Socmedica
Decision Support System for clinical practice created
on the basis of
the United Medical Knowledge Base
1. Problem
Medical errors and unpredicted complications
on various stages of diagnostics and treatment
As a consequence:
- high mortality rate
- unpredicted complications
- enormous costs
1. Problem
Anatomy of medical errors
Due to medical errors:Due to medical errors:
170 000170 000 patients annually get disabled
50 00050 000 deaths occurs annually
www. лига защиты пациентов
440 000440 000 deaths occurs annually
due to medical errors
Journal of Patient Safety, Forbes
Before a medical error goes public, it
pass through a multilevel “filter”:
1. A large number of errors remains
on physician’s conscience; a half of
medical specialists does not even
realize their fault.
2. Errors are partly covered up by
solidarity medical community.
3. Next, management of the
institution cares about its statistics.
Only numbers that pass all three
filters are published.
1. Problem
Costs of medical errors
$ 7,3 B$ 7,3 B annually spent on medical errors
www.cpmhealthgrades.com
An average general in-patient institutions spent annually
≈≈ $1,5 M$1,5 M on medical errors
1. Problem
of health insurance company
Lack of supervision of treatment
Compliance of diagnostic and treatment procedures to the applied standards as
well as reasonableness of the applied standards to a particular patient is a complex
routine task. It requires a staff of experts involving different medical specialists. The
result is fraud and abuse of services provided by insurance companies.
Prediction of possible „costly” diseases in a client.
Decision making after insurable event requires a big staff of highly qualified
experts.
2. Demand / market
A substitute is Electronic Health Records systems (EHR systems).
Main consumers
– b2b – medical institutions, insurance companies and manufacturers
of EHR systems;
– b2c – physicians, patients and internet users, who care about their
health;
– b2g – government agencies that participate in the computerization
of healthcare
Volume of the Russian market of EHR systems is 11.5 billion RUB per
year.
Its growth rate is 9 % per year.
2. Demand / market
Global market
EHR – market of Electronic Heath Records systems (Medical IT systems)
CDSS – target segment (Clinical Decision Support Systems)
• Market size for 2014 - $3,74B;
• CAGR - 25%.
According to Marketsandmarkets.
Increased demand for analytical IT decisions that allow to reduce the probability of medical errors will
drive the growth of global market decision support systems for clinical practice. They will reduce costs of
clinics and improve quality of healthcare.
2. Demand / market
Competitive comparison of the existing expert systems
Expert systems Targeted
audience
Personification
of patients Forecasting Diagnostics Decision
support Number of diseases Input data Self-
learning
Socmedica* pat, doc, clinic Y Y Y Y all any Y
IBM Watson* pat, doc, clinic ? Y Y Y oncology, urology any Y
Эксперт doc N N N Y 3 sympt, lab N
Pxdes doc N N Y N 1 (pneumoconiosis) x-ray N
EMERGE doc, clinic N N Y Y chest pain sympt, lab N
CaDet doc, clinic N Y Y Y oncology sympt, epid N
Apache III doc, clinic N Y N Y severity of patient's
condition
sympt, lab N
DXplain doc, clinic N N Y Y 2400 sympt, lab N
Germwatcher doc, clinic N N Y Y hospital infections lab N
PEIRS doc, clinic N N Y N laboratory interpretation lab N
Puff doc, clinic N N Y N pulmonary pathology sympt, lab N
SETH doc, clinic N Y Y Y clinical pharmacology sympt, lab N
easydiagnosis pat, doc N N да да ? (main groups of diseases) sympt N
nhsdirect pat N N N N
? (main groups of
diseases)
sympt N
webmd pat N N да N
? (main groups of
diseases)
sympt N
symcat pat N N да N 800 sympt, epid N
The existing expert systems are usually a local solution to a narrow range of issues.
The only example of a complete system of decision support and potential competitor is IBM Watson super computer, which now undergoes
clinical testing.
