Synthesis of Chemicals

1. Mark D. Kats (born in 1937, higher education) - an applied mathematician, doctor of science, academician of Ukrainian Production Engineering Academy and Ukrainian Academy of Ecological Sciences, corresponding member of International Academy of Computer Sciences and Systems. 37/24 Donetskaya St., Severodonetsk Lugansk Region 349940 Ukraine Tel.: (380-6452) 30875, E-mail: root@ixt.lg.ua (Kats M.D.).

2. Name of the project.

"Purposeful synthesis of chemicals having preset physical and chemical properties."

3. Field for the offer application.

Biologically active substances. medical preparations, synthetic dyes, etc.

4. Description of the offer.

Synthesis of new chemicals having preset properties is an extremely labor-consuming task because almost always improvement of one property causes deterioration of some others.

Efficiency of research in the field of new organic chemicals synthesis can be sharply increased if we manage to find a relationship between a molecule structure and physical and chemical properties of the chemical.

We have developed a new mathematical simulation method - a mosaic portrait method - that allows to solve this problem. A table of experimental data is an initial material for this solution; each line of the table contains information about input variables (chemical formula of one chemical) and output variables (experimentally defined physical and chemical properties of the chemical).

When making a mosaic model the structure of a chemical is represented as follows: in each position a corresponding code is given to each substitute appearing in experimental data, and the molecule is described with a corresponding code chain.

The generalized index of physical and chemical properties takes one of two possible values: 1 - "good" if all output variables meet preset limits, and 0 - "bad" if at least one variable does not meet the above limits.

Based on the table obtained after the above mentioned representation and using the mosaic portrait method we found combinations of substitute codes which can be found in formulae of chemicals having a certain value of generalized index (e.g., 1) and are not found in any formulae of chemicals having another value thereof (e.g., 0).

These combinations form a mosaic model of relationship between the set of physical and chemical properties and chemical structure of the chemical class studied.

This model has been used as a basis for development of a formal method to synthesize formulae of new compounds potentially possessing preset physical and chemical (consumer) properties.

Application of this offer will allow:

- to create informative mathematical models of relationship between the structure of a chemical compound class and physical and chemical models that are interesting for an explorer;

- to create informative mathematical models of relationship between the structure of a chemical compound class and any set of physical and chemical properties;

- to use the obtained models for prediction of physical and chemical properties (sets of properties) of new, previously unknown compounds that belong to the chemical compound class studied; this work is performed based on the chemical formulae of the compounds;

- to synthesize formulae of compounds which potentially have preset properties (a set of preset consumer properties);

- to perform purposeful synthesis of new chemical compounds having preset physical and chemical properties;

- to achieve substantial reduction of time, labor and cost required for the development.

5. Advantages in comparison with analogues.

Among methodic approaches used to synthesize new compounds there is not any one known that would allow to create formally a chemical formula of a compound potentially having preset physical and chemical properties.

6. Potential users.

R&D Institutes and research centers of companies developing new biologically active substances, medical preparations, synthetic dyes, etc.

7. Finality of the development.

Methods for studying relations between the chemical structure (chemical formula) of certain class compounds and physical and chemical properties thereof as well as purposeful synthesis of new, previously unknown compounds of this class potentially having preset consumer properties have been mastered and have shown good test results.

E.g., this method was used to obtain the model of a set of consumer properties (light fastness, selectivity and stability to sublimation) vs. the structure of disperse monoazodyes.

This model was used as a basis to predict properties of 73 new previously unknown dyes by their chemical formulae. After these dyes have been synthesized and their color properties have been experimentally found it appeared that the prediction was right for 87% cases.

Based on this model and using logical programming method formulae of 16 new dyes were synthesized. After their chemical synthesis and color testing it appeared that 14 dyes met the set requirements in all properties and for 2 dyes values of stability to sublimation were 0,5 points lower than preset ones; this does not exceed the error limit for the research method selected [1].

The most important methodic works and a series of examples of their practical use are given in articles [1-7].

1. M.D.Kats, E.I.Mostoslavskaya. Structure of disperse monoazodyes vs. consumer properties thereof referring to lavsan. - Zhurnal prykladnoy khimii, 1983, No.9, pp.2135-2141.

2. N.V.Lysun, M.D.Kats, G.E.Krichevsky. Purposeful synthesis of dyes having preset properties referring to polyamide fibers. - Khimia and khimicheskaya tekhnologiya, No.6, 1984, pp.700-703.

