego states. The Tokyo University

Egogram is reportedly in use in Japan. Egogram is a

sort of psychological scales theoretically based on

Transactional Analysis. Tokyo University Egogram

(TEG) published in 1984 was a questionnaire with

reliability and validity. Since then, it has been

widely used in various fields such as medical care,

education, and industry. The second edition of TEG

was published in 1993 after three years of basic

studies. In this study, we investigated the use of

TEG 2.0 for its personality application to predict the

self of HMD and the patient user for best interaction

based on the finding of the self through experimental

analysis of the egogram using TEG2.0. The TA has

been studied (Trautmann, 1981) for personality

analysis, reflected in the TEG system for studying

human personality.

As specified by Berne and modified by (Dusay,

1982) the five ego states are as below:

1. A nurturing parent subself: supports care,

attention, and positive reinforcement.

2. An evaluative parent subself; critic, pusher, it

reflects the norms and values of the society and

set up standards and measures.

3. A central organizing subself, who is the self that

often works with the observer and act as the

leader.

4. A good socialized adapted child subself. This is

obedient, conforming child who tries to please

authorities, and it lacks creativity.

5. A natural child sub self, creative, nonconforming,

spontaneous and playful. (As shown in Fig.3.)

A state of mind is a relatively coherent pattern a

composite of diverse forms of experience and

expression that appear almost simultaneously. A

survey has been carried out to collect data on

Japanese subject persons of different gender (male,

female), and different ages (children, adults and old

age). Each person has entered their responses for

questionnaires (TEG 2.0 based 60 questions).

The object doctor and subject patient users (in

advance for database personality construct purposes)

after entering the user profile information (gender,

age range), would answer (response) to these 60

questions as Yes, Yes/No and No. The Scoring

answers as specified by TEG would be 2, 1, and zero,

respectively. The collected sum answer would

represent their ego state as number. One example for

Doctor A ego gram is shown as in Fig.5. The highest

value would represent the best estimation of self

state of that person as one of the any state in Fig.3.

These ego grams for personality extraction for

patient purposes are stored in database and indexed.

There are five categories of age class and these are:

Child (6 to 12) years, junior young (12 to 18), senior

young (18~26), adult (26~45), senior adult (45~60),

Old (61~). These categories are set according to the

educational system and working structure in Japan.

category to be related to elementary school class,

category is related to intermediate school and

high school. The 3

category is relative to university

class and young inexperienced workers. The 4

category is related to middle class workers of

different slices.

The 5

class is relative to experienced workers and

advanced middle class. The last class is the old

and retired class people. Such classifications reflect

the relative social characteristics of people as

general class reflecting each class personality and

its relative characteristics as specific specialization

on each class.

3 ACTION DECISON MODEL

Our system outline is as presented in Fig.4, and

Fig.7. The patient user when visiting VDS is sitting

on chair where there is touch panel beside him/her.

The patinet enters information by clicking on check

box, on his gender selection box and age class box.

The system uses a generative program to comput the

user personality using what we have called a

universal template (Fujita, 2008). The user’s face;

using the active appearance technology (Fujita,

2007) is been the computation subject to compute

and categorize the searching keys to localize the best

estimation to select the best “fit” of the human user

from the template data base for emotional based

reasoning. The Templates data base is a collective

database of samples data of categorized according to

user personality type. Each template is a set of six

emotions (sad, happy, disgust, surprise, angry, fear)

as shown in Fig.7, and neutral (no emotion). These 7

types of face templates set are been categorized

according the user gender key and age class key.

The localization and detection of the user emotion is

based a systematic estimation approach using OKI

FSE V4, SDK (OKI). For the eyes centre there is

one feature point for each eye. For the eyelids there

are 5 feature points for each eye. For the eyebrows

there are three points for each eyebrow. There are 8

feature points for the mouth and three feature points

HEALTHINF 2010 - International Conference on Health Informatics

for localizing the nose. Also, there are 12 feature

points specifying the contour of the face from the

ears down around. Using these feature points we

can track the emotional feature of the human user

based on the value difference between the tracked

point and the labelling dictionary in the database

specifying the best emotional estimation and the

selection of the emotional state among the six

Ekman universal emotional states (Fujita, 2009).