* Main advantages of Socmedica over IBM Watson:
1. Along with question-answering communication method with the system, included into IBM Watson model, Socmedica uses a principle of
background monitoring of clinical material of a patient. We believe that most physicians do not realize that they commit errors; therefore,
they will not make any requests to the system. Other physicians are too busy to make requests in timely manner. Our approach minimizes
the human factor that leads to errors.
2. In Socmedica system, a search for answer is similar to thinking pattern of a physician; semantics speak in terms of medical ontologies.
3. Solution
Decision support system for clinical practice
EMR Virtual image of
a patient
Decision support system
1. Anonymized electronic medical record
(EMR) is uploaded to the cloud
2. Any EMR format can be analyzed
3. The system creates a virtual image of the
patient
4. The virtual image is constantly adjusted and
optimized in the background
5. The system processes any inquiries up to
the moment of discharge of the patient
6. Physician receives recommendations at
the workplace
3. Solution
Example: Recommendations of the system displayed on physician’s PC
Риск развития
тромбоэмболии
легочной артерии
73%
Прогнозирование рисков
возникновения осложнений
Ранняя диагностика
госпитальных осложнений
Рекомендации системы по
профилактике,
дифференциальной
диагностике и лечению
осложнений
Мониторинг за лечебным
процессом и состоянием
пациента
4. Basic technology
UMKB
M
Model of presentation of medical
knowledge
System of modeling of knowledge
United Medical Knowledge Base (UMKB)
Algorithms of predictive analytics and
decision support
4. Basic technology
Technology of medical knowledge repre
М
We developed a model of medical knowledge representation that combines and structures
the information offered by various areas of medicine from clinical practice to molecular
biology and genetics.
13
4. Basic technology
Technology of medical knowledge representation
Constructor
of ontologies
Crowd-
sourcing
system of
knowledge
modeling
Computer-
ized analysis
of medical
texts
Integration of
knowledge
Formation of
evidence level
Real-time
analysis of
EHRs with
data
extraction
14
4. Basic technology
Computerized analysis of medical texts
ABBYY
Morphological
and Lexical
Analyzer
4. Basic technology
Result of text analysis
4. Basic technology
Example: Modeling of the pathogenesis of myocardial infarction
Intellectual property
Obtained patents and copyrights
• Modeling system for medical knowledge base – Socmedica (State Registration Certificate of a Computer
Program no. 2014618583)
• Unified classifier of medical terms “Socmedica-MT” (State Registration Certificate of a Database
no. 015620304)
• Patent “Method of determination of drug interactions and contraindications for drugs with the use of a
structured knowledge base”. Application no. 2015111641 on the 31st of March, 2015.
• Patent “Method of automatic selection of drugs”. Application no. 2015111641 on the 31st
of March,
2015.
• Graphical user interface of a decision support system for drugs prescription. Applications
no. 2015501457 and no. 2015501457.
• Trademark Соцмедика/Socmedica (Certificate of trademark no. 528331)
• Corporate identity (Trademark Certificate no. 494814)
• Algorithm of predictive analytics and differential diagnosis – (patent applications are prepared)
Experimental prototype of the Clinical Decision Support System for drug
prescription is already available at
http://www.socmedica.com/page/pharm_expert
5. Business model
Commercialization plan
1. Mobile version of the product. On the initial stage it will be distributed among physicians and patients free of charge
in order to scale of the project quickly. Subsequently, this direction can be monetized through advertising or subscription
fees.
2. Installing the product in already existing electronic health records systems (EHR systems) in healthcare institutions.
System can be introduced into the structure of any EHR system. After that, it analyzes medical e-records in the
background mode and gives conclusions with practical recommendations. Physicians regularly see and consider these
recommendations in their workplace. The cost of installation of the expert system is averagely $200 per year per
workplace. The price will vary depending on the number of workplaces. Additional source of income will be license
renewal and system management services. Planned sails volume is $1.2 million in 2016, and $17.5 million in 2020 (after
4 years).