3. M.D.Kats, N.V.Lysun, E.I.Mostoslavskaya, G.E.Krichevsky. - Study of disperse monoazodyes structure vs. light stabilities thereof referring to polyamide fiber. - Zhurnal prykladnoy khimii, 1988, No.5, pp.1196-1199.

4. M.D.Kats, G.E.Krichevsky. Development of empirical relationship of organic compound properties vs. their structure. - Tekhnologiya tekstilnoy promyshlennosty, 1979, No.4.

5. M.D.Kats, G.E.Krichevsky. Mathematical model of disperse monoazodye light stabilities vs. their structure. - Tekhnologiya tekstilnoy promyshlennosty, 1979, No.5.

6. M.D.Kats. Method for development of the empirical relationship: structure of an organic compound of a certain class vs. its reactivity. - Zhurnal prykladnoy khimii, 1984, No.1, pp.180-182.

7. M.D.Kats, G.E.Krichevsky. Plotting relationship of benzene series azocompounds vs. their resistance to photodestruction referring to polyester fibers. - Zhurnal prykladnoy khimii, 1984, No.1, pp.144-149.

8. Protection of the offer.

Mosaic portrait method is used as methodological basis for studying chemical compound structures vs. their properties as well as purposeful synthesis of chemical formulae of new compounds potentially having preset consumer properties. It is not protected but the main part of algorithm ensuring polynomiality of computer time and the dependence time of realization vs. problem dimensionality, correspondingly, was not published and the computer software for its realization is possessed only by the author.

9. The ownership for the offer belongs to Marc D. Kats.

10. Brief Introduction of the Company

Research and Production Enterprise METROKOM

11 Egorov st., Severodonetsk,

Lugansk region, Ukraine, 349940

Fax No. (380-6452) 47820.

Director General - Victor A. Lemes, corresponding member of Ukrainian Production Engineering Academy and Ukrainian Academy of Ecological Sciences, tel. (380-6452) 40156.

Deputy Research Director - Mark D.Kats, doctor of science, tel.: (380-6452) 30875

RPE METROCOM is a multi-branch institution. One of the main direction of its activities is

Rendering intellectual services in solving wide range of research and application problems the solution of which by known methods presents serious and in many cases insuperable methodic and computation difficulties.

Such problems include, for example, construction of mathematical models for:

- differential diagnosis of diseases having similar symptoms;

- prediction of disease progress and outcome;

- selection of optimal treatment strategy for a certain disease taking into consideration individual features of the patient;

- selection of one variant of surgical interference out of many others based on remote consequences criteria;

- early (or even in latent period) diagnosis of chronic diseases having life-threatening prognosis (oncological, etc.);

- preliminary screening based on mass preventive examination data;

- study of relations by the table of experimental data obtained as a result of medical examination.

This enterprise developed unique research methodology allowing to use information obtained at observation conditions as well as formalized procedures for construction of informative mathematical models of objects of any physical nature and for solution of problems referring to optimization, diagnosis and behavior prediction for systems studied.

Specialists of RPE METROCOM have for many years successfully solved many complicated research and application problems in medicine, chemistry, biology, sociology as well as chemical, metallurgical, biotechnological, textile, etc. technologies.

The enterprise has 65 major employees; it was re-registered in 1992. The enterprise has collective form of property.

Some data about the author of the offer

Mark D. Kats is a doctor of science, academician of Ukrainian Production Engineering Academy and Ukrainian Academy of Ecological Sciences, corresponding member of International Academy of Computer Sciences and Systems. He has been dealing with mathematical problems of research methodology for "large" technical, biological and social systems for more than 25 years.

He has developed new highly efficient methods for studying objects of any physical nature based on observation data ("passive" experiment).

These methods have been practically checked for many years and demonstrated high efficiency in solving many complicated problems in various fields of science and technology (medicine, biology, chemistry, sociology as well as chemical, metallurgical, biotechnological, textile, etc. technologies).

M.D.Kats is the author of more than 100 publications and 12 inventions.

Due to the fact that the human body is very complicated medical diagnostics at present is not a science but rather an art of a few highly qualifies professionals. Due to inadequacy of mathematical methods known and to the difficulty of the problem multiple efforts to formalize the diagnosis process using mathematical models did not come up to expectations. As an alternative the problem was solved in a roundabout way, i.e. by developing expert systems that formalize subjective knowledge possessed by specialists. However after huge amounts of money were spent for their development it became clear that the knowledge of specialists is not sufficient for reliable differential diagnosis, especially in case of diseases having similar symptoms (those that are difficult to differentiate).