4 HCI FOR VDS SYSTEM

In this part we would discuss how to define and

establish the “self” or internal mental mechanism

through which the system (VDS), would use to

interact with the mental self of the human user. We

have used an experimental survey to collect data.

Based on these collected data we have created the

mental self.

The Doctor Ego gram has been studied and

experimentally brought up using empirical analysis.

Doctor A personality and his/her answer related to

the TEG Questionnaires have been carried using an

empirical study analysis and analytical based

observations. This has been done by asking the

doctor to fill and answer questions based on TEG 60

questionnaires, and defined in the same way as

shown on Fig.5.

The action scenario between the patient and the

VDS would be based on the styles and wordings that

are used by the MD him/her self in actual and other

diagnosis practices. This part is not yet reported here

in this status report paper due to space. However the

style would be related to looking to the issues from

minutes things to larger parts, collecting the micro

views and macro views in different prospective for

analytical based reasoning. These collected images

are analyzed and reasoned in VDS related to the

style that the MD usually do during his routines

diagnosis. As the MD is in nature is a Japanese

character, so this also would be considered in the

system reflecting the psychological and cultural side

into the reasoning process. This conceptual

interaction is based on transactional analysis as

shown in Fig. 8, assuming that the style of

communication between the user and VDS system is

Rogerian style (based on Cal Rogers’ work in

psychology) which

encourages the involved two

parties in positive style of engagement based on

empathic position assuming that they share to

explore common ground related to medical

diagnosis. As shown in Fig. 9 the state transition of

VDS’s self change due to emotion state change of

the patient user. Fig. 7 observes the user emotion

state by computing the change in the feature points,

and accordingly MD system can estimate the

emotion state of the patient and integrate it with in

the diagnosis for inference with other observation

extracted from the keywords. The system

implementation is as shown in Fig.9 and Fg.10.

That shows the snapshot of the system

implementation.

Figure 9: Implementation of Doctor A self and patient self.

Figure 10: State Transition implementation of VDS.

The system observes to the user in cyclic time

period of 10 sec margin for incremental type

reasoning. VDS system is the initiative to talk with

the user. The system estimate and compute the

emotional state of the patient user while VDS

system is talking, to collect if there is any change in

the emotional state of the user and the appropriate

keywords for inference purposes.. At the initial state

the user emotional state is set as determined by the

best match of that user with the best estimate for the

VIRTUAL MEDICAL DOCTOR SYSTEMS - Status Progress Report on Virtual Medical Doctor System (VDS)

Interaction Interface

selected ego gram that set with the user personality.

Then the user initial personality set is been selected.

The system (i.e. VDS) would talk (with emotion)

and check and collect if there is any change in the

user emotion according to the rules shown below. If

there is a change then Doctor A would record this

state and select the appropriate action and related

scenario to that state. The action can be represented

by appropriate transaction state, selected among the

5 states mentioned in Fig. 3. The system should have

a trace to all states so that it can return back to its

original state when there is no specific emotional

state change in the user emotions. If the patient user

emotion state is neutral, this reflects that the user is

adult state. If the user is happy state, then the user is

nurturing parent state. If both the VDS system

emotion state and the estimated patient user emotion

state are the same, then the patient user emotion

state is NP. If the estimated patient user emotion

state is surprise then the user state is FC. If the

estimated patient user emotion state is «angry» or

«sad» or «disgust» (negative response) then the

patient user emotion state is CP. The

implementation is shown in Fig. 9 and Fig.10 and it

is as follows:

Self state Condition

K_NP→K_AC U_CP＞4

K_AC→K_NP U_CP≦4

K_AC loop U_CP＞4

K_NP→K_FC U_NP＞7 or U_FC>7

K_FC→K_NP U_NP≦7 or U_FC≦7

K_FC loop U_NP＞7 or U_FC>7

K_NP→K_A U_A＞5

K_A →K_NP U_A≦5

K_A loop 10＞U_A＞5

K_A →K_CP U_A＞9

（Transition finish）

※ K_CP→K_A and K_CP Loop not exist.