3. Analysis of anonymized medical e-records in cloud. Healthcare institutions upload anonymized EHRs of patients into
cloud to analyze them with expert system. The system creates a virtual image of a patient and processes any requests up
to the discharge of the patient from the hospital. Decision support for one patient image will cost $10—$15 depending
on the specialization of a unit, which will be covered by healthcare institutions. Planned volume of sails is $0.5 million for
2016, and $1.9 million in 2020 (after 4 years).
4. Sell of product licenses to manufacturers and/or suppliers of EHR systems. After purchase of a license,
manufacturers and/or suppliers of EHR systems will be able to implement into clinics their own products with already
existing clinical decision support system. Today we actively negotiate with such potential partners. Manufacturers
and/or suppliers of EHR systems are interested in the integration of a clinical decision support system to improve quality
and competitiveness of their EHR. We have already made a preliminary arrangement with CompuGroupMedical (CGM)
about integration of the developed product into their system CGM CLININET. CGM is one of the world-leading
companies in the eHealth area. It delivers EHR systems in 35 countries to more than 385 000 clients. It is a good chance
for us to enter the international market.
5. Business model
131 000
EMRs
monthly
131 000
EMRs
monthly Decision
support 600
RUB
Decision
support 600
RUB
Virtual image of a
patient
Expert decision support systemExpert decision support system
in-patient units of health care
facilities (potential clients) -
661
in-patient units of health care
facilities (potential clients) -
661
Insurance company
(compulsory and voluntary
medical insurance)
Insurance company
(compulsory and voluntary
medical insurance)
Report on quality of
medical care 300
RUB
Report on quality of
medical care 300
RUB
Certificate of
insurance
Certificate of
insurance
Why will health care institutions buy our product?
3. The use of our product:
4. 1. decreases the number of medical errors and
unpredicted complications
5. 2. cuts costs and gives additional income.
3. provides individual approach to every
patient
4. improves quality of medical care
5. reduces mortality
6. improves competitive position of a
facility
7. attracts inflow of patients
+
Example of surgical hospital unit with 650 beds,
which spends about 20 million RUB monthly on
medical errors
Additional monthly income due to the increased
patient inflow.
6. Key team members
G. A. Blejyants. CEO. Cardiovascular surgeon, PhD in medicine.
More than 14 years of clinical practice.
Experience in the development of medical classifiers.
Author of the model of medical knowledge representation.
N. A. Tumanov. Executive director. Psychiatrist, PhD in medicine.
More than 14 years of clinical practice.
Experience in modeling of medical knowledge.
Experience in the creation of algorithms that operate similar to thinking pattern of a physician.
Yu. A. Isakova. Head of the project in pharmacology and pharmacy.
Pharmacist, leading researcher of the Dpt. of Clinical Pharmacology, Research Clinical Center “RZD”.
Member of Russian Society for Evidence Based Medicine, Russian & International Society for
Pharmacoeconomics and Outcomes Research (RSPOR & ISPOR).
A. V. Panosyan. IT director
Software developer
Experience in the creation of system managing artificial neural network.
Author of the modeling system of medical knowledge.
M. Guseynov. Chief programmer.
Software developer.
Experience in creating self-learning database.
Experience in creating systems managing artificial neural network.
M. G. Abgaryan. Director for external relations. PhD in engineering.
Experience in implementing systems of storage, processing and visualization of medical images in Russian
healthcare institutions. Experience in organizing development and production of professional graphic DICOM station
A. V. Lapuk. Mentor, specialist with international experience in the field of medical research.
Molecular biologist. Full member of the American Association of Cancer Research, New York Academy of
Sciences. Her valuable research experience helps the team to search for alternative niches for application
UMKB. Scientist at Vancouver Research Institute of HealthCare (British Columbia, Canada).
R. S. Melkonyan. Director of Medical department. MD.
Cardiovascular surgeon, therapist.
14 years of clinical practice. Has been studying and creating algorithms of expert system for “General practitioner”
system for the last 5 years.
M. A. Sarkisian. Director of the Division on scientific collaboration and interacademic relations. Professor at
Yevdokimov Moscow State University of Medicine and Dentistry.