Vital progress in the field of medical diagnosis and its convert ion from intuitive art to regular science having high level of formalization can be achieved in case of application of a mathematical apparatus allowing, by using formalized logical procedures based on experimental data table each line of which contains symptom values and verified diagnosis of one patient, to generate objectively (without expert involvement) differential syndromes specific for each disease differentiated.

We have developed such a mathematical apparatus, tested it, and for many years it has been successfully used for differential diagnosis of diseases that are difficult to differentiate.

RPE METROCOM proposes cooperation in development and commercialization of unique intelligent systems for computer-aided differential diagnosis of any groups of diseases that are difficult to differentiate.

As to the accuracy of diagnosis intelligent systems that are commercialized as software packages vitally surpass similar expert systems; expenses and computer-time required for their development are much lower. In case of corresponding advertising they can completely supplant expert systems of similar purpose from intelligent medical product market.

1. Analysis of the problem status

Diagnosis was in the past, is at present and will be in future the most important problem of medicine and the accuracy of diagnosis achieved at certain historical periods generally determines the state-of-the-art in medical science.

Examination of a patient at modern diagnosis centers (data provided by anamnesis, physical investigation, laboratory and instrument methods, clinical treatment, etc.) gives a great scope of basic information (more than 300 characteristics that are measured mainly by numerical scales). If each of these characteristics is measured only by most simple name-scales ("yes-no", "more-less") the amount of basic data will make up to 2 bits to 300th power which is much higher than the number of elemental particles in the whole visible Universe.

Due to the fact that the human body is very complicated and is characterized by practically infinite number of disease symptoms as well as to the fact that symptoms and clinic of a disease are greatly influenced by the individual features of a patient and because of limited knowledge of specialists, medical diagnosis nowadays is not a science but rather an art of a few highly qualified professionals.

Medical diagnosis is to some extent similar to technical diagnosis. Despite of the fact that problems of technical diagnosis are much less important, their solution without application of mathematical models according to paradigm accepted in modern science is considered not only incorrect but even indecent.

After computer appearance and development of applied mathematics research attempting to formalize the diagnosis process using mathematical models boomed. The results of this work mainly did not come up to expectations and rare success was caused either by relative simplicity of the problem (differentiation of diseases that are rather remote in their symptom space) or by its inadequate simplification. As a result, at best models "diagnosing a disease not worse than an average doctor" appeared.

And this is not surprising because due to the lack of a priori information on the model structure, absence of correct formal structural identification methods and reliable methods of parameter identification in case of processing data bulk obtained in observation conditions ("passive experiment"), simulation of complicated objects using modern mathematical methods also still is an art.

Principal difficulties in "large" system simulation (and medical diagnosis systems also belong to such systems)) made it necessary to look for roundabout ways. One of these ways being intensively developed at present is creation of expert medical systems. An expert system is a computer system incorporating formalized knowledge possessed by specialists in a certain concrete subject which is able to take expert decisions within this subject (to solve problems in such a way as a man-expert would do).

Efficiency of the expert system operation first of all depends on quantity and quality of the information available in its knowledge base. This is a weak point of expert systems because (1) knowledge base is formed on the basis of subjective ideas of experts whose knowledge is limited and (2) specialists are not able to formalize their knowledge as clear rules; moreover many of them would not at all think of the rules that they follow.

After much money has been spent for development of a great number of various medical expert systems and objective analysis of their efficiency has been carried out, the same as known a priori, from the definition, will come out:

- When solving relatively simple problems of differential diagnosis (those which are successfully solved by specialists using non-formalized approaches), accuracy of diagnosis achieved by means of expert systems and by an expert will be close and sufficient.

- But when solving the most important and complicated problems of differential diagnosis, namely when differentiating diseases having similar symptoms; prognosing progress of a disease (for instance, acute myocardial infarction complications), long-term consequences of surgical interference depending on the operation type selected; in case of early (including the latent period) diagnosis of chronic diseases with unfavorable for life prognosis (oncological diseases, chronic nephrism, etc.), accuracy of diagnosis achievable by means of experts systems and by an expert will be close and substantially insufficient.

2. DEFINITIONS TAKEN AND FORMULATION OF DIFFERENTIAL DIAGNOSIS PROBLEMS

Quite a good progress in medical diagnosis and its conversion from intuitive art of a few talented professionals into a strict science with high level of formalization can be achieved only by transfer from the use of subjective diagnosis information provided by experts to objective information concerning dependence of diagnosis on individual characteristics of a patient and symptom values that are generated using methods provided by artificial intelligence.