K_NP loop: U_CP≦4 or U_NP≦7 or U_FC≦7 or

U_A≦5

We need to mention here due to space limitation we

have not discussed the issue of voice (speak)

generation and emotional extraction of

voice(Kurematsu et.al 2009). The voice and face is

been synchronized in real time and articulated to the

generated scenario by the VDS according to CIGs.

5 REASONING SCENARIOS

The paper reports here part of our project outcome

that is related to interaction between VDS avatar and

Patient. The voice recognition issues is been also,

discussed in (Fujita, 2009). The action scenario is to

create a diagnosis based on the guidelines given by

the Doctor A. Doctor A is a nominated Doctor which

is the object system would mimic to interact with

patient through VDS avatar. Implementing medical

guidelines of Doctor A in active computer-based

decision participates to enhance the best practices of

medical services on behalf of Doctor A. Our system

reported here briefly, participates to provide

cognitive interaction between real patient and

specialized doctor A (avatar) through computer

interpretable guidelines (CIGs).

We have to represent various types of diagnosis

guideline using formal representation. Consequently,

acquire, verify and evaluate these formalized

guidelines for daily routines diagnosis.

The system would be facilitated at hospital A where

Doctor is working. So the system would use the

computer interpretable guidelines (CIG) based on

Doctor A as first diagnosis procedure to specify and

categorize (classify) patients according to their

status and profile. Please note that the classification

and diagnosis is based on Doctor A cognitive

interaction. The reasoning knowledge (eg. Doctor A

methods and Doctor B methods) should be separated

from domain knowledge (eg. laboratory tests, used

drugs). Also the representation should support the

use of standard data model and medical

terminologies like HL7 UMLS (Tanaka, 2000)

We are using semantic net for representing the

reasoning part. The domain knowledge is specified

by automatic retrieval by establishing a link between

the ontology and the patient database. This is

reported in another paper in this conference.

6 CONCLUSIONS

This paper is reporting a progress status of our

project related to mental cloning based concept on

how to reason and represent human emotion in

scientific way and use that emotion to reason with

human user. We articulate realization to MD

objective machine. The MD is usually a real person

that based on interviews, we extract his personality

that is to be used into the system and act on his

behalf on mental basis using his/her routine

diagnosis procedure. The MD views have been

integrated into our representation in MD ego gram.

Using this with other related information we create

a system that can interact with the patient user based

on Transaction analysis protocol. The system would

be examined in Beta space at a hospital where that

MD is working.

This would have people (patient users) interact

with VDS system to experience his/her (i.e., MD)

emotional transition to the MD created personality

HEALTHINF 2010 - International Conference on Health Informatics

and his/her transactional based analysis with patient

users. The collected data of the evaluation would be

examined to revise the VDS’s personality and

diagnosis knowledge. The personality is reflected

from majority of answers that reflect how people

can look to the VDS through his work and the

gathered cognitive thinking on him/her. We think

this approach may contribute to create the

foundation of mental cloning based computing that

can contribute to establish the best engagement and

harmony between human and machine taking into

consideration the human emotional recognition as

computational mechanism in this interaction, for

medical services.

The inference engine of the knowledge bases of

the VDS knowledge hierarchy is briefly, reported in

a companion paper in this proceedings. The

prototype version of the system is to be used in

medical practices in Kitamatuzono clinic, Morioka,

Japan. The related statistical data on experimenting

the work is to be reported in the near future.

ACKNOWLEDGEMENTS

This research is supported by the Ministry of

Internal Affairs and Communications of Japan

under the Strategic Information and

Communications R&D Promotion Programme

(SCOPE). We appreciate the supports provided by

Medical Doctors in Iwate region Hospitals to mimic

the diagnosis procedure into our system for testing

purposes.

REFERENCES

Fujita, H., Hakura, J. Kurematsu, M. 2009 “Intelligent

human interface based on mental cloning-based

software” International Journal on Knowledge-Based

Systems, Elsevier, 22 (3), pp. 216-234, April.

Pierre-Yves Oudeyer: 2003 «The production and

recognition of emotions in speech: features and

algorithms» ， International Journal of Human

Computer Interaction, Vol.59(1-2) pp.157-183.