18 years of experience in clinical practice. His main task is to involve academic and scientific community (from
students to senior specialists) in the process of UMKB modeling.
G. N. Mdinaradze. Specialist in insurance medicine. PhD in stomatology.
16 years of clinical practice. Since 2011 he holds position of CEO of the OOO “Rosneft Zdorovye” and Deputy Head
of Department of Social development of the OAO “NK Rosneft” where he developed and implemented programs of
insurance and medical support for employees of the “Rosneft”.
S. V. Vartanyan. Deputy director of external relations.
Employed in the ZAO “Socmedica” in the Division of cooperation with centers of medical science and medical
facilities to fill UMKB.
Supervises commercial issues.
6. Key team members
7. Stages of project development and investments needed
and required volume of investments
$1.75M
$1.75M
A technology for modeling of medical knowledge has been developed
Partnership relations with research centers have been achieved
United medical knowledge base has been created
Working prototype is ready: a decision support system for drug therapy
Decision support system for clinical practice
Stage 2:
System of risk prediction for clinical complications
Algorithms of risk prediction, which will be used in the expert system…
Stage 3:
Expert diagnostic system „Electronic therapist”
Diagnostic algorithms, which will be used in the expert system…
Stage 4:
Expert system of personal medical user support „Personal doctor”
Development of a module for the creation of individual image of patient…
1 stage
completed
Final product
8. Financial forecast
On the current stage active negotiations with prospective purchasers are carried. Contracts have been signed; the first
sell is expected within 4 months. 14 month after required investments, our company will become self-financed. Two
years after the beginning of financing, net profit should be about $0.2 million. We predict possibility of withdrawal of an
investor in the beginning of the 3rd year by selling its share to a strategic investor. As such strategic investors, we
regard large companies, leaders of EHR market.
Gevorg Blejyants
Тел: +7 (926) 991-10-41
E-mail: blejyants@socmedica.com
www.socmedica.com
Nikolai Tumanov
Тел: +7 (916) 625-90-40
E-mail: tumanov@socmedica.com
Socmedica

Decision Support System for clinical practice created on the basis of the United Medical Knowledge Base

  • 1.
    Socmedica Decision Support Systemfor clinical practice created on the basis of the United Medical Knowledge Base
  • 2.
    1. Problem Medical errorsand unpredicted complications on various stages of diagnostics and treatment As a consequence: - high mortality rate - unpredicted complications - enormous costs
  • 3.
    1. Problem Anatomy ofmedical errors Due to medical errors:Due to medical errors: 170 000170 000 patients annually get disabled 50 00050 000 deaths occurs annually www. лига защиты пациентов 440 000440 000 deaths occurs annually due to medical errors Journal of Patient Safety, Forbes Before a medical error goes public, it pass through a multilevel “filter”: 1. A large number of errors remains on physician’s conscience; a half of medical specialists does not even realize their fault. 2. Errors are partly covered up by solidarity medical community. 3. Next, management of the institution cares about its statistics. Only numbers that pass all three filters are published.
  • 4.
    1. Problem Costs ofmedical errors $ 7,3 B$ 7,3 B annually spent on medical errors www.cpmhealthgrades.com An average general in-patient institutions spent annually ≈≈ $1,5 M$1,5 M on medical errors
  • 5.
    1. Problem of healthinsurance company Lack of supervision of treatment Compliance of diagnostic and treatment procedures to the applied standards as well as reasonableness of the applied standards to a particular patient is a complex routine task. It requires a staff of experts involving different medical specialists. The result is fraud and abuse of services provided by insurance companies. Prediction of possible „costly” diseases in a client. Decision making after insurable event requires a big staff of highly qualified experts.
  • 6.
    2. Demand /market A substitute is Electronic Health Records systems (EHR systems). Main consumers – b2b – medical institutions, insurance companies and manufacturers of EHR systems; – b2c – physicians, patients and internet users, who care about their health; – b2g – government agencies that participate in the computerization of healthcare Volume of the Russian market of EHR systems is 11.5 billion RUB per year. Its growth rate is 9 % per year.
  • 7.
    2. Demand /market Global market EHR – market of Electronic Heath Records systems (Medical IT systems) CDSS – target segment (Clinical Decision Support Systems) • Market size for 2014 - $3,74B; • CAGR - 25%. According to Marketsandmarkets. Increased demand for analytical IT decisions that allow to reduce the probability of medical errors will drive the growth of global market decision support systems for clinical practice. They will reduce costs of clinics and improve quality of healthcare.
  • 8.
    2. Demand /market Competitive comparison of the existing expert systems Expert systems Targeted audience Personification of patients Forecasting Diagnostics Decision support Number of diseases Input data Self- learning Socmedica* pat, doc, clinic Y Y Y Y all any Y IBM Watson* pat, doc, clinic ? Y Y Y oncology, urology any Y Эксперт doc N N N Y 3 sympt, lab N Pxdes doc N N Y N 1 (pneumoconiosis) x-ray N EMERGE doc, clinic N N Y Y chest pain sympt, lab N CaDet doc, clinic N Y Y Y oncology sympt, epid N Apache III doc, clinic N Y N Y severity of patient's condition sympt, lab N DXplain doc, clinic N N Y Y 2400 sympt, lab N Germwatcher doc, clinic N N Y Y hospital infections lab N PEIRS doc, clinic N N Y N laboratory interpretation lab N Puff doc, clinic N N Y N pulmonary pathology sympt, lab N SETH doc, clinic N Y Y Y clinical pharmacology sympt, lab N easydiagnosis pat, doc N N да да ? (main groups of diseases) sympt N nhsdirect pat N N N N ? (main groups of diseases) sympt N webmd pat N N да N ? (main groups of diseases) sympt N symcat pat N N да N 800 sympt, epid N The existing expert systems are usually a local solution to a narrow range of issues. The only example of a complete system of decision support and potential competitor is IBM Watson super computer, which now undergoes clinical testing. * Main advantages of Socmedica over IBM Watson: 1. Along with question-answering communication method with the system, included into IBM Watson model, Socmedica uses a principle of background monitoring of clinical material of a patient. We believe that most physicians do not realize that they commit errors; therefore, they will not make any requests to the system. Other physicians are too busy to make requests in timely manner. Our approach minimizes the human factor that leads to errors. 2. In Socmedica system, a search for answer is similar to thinking pattern of a physician; semantics speak in terms of medical ontologies.
  • 9.
    3. Solution Decision supportsystem for clinical practice EMR Virtual image of a patient Decision support system 1. Anonymized electronic medical record (EMR) is uploaded to the cloud 2. Any EMR format can be analyzed 3. The system creates a virtual image of the patient 4. The virtual image is constantly adjusted and optimized in the background 5. The system processes any inquiries up to the moment of discharge of the patient 6. Physician receives recommendations at the workplace
  • 10.
    3. Solution Example: Recommendationsof the system displayed on physician’s PC Риск развития тромбоэмболии легочной артерии 73% Прогнозирование рисков возникновения осложнений Ранняя диагностика госпитальных осложнений Рекомендации системы по профилактике, дифференциальной диагностике и лечению осложнений Мониторинг за лечебным процессом и состоянием пациента
  • 11.
    4. Basic technology UMKB M Modelof presentation of medical knowledge System of modeling of knowledge United Medical Knowledge Base (UMKB) Algorithms of predictive analytics and decision support
  • 12.
    4. Basic technology Technologyof medical knowledge repre М We developed a model of medical knowledge representation that combines and structures the information offered by various areas of medicine from clinical practice to molecular biology and genetics.
  • 13.
    13 4. Basic technology Technologyof medical knowledge representation Constructor of ontologies Crowd- sourcing system of knowledge modeling Computer- ized analysis of medical texts Integration of knowledge Formation of evidence level Real-time analysis of EHRs with data extraction
  • 14.
    14 4. Basic technology Computerizedanalysis of medical texts ABBYY Morphological and Lexical Analyzer
  • 15.
  • 16.
    4. Basic technology Example:Modeling of the pathogenesis of myocardial infarction
  • 17.
    Intellectual property Obtained patentsand copyrights • Modeling system for medical knowledge base – Socmedica (State Registration Certificate of a Computer Program no. 2014618583) • Unified classifier of medical terms “Socmedica-MT” (State Registration Certificate of a Database no. 015620304) • Patent “Method of determination of drug interactions and contraindications for drugs with the use of a structured knowledge base”. Application no. 2015111641 on the 31st of March, 2015. • Patent “Method of automatic selection of drugs”. Application no. 2015111641 on the 31st of March, 2015. • Graphical user interface of a decision support system for drugs prescription. Applications no. 2015501457 and no. 2015501457. • Trademark Соцмедика/Socmedica (Certificate of trademark no. 528331) • Corporate identity (Trademark Certificate no. 494814) • Algorithm of predictive analytics and differential diagnosis – (patent applications are prepared)
  • 18.
    Experimental prototype ofthe Clinical Decision Support System for drug prescription is already available at http://www.socmedica.com/page/pharm_expert
  • 19.
    5. Business model Commercializationplan 1. Mobile version of the product. On the initial stage it will be distributed among physicians and patients free of charge in order to scale of the project quickly. Subsequently, this direction can be monetized through advertising or subscription fees. 2. Installing the product in already existing electronic health records systems (EHR systems) in healthcare institutions. System can be introduced into the structure of any EHR system. After that, it analyzes medical e-records in the background mode and gives conclusions with practical recommendations. Physicians regularly see and consider these recommendations in their workplace. The cost of installation of the expert system is averagely $200 per year per workplace. The price will vary depending on the number of workplaces. Additional source of income will be license renewal and system management services. Planned sails volume is $1.2 million in 2016, and $17.5 million in 2020 (after 4 years). 3. Analysis of anonymized medical e-records in cloud. Healthcare institutions upload anonymized EHRs of patients into cloud to analyze them with expert system. The system creates a virtual image of a patient and processes any requests up to the discharge of the patient from the hospital. Decision support for one patient image will cost $10—$15 depending on the specialization of a unit, which will be covered by healthcare institutions. Planned volume of sails is $0.5 million for 2016, and $1.9 million in 2020 (after 4 years). 4. Sell of product licenses to manufacturers and/or suppliers of EHR systems. After purchase of a license, manufacturers and/or suppliers of EHR systems will be able to implement into clinics their own products with already existing clinical decision support system. Today we actively negotiate with such potential partners. Manufacturers and/or suppliers of EHR systems are interested in the integration of a clinical decision support system to improve quality and competitiveness of their EHR. We have already made a preliminary arrangement with CompuGroupMedical (CGM) about integration of the developed product into their system CGM CLININET. CGM is one of the world-leading companies in the eHealth area. It delivers EHR systems in 35 countries to more than 385 000 clients. It is a good chance for us to enter the international market.
  • 20.
    5. Business model 131000 EMRs monthly 131 000 EMRs monthly Decision support 600 RUB Decision support 600 RUB Virtual image of a patient Expert decision support systemExpert decision support system in-patient units of health care facilities (potential clients) - 661 in-patient units of health care facilities (potential clients) - 661 Insurance company (compulsory and voluntary medical insurance) Insurance company (compulsory and voluntary medical insurance) Report on quality of medical care 300 RUB Report on quality of medical care 300 RUB Certificate of insurance Certificate of insurance
  • 21.
    Why will healthcare institutions buy our product? 3. The use of our product: 4. 1. decreases the number of medical errors and unpredicted complications 5. 2. cuts costs and gives additional income. 3. provides individual approach to every patient 4. improves quality of medical care 5. reduces mortality 6. improves competitive position of a facility 7. attracts inflow of patients + Example of surgical hospital unit with 650 beds, which spends about 20 million RUB monthly on medical errors Additional monthly income due to the increased patient inflow.
  • 22.