We assume that artificial intelligence is an algorithm that allows, based on the table of experimental data describing behavior of the object (system) of any physical nature and not using subjective information about the structure of a model provided by an expert and using formalized procedures, to construct an objective mathematical model of the object (system) under study carrying quite a large scope of new, untrivial information about interrelations between input and output variables of the object under study that was previously unknown to the specialists in this subject.

As applied to medical diagnosis these interrelations for each disease differentiated shall be presented as a number of differential syndromes inherent to this disease only.

We assume that formal differential diagnosis is a formalized procedure realized by a computer and enabling to reliably differentiate each disease from the group of diseases close as to symptoms while using appropriate mathematical models.

Based on this definition differential diagnosis problems can include the following:

- differential diagnosis within the group of diseases close as to symptoms;

- prognosis of disease progress and outcome;

- early diagnosis of diseases dangerous for life (for instance, cancerous disease in the latent period).

The problem of differential diagnosis model construction can be mathematically formulated as follows:

GIVEN:

Table of experimental data M=XxY (X={Xij}, i=1,m, j=1,n; Y={Yil}, l=1,k), each line of the table contains information about symptoms values (Xij) and verified diagnosis Yil for the i-th patient. (Here m is a number of lines (patients) in table M, n is a number of columns (symptoms) in table M, K is a number of diseases to be differentiated.)

required: to construct, based on table M and using formalized procedures, a mathematical model consisting of K disjunctions of differential syndromes each disjunction containing differential syndromes of only one of K diseases to be differentiated.

3. METHODS intended FOR SOLUTION OF FORMAL DIFFERENTIAL DIAGNOSIS PROBLEMS

If based on examination results a table has been obtained and each line of this table contains symptom values and verified diagnosis for one patient and all patients examined suffer from a set of diseases difficult to differentiate from each other, a mathematical model of differential diagnosis can be constructed using a new mathematical simulation method called "mosaic portrait".

This method essentially realizes the following formalized procedures:

a) conversion of initial experimental data table M to table M' using formalized procedure for splitting the range of values of each symptom into subranges (conversion from continual scales used for measurement of symptoms to discrete ones). In this case a specific code is applied to each subrange of values of each symptom;

b) search of code combinations which can be found in table M' in lines corresponding to one disease and are not found in any line for other diseases.

These combinations are interpreted as differential syndromes of a corresponding disease. The mosaic model obtained in such a way consists of K disjunctions, each containing differential syndromes of one of K diseases to be differentiated.

Well-known realization methods as per paragraph b) require complete search for all possible combinations of value subranges for all symptoms and belong to so called NP-problems. Computer time required for the solution of such problems depends exponentially on the number of input variables.

When the number of symptoms is more than 15 these problems are practically insoluble.

Application of the mosaic portrait method allows to solve problems with dimensionality of the order of 1000 input variables in reasonable time.

4. NEW POSSIBILITIES ARISING WHEN USING MOSAIC PORTRAIT METHOD FOR SOLUTION OF MEDICAL PROBLEMS

Application of the mosaic portrait method allows to solve a number of critical medical problems solution of which by means of well-known methods caused serious and mostly insoluble methodical and computation difficulties.

These problems include the following:

- formal differential diagnosis of diseases having similar symptoms;

- formal prognosis of disease progress and outcome alternatives;

- formal selection of one possible surgical interference out of a set of various alternatives based on long-term consequences criteria;

- early (or even in the latent period) diagnosis of chronic diseases with the prognosis dangerous for life (oncological diseases, etc.);

- preliminary screening based on mass preventive examination data;

- construction of informative mathematical models using the table of experimental data resulting from any medical examination.

High self-descriptiveness of mosaic models allows to make the accuracy of differential diagnosis much higher, to achieve substantial reduction of its cost and load on a patient by excluding invasive and low-informative diagnostic procedures and also to formalize diagnosis procedure and to realize it by a computer.

5. EXAMPLES OF PRACTICAL APPLICATION OF NEW DIFFERENTIAL DIAGNOSIS METHODS

At present we acquired a large experience in using the mosaic portrait method for construction of differential diagnosis models for diseases difficult to differentiate and their practical application for formal diagnosis and prognosis of disease outcome.

A method for prognostication of myocardial infarction complications at the acute phase has been developed in collaboration with the Military Medical Academy, Saint-Petersburg [1,2].

Differential syndromes typical for each of myocardial infarction consequences have been obtained based on experimental data containing information about patients who died of infarct complications (cardiogenic shock, perfusion insufficiency, ventricular fibrillation, cardiac rupture) and had infarct without consequences.

The method for prognostication of myocardial infarction consequences was adopted at the Military Medical Academy, Saint-Petersburg, in hospital No.23, Moscow, in hospital No.20 and polyclinic No.42, Saint-Petersburg. 80 to 88% of prognoses have been verified by clinic data and in case of lethal outcome - by results of pathologicoanatomic investigation.

As a result of preventive treatment aimed at studying prognosticated complication (complications) the rate of death of large-nidus infarction was reduced by 37% and that of small-nidus infarction - by 45%.

Based on the results of this work, a software package for an intelligent system realization called "prognosis of myocardial infarction complications at acute phase" was developed.

Initial information about the state of a patient including anamnesis, examination data, electric cardiography data (39 indicants totally) is entered by keystroke in the question-answer mode.

This package solves the following problems:

- prognostication of one or several possible myocardial infarction complications based on the information about the patient's state collected on his first day in the hospital;

- if several complications are prognosticated, estimation of the probability for each of them to come true;

- recommendations on preventive therapy for a complication (complications) being prognosticated and corresponding symptoms-eliminating therapy taking into account compatibility of medicines and treatments;

- every two days a new prognosis is made based on treatment results, correspondingly recommendations on preventive and symptoms-eliminating therapy in accordance with this prognosis are given;

- on inquiry information about differential syndromes used as a basis for the prognosis is displayed;

- information about the patient, prognostication of complications, syndromes used as a basis for the prognosis and recommended treatment are input into the data base.

A simple (without gastroscopy) and express method of differential diagnosis "gastric ulcer - gastric cancer" with accuracy of 96.4 % has been developed and put into practice in collaboration with the Military Medical Academy.

Based on the results of this work, a software package for an intelligent system realization called "DIFFERENTIAL DIAGNOSIS GASTRIC ULCER - GASTRIC CANCER" was developed.

A method for differential diagnosis of various pathogeneses ("shock lung", aspiration, atelectasis, toxic-septic, hypostatic and bronchial pneumonia ) for burnt patients was developed in cooperation with the Kharkov Centre for Burnt Patients; this method ensures early (within 1 to 2 days of disease progress) diagnosis, allows to differentiate the therapy and increase the treatment efficiency [3,4]. Based on the results of this work, a software package for an intelligent system realization called "DIFFERENTIAL DIAGNOSIS of pathogenesis of pneumonia for burnT patients" was developed.

In collaboration with the Military Medical Academy, based on biomicroscopy of bulbar conjunctiva, reliable and express methods of differential diagnosis called "2nd phase of hypertensive disease - chronic diffuse glomerulonephritis with hypertension" and "chronic glomerulo-pyelonephritis" were developed and put into practice.

6. MAIN TASKS AND FINAL purpose OF THE WORK

The main task of the work is to create an efficient intelligent system having no analogues in the world practice; the system is realized by a computer and while using formalized procedures allows to carry out correct computer-aided diagnosis within a group of diseases that are difficult to differentiate.

The depth of the medical diagnosis system created will be constantly increasing: diagnosis accuracy will become higher due to feedback - model after-education based of reliably verified errors of formal diagnosis.

After the intelligent differential diagnosis system is completely developed and patented it will be represented as a final commercial product - PC software package.

As practically all EXPERT SYSTEMS AND INTELLIGENT SYSTEMS well-known at present and allowing to obtain knowledge using the mosaic portrait method use the same language of algebra of logic in which any hypothesis is formulated as a proposition "if..... then..." and the expert systems accumulate (or must do it) all well-known knowledge in this field, then if expert and intelligent systems created for the same field are available, their intersection (common hypotheses) is an a priori known, trivial information; logic difference between propositions of expert and intelligent systems is misinformation (false information); logic difference between propositions of intelligent and expert systems is new, untrivial information unknown for the specialists in this field.

That is why intelligent medical systems can replace expert systems at the market of intelligent medical products.

7. Program of work

Formal differential diagnosis models can be developed in collaboration with any medical institutions (R&D Institute, university, diagnognostic center, hospital, etc.) which:

- specialize in studying (treating) of certain diseases;

- have qualified specialists and up-to-date diagnostic equipment for correct diagnosis verification;

- have archival materials or possibility to examine not less than 60 patient suffering of each disease included in the group of diseases to be differentiated within an acceptable time period (up to one year).