Fujita, H., Hakura, J. Kurematsu, M. Chida, S. and

Arakawa, Y. :2008 “Empirical based Techniques for

Human Cognitive Interaction Analysis: Universal

Template Design”，the 7th New Trends in Software

Methodologies, tools and Techniques (Proceedings of

SoMeT_08), pp.257-277. IOS press, ISBN: 978-1-

158603-916-5

Fujita, H., Hakura, J. Kurematsu, M.: 2007 “Virtual

Human Interaction based on Emotional Cognition”,

Innovations 07, IEEE Computer Society, publication

Horowitz: 1988: Introduction to Psychodynamics. A New

Synthesis: By Mardi J. Horowitz. New York: Basic

Books, Inc.

David Lester 1993 «On the disunity of the self: A systems

theory of personality», J. Current Psychology,

Springer New York, Volume 12, Number 4/ Dec.

pp312-325

Berne, E. 1961 Transactional analysis in psychotherapy:

A systematic individual and social psychiatry London:

Souvenir Press (Originally published in 1961 by N.

Y.: Grove Press)

Dusay, J. M. 1972 Egograms and the “constancy

hypothesis” Transactional Analysis Journal, 2, 37-42.

Stewart, I. 2001 Ego states and the theory of theory: The

strange case of the little professor Transactional,

Analysis Journal, 31, 133-147.

Trautmann, R. L. & Erskine, R. G. 1981 Ego state

analysis: A comparative view Transactional Analysis

Journal, 11, 178-185.

Woollams, S. & Brown, M. 1978 Transactional Analysis:

A modern and comprehensive text of TA theory and

practice MI: Huron Valley Institute Press.

J.Weizenbaum, 1966 "ELIZA - A Computer Program for

the Study of Natural Language Communication

Between Man and Machine", Communications of the

Association for Computing Machinery, Vol.9, pp.36-45.

Hakura, J., Kurematsu, M., Fujita, H., 2008 An

Exploration toward Emotion Estimation from Facial

Expressions for Systems with Quasi-Personality,

International Journal of Circuits, Systems and Signal

Processing, Vol. 1, No. 2, 137-144.

Hakura, J., Kurematsu, M., Fujita, H 2009 «Facial

Expression Invariants for Estimating Mental States of

Person» Frontiers in Artificial Intelligence and Appli-

cation series, Volume 199, New Trends in Software

Methodologies, tools and Techniques (SoMeT_09),

pp.518-530, IOS press, ISBN: 978-1-60750-049-0.

Kurematsu, M., Ohashi, M. Kinoshita,O. Hakura, J. And

Fujita, H., 2009: “An Approach to implement Listeners

Estimate Emotion in Speech” Frontiers in Artificial

Intelligence and application series, Volume 199, New

Trends in Software Methodologies, tools and

Techniques (SoMeT_09),.pp531-540, IOS press,

ISBN: 978-1-60750-049-0.

OKI FSE Ver. 4, A Face Recognition Middleware for

Embedded System: http://www.oki.com/en/press/

2008/07/z08019e.html

Tanaka, M., Noguchi, M 2000: Concept Retrieval of

Medical Text using UMLS, Japan Journal of Medical

Informatics, Vol.20, pp.934-935.

Smith, 2000, Reforming Markets in Health Care-An

Economic Perspective, Open University Press,

Buckingham, 2000.]

Mikkola, 2003, Hospital Pricing reform in the public

health care system- an empirical case study from

Finland, International journal of Health Care Finance

and Economics, 3 (4) 267-286.

NIPSSR, 2006; National Institute of Population and Social

Security Research, “Population Statistics of Japan,”

2006; Tokyo: NIPSSR.

Leflar,2005: Leflar, R.B and F. Iwata, “Medical Error as

Reportable Event, as Tort, as Crime: A Transpacific

Comparison,” Widener Law Review 189, no.25 (2005).

VIRTUAL MEDICAL DOCTOR SYSTEMS - Status Progress Report on Virtual Medical Doctor System (VDS)

Interaction Interface