    6. Key teammembers G. A. Blejyants. CEO. Cardiovascular surgeon, PhD in medicine. More than 14 years of clinical practice. Experience in the development of medical classifiers. Author of the model of medical knowledge representation. N. A. Tumanov. Executive director. Psychiatrist, PhD in medicine. More than 14 years of clinical practice. Experience in modeling of medical knowledge. Experience in the creation of algorithms that operate similar to thinking pattern of a physician. Yu. A. Isakova. Head of the project in pharmacology and pharmacy. Pharmacist, leading researcher of the Dpt. of Clinical Pharmacology, Research Clinical Center “RZD”. Member of Russian Society for Evidence Based Medicine, Russian & International Society for Pharmacoeconomics and Outcomes Research (RSPOR & ISPOR). A. V. Panosyan. IT director Software developer Experience in the creation of system managing artificial neural network. Author of the modeling system of medical knowledge. M. Guseynov. Chief programmer. Software developer. Experience in creating self-learning database. Experience in creating systems managing artificial neural network.
  • 23.
    M. G. Abgaryan.Director for external relations. PhD in engineering. Experience in implementing systems of storage, processing and visualization of medical images in Russian healthcare institutions. Experience in organizing development and production of professional graphic DICOM station A. V. Lapuk. Mentor, specialist with international experience in the field of medical research. Molecular biologist. Full member of the American Association of Cancer Research, New York Academy of Sciences. Her valuable research experience helps the team to search for alternative niches for application UMKB. Scientist at Vancouver Research Institute of HealthCare (British Columbia, Canada). R. S. Melkonyan. Director of Medical department. MD. Cardiovascular surgeon, therapist. 14 years of clinical practice. Has been studying and creating algorithms of expert system for “General practitioner” system for the last 5 years. M. A. Sarkisian. Director of the Division on scientific collaboration and interacademic relations. Professor at Yevdokimov Moscow State University of Medicine and Dentistry. 18 years of experience in clinical practice. His main task is to involve academic and scientific community (from students to senior specialists) in the process of UMKB modeling. G. N. Mdinaradze. Specialist in insurance medicine. PhD in stomatology. 16 years of clinical practice. Since 2011 he holds position of CEO of the OOO “Rosneft Zdorovye” and Deputy Head of Department of Social development of the OAO “NK Rosneft” where he developed and implemented programs of insurance and medical support for employees of the “Rosneft”. S. V. Vartanyan. Deputy director of external relations. Employed in the ZAO “Socmedica” in the Division of cooperation with centers of medical science and medical facilities to fill UMKB. Supervises commercial issues. 6. Key team members
  • 24.
    7. Stages ofproject development and investments needed and required volume of investments $1.75M $1.75M A technology for modeling of medical knowledge has been developed Partnership relations with research centers have been achieved United medical knowledge base has been created Working prototype is ready: a decision support system for drug therapy Decision support system for clinical practice Stage 2: System of risk prediction for clinical complications Algorithms of risk prediction, which will be used in the expert system… Stage 3: Expert diagnostic system „Electronic therapist” Diagnostic algorithms, which will be used in the expert system… Stage 4: Expert system of personal medical user support „Personal doctor” Development of a module for the creation of individual image of patient… 1 stage completed Final product
  • 25.
    8. Financial forecast Onthe current stage active negotiations with prospective purchasers are carried. Contracts have been signed; the first sell is expected within 4 months. 14 month after required investments, our company will become self-financed. Two years after the beginning of financing, net profit should be about $0.2 million. We predict possibility of withdrawal of an investor in the beginning of the 3rd year by selling its share to a strategic investor. As such strategic investors, we regard large companies, leaders of EHR market.
  • 26.
    Gevorg Blejyants Тел: +7(926) 991-10-41 E-mail: blejyants@socmedica.com www.socmedica.com Nikolai Tumanov Тел: +7 (916) 625-90-40 E-mail: tumanov@socmedica.com Socmedica

Editor's Notes

  • #22 Cost of medical errors Cost cutting + additional income Cost of electronic system