7.1 More precise definition of the problem. collection of experimental data required

7.1.1 List of nosologic units requiring differentiation shall be finalized.

7.1.2 A list of input variables which can be potentially used to solve the problem shall be made. (This list must be surplus i.e. in addition to well-known variables which are selected based on positive experience in differential diagnosis of diseases studied it shall also contain other variables which are selected based on intuition of specialists.

7.1.3 A formalized history shall be developed, i.e. a unified form containing list of symptoms determined as per paragraph 7.1.2.

7.1.4 Minimum and sufficient scope of experimental studies, required to solve differential diagnosis problem and to find optimum treatment taking into account individual features of a patient, shall be determined.

7.1.5 Patients with diseases as per paragraph7.1.1 shall be purposefully examined; correct verification of diagnosis within the group of diseases under study shall be organized; results of examination using the unified form (see paragraph 7.1.3) shall be recorded.

7.1.6 Collection of experimental data shall be finished with a table each line of which contains information about symptoms and verified diagnosis for one patient.

7.2 DEVELOPMENT OF INTELLIGENT COMPUTER SYSTEM PROPER includes THE FOLLOWING STAGES:

7.2.1 Construction of differential diagnosis mathematical models based on the table of experimental data (see paragraph 7.1.6).

7.2.2 Minimization of the models as per paragraph 7.2.1.

7.2.3 Evaluation of adequacy of differential diagnosis models using new experimental data.

7.2.4 Repetition of paragraphs. 7.2.1 and 7.2.2 using experimental data including the initial table as per paragraph 7.1.6 and the table used to evaluate adequacy of the model (paragraph 7.2.3).

7.2.5 Creation of an intelligent medical system for development of a software package providing solution of the problem stated.

7.3 Constant after education of the system

As initial experimental data used for construction of a model may contain diagnosis errors, some errors may also occur in case of formal differential diagnosis. It is found out experimentally that percentage of diagnosis errors in the initial data (accuracy of diagnosis achieved at a medical institution whose experimental data were used) and while using the model are practically the same. After education of the model based on additional experimental data providing actual recording of formal diagnosis errors will allow to construct the next version of the model ensuring diagnosis with less percentage of errors than made by specialists.

7.3.1 Development of a formalized procedure of the system self-improvement - after education of the models using reliably verified errors of formal diagnosis.

7.3.2 Collection of information about actual cases of inaccurate differential diagnosis at medical institutions participating in the development of the system.

7.3.3 Correction of the models and software package using information about actual cases of inaccurate diagnosis. (Sequential development of new, more precise versions of the system).

7.4 PATENTING OF AN INTELLIGENT MEDICAL SYSTEM

The models obtained by mosaic portrait methods contain a great number of new, unknown to the medical science differential syndromes for each disease to be differentiated which fact will allow to patent the corresponding system.

8. COMMERCIALIZATION OF THE SYSTEM

8.1 Arrangement of advertising campaign:

- development of demonstration disks;

- publications in medical journals, papers and presentations of demonstration versions at scientific conferences, delivery of advertising materials to practical medical institutions, etc.

8.2 Commercialization of the system.

References:

1. G.M.Yakovlev, V.N.Ardashev, M.D.Kats, T.A.Galkina. Mosaic portrait method in the myocardial infarction prognostication. Cardiology, 1981, No.6.

2. Prognosis of outcome and complications of acute myocardial infarction (edited by V.P.Malygina). Moscow, Voyenizdat, 1987, p.128.

3. L.M.Tsogoeva, D.E.Pekarsky, S.F.Kudrya, M.D.Kats. Mosaic portrait method in differential diagnosis of pneumonia for burned patients. Clinic surgery, 1991, No.3.

4. L.M.Tsogoeva. Differential diagnosis and peculiarities of treatment of various forms of pneumonia for burned patients. Abstract of candidate thesis, Kharkov, 1991.

5. V.S.Zaitsev. Microcirculation state and rheologic properties of blood at hypertensive disease, chronic glomerulo- and pyelonephritis. Abstract of candidate thesis. Leningrad, 1984.

In case you agree to our offer in principle, within a month's period we are ready to present a draft two-sided agreement stipulating our relations at all stages of the intelligent system development and implementation.

Information supplied by the Author December 1998.  Page last updated: January 19, 2004