Systematic literature review. A team of experts identifies the scope of review and formulates a research question. Then, MedicBK algorithms, with the help of PICO concept, perform the search in CENTRAL, MEDLINE and Embase by using keywords and Medical Subject Headings terminology. In addition, research registers (clinicaltrials.gov…) are investigated.

The resulting data set is reviewed by the expert team and the articles which were excluded are reflected in the PRISMA chart for transparency purporses.

The network meta-analysis performs both direct and indirect paired comparisons of the interventions of interest. At the same time, it is possible to select a reference intervention and a subgroup of patients. The intervention uses an incidence rate ratio (IRR) or odds ratio (OR) as an intervention effectiveness/security measure.

The criteria for including a study in a network meta-analysis are:

• randomized controlled trial (RCT) with at least 2 groups. The comparison group can be either a placebo or an active control;
  
• the ability to extract the necessary data, including endpoints and the data needed to calculate the intervention's effectiveness/safety (effect size).

Apache PDFBox, Tabula;
cTAKES , RxNorm_index, OrangeBook, UMLS, LVG;
OpenNLP

"Spring" framework is used as a server of applications. Data storage and data processing are done with "DBMS Postgresql". All basic components of the software are developed with the help of MSA. Interoperability is provided through message exchange which is done according to the protocol "AMQP" by using "RabbitMQ". The components are put into Docker containers and are managed by "Swarm".

Interface: React.js + Material-UI.
Data exchange: GraphQL.
Authentication and authorization: JSON Web Token(JWT).