Research Projects

Our involvement in international research projects guarantees our always being up to speed in IT research. Together with leading research institutions, we develop trend-setting solutions for the most varied branches. We are currently involved in the following research projects:



ASSESS CT will contribute to better semantic interoperability of eHealth services in Europe, in order to optimise care and to minimise harm in delivery of care. The ASSESS CT project, integrating a broad range of stakeholders, will investigate the fitness of the international clinical terminology SNOMED CT as a potential standard for EU-wide eHealth deployments. The ASSESS CT consortium addresses this challenge by investigating a number of issues related to the current use of SNOMED CT such as concrete reasons for adoption/non adoption of SNOMED CT, lessons learned, success factors, type and purpose of use, multilingualism, cultural differences, strengths and weaknesses. One task is to examine the fitness of SNOMED CT for natural language processing (NLP) in order to automatically structure the contents of clinical documents in order to support and enhance semantic interoperability.

For further informations: ASSESS CT



The goal of the XplOit research project is to develop models – or rather a model-based IT platform – which improves the prediction of complications in regard to patients who have received a bone marrow transplant (BMT). The models that are to be developed in XplOit will take such factors as clinical data, laboratory parameters, viral findings, the condition of the immune system and genetic information into account and calculate individual risk predictions that might also change during the course of treatment.
The XplOit collaborative project was launched in March 2016 and is scheduled to run over a period of 5 years. The project will be conducted by an internationally-experienced, multi-disciplinary team of experts from the fields of medicine, systems biology, computational linguistics, medical informatics and bioinformatics. Averbis will contribute tools for the extraction of data from clinical text documents.

For further informations: XplOit


The PH3 research project addresses the automatic classification of patents to user-specific categories. This classification should allow typical intellectual property management processes such as competitor analysis, freedom-to-operate analyses, market trend detection and landscaping analyses to be performed much faster than has hitherto been possible. Currently, these analyses require the costly, time-consuming work of experts, because they usually have to be performed manually, due to the complexity of the issues. The aim of our project is to develop software based on Big Data technologies which is able to combine semantic text analysis techniques and machine-learning based classification algorithms so intelligently that IP analyses can largely be automated. PH3 is a two-year research project in the framework of the “Zentrales Innovationsprogramm Mittelstand (ZIM)” (central innovation programme for SMEs). The project will be conducted by Averbis GmbH, in cooperation with the Abteilung für Wissensmanagement in der Bioinformatik (department for knowledge management in bioinformatics) at the Humboldt University in Berlin, under the leadership of Professor Leser.


Forschung averbis eu CASES

EU Cases – ”Linking Legal Open Data in Europe” is a research project of the European Union with the aim of developing a research platform which aids attorneys Europe-wide in finding court decisions regarding particular issues. This is particularly relevant in the area of European Case Law where national decisions often have direct ramifications in other member states. The basis of the system consists of public databases of the EU-member states in which all legislation and court decisions are readily available. With the help of computer linguistic and legal informatics methods, processes are developed that map the contents of these documents on a standardized Ontology, ultimately allowing for the recognition of the relation of documents to eachother and the identification of relevant documents for search inquiries.

For further informations:

CDI – Clinical Data Intelligence

averbis kdi

“Clinical Data Intelligence“ is a three-year research project which deals with the further processing and integration of various medical and clinical data (e.g. medical reports, x-ray results and even biochip data). These various data sources are to be compiled in one common database which is to provide an added value to existing medical information. It will be possible, for example to carry out automated searches for yet to be discovered side-effects of medications using the existing data inventory, enabling in addition, a better quantification of known correlations.
CDI is funded by the Federal Ministry of Economics and Technology (BMWi) within the scope of “Smart Data”, a contest carried out by the German federal government. Averbis provides crucial components for the analysis of various medical reports and is further developing its own technologies based on the CDI application cases from the fields of Nephrology and Gