=Paper=
{{Paper
|id=Vol-2544/shortpaper5
|storemode=property
|title=Antibids - Antibiotics Big Data System
|pdfUrl=https://ceur-ws.org/Vol-2544/shortpaper5.pdf
|volume=Vol-2544
|authors=Natalya Shakhovska
|dblpUrl=https://dblp.org/rec/conf/irehi/Shakhovska18
}}
==Antibids - Antibiotics Big Data System==
https://ceur-ws.org/Vol-2544/shortpaper5.pdf
Antibids - Antibiotics Big Data System
Natalya Shakhovska
Head of Artificial intelligence department, Lviv Polytechnic National
University, Ukraine
Abstract: Development of decision support clinical system AntiBidS (Antibiot-
ics Big Data System) that will serve to the collection, processing and analysis
Big medical data from various sources, to simplify the process of personalizing
treatment, standardization of approaches for selecting schemes of antibiotic
therapy, to collect the new trends in pharmaceutical products on the Internet.
All of them will provide expansion of the social aspect in the work of medical
staff and in the health and well-being of patients.
Keywords: Antibiotics, Big Data, System, personalizing treatment, patient,
medical data.
Introduction
Proposal outline: development of decision support clinical system AntiBidS (Anti-
biotics Big Data System) that will serve to the collection, processing and analysis
Big medical data from various sources, to simplify the process of personalizing
treatment, standardization of approaches for selecting schemes of antibiotic thera-
py, to collect the new trends in pharmaceutical products on the Internet. All of
them will provide expansion of the social aspect in the work of medical staff and in
the health and well-being of patients.
Objectives
• Simplify and improve the process of personalization antibiotic treat-
ment of patients;
• Collect information about medications from different pharmacies da-
tabases and automatically parse.
• To allow of doctor find needed medications without remembering all
trade-marks and pharmacies groups.
• Automatically medical e-prescription creation.
Incoming information:
Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons Li-
cense Attribution 4.0 International (CC BY 4.0) IREHI 2018 : 2nd IEEE International Rural
and Elderly Health Informatics Conference
2
• Information about the disease
• Patient information (medical record with diagnose)
• Instruction for medication
Data processing:
• Medical instruction parsing
• The medication (antibiotic) selection
• E-prescription creation
The technical approach
Phase 1. To collect medication instructions
3
Indication
Contraindication
allergic reaction
active substance
dosage
diseases
Graph and document-oriented database combination
4
CREATE (Ampicilin:Antibiotic {title: Ампіцилін, latin_title: Ampicilin,
release_form: ‘Tablets 500 000 IU',application_method:'Inside of 400,000 -
500,000 IU 2-3 times a day for 10-12 days'})
CREATE (Candidiasis:Disease {name: Candidiasis gastrointestinal tract'})
CREATE (SkinLesions:Disease {name: Lesion of skin'})
CREATE (MucosalLesions:Disease {name: Mucosal lesions'})
CREATE (Liver:Disease {name: Liver illness})
CREATE (Stomach:Disease {name: Acute gastrointestinal diseases'})
CREATE (Ulcer:Disease {name: Gastric ulcer and duodenal ulcer'})
CREATE (UteineBleeding:Disease {name: Uterine bleeding'})
CREATE
(Candidiasis)-[:INDICATION]->(Ampicilin),
(SkinLesions)-[:INDICATION]->(Ampicilin),
5
(MucosalLesions)-[:INDICATION]->(Ampicilin),
(Liver)-[:CONTRAINDICATION]->(Ampicilin),
(Stomach)-[:CONTRAINDICATION]->(Ampicilin),
(Ulcer)-[:CONTRAINDICATION]->(Ampicilin),
(UteineBleeding)-[:CONTRAINDICATION]->(Ampicilin)
Phase 2. Medication selection.
An example of a parallel connection of graphs for a system of work with instruc-
tions for medical products
6
Phase 3. The patient data collection system
7
The system for processing medical data and predicting the patient's condition
The result of power bands of HRV plotting
8
Conclusions
Raising awareness of physicians with new medicines allow decrease in time spent for
searching for information about them.
Improving the quality of medical treatment by personalizing treatment schemes. Ana-
lysing the efficiency of patient pathway management both at primary care level (pre-
vention and early detection) and en route encompassing
Ability to use the program not only to antibiotic therapy, but doctors can use for other
fields that will increase the quality of medical care.
Providing hospitals the proposed information system for the rational antibiotic therapy
for diseases caused by different types of surgical infection.
Analysis of treatment's results, according to which possible to determine the efficacy of
using the therapeutic schemes and prognostication of next methods of treatments.
The inclusion of large amounts of data into useful information for planning authorities
in the field of public health and implementation approach "health in all policies".
The intelligence coach increase patient’s well-being.
References
1. Shakhovska N. Antibids - Antibiotics Big Data System. IREHI 2018. http://ieee-rural-
elderly-health.com/2018/wp-content/uploads/2018/12/IREHI-Programm-1.pdf
2. Shakhovska N., Fedushko S., Greguš ml. M., Shvorob I., Syerova Yu. Development of
Mobile System for Medical Recommendations. The 15th International Conference on Mo-
bile Systems and Pervasive Computing (MobiSPC) August 19-21, 2019, Halifax, Canada.
Procedia Computer Science. Volume 155, 2019, Pages 43-
50. https://doi.org/10.1016/j.procs.2019.08.010
3. Fedushko S., Michal Gregus ml., Ustyianovych T. Medical card data imputation and pa-
tient psychological and behavioral profile construction. The 9th International Conference
on Current and Future Trends of Information and Communication Technologies in
Healthcare (ICTH 2019) November 4-7, 2019, Coimbra, PortugalProcedia Computer Sci-
ence. Volume 160, 2019, Pages 354-361. https://doi.org/10.1016/j.procs.2019.11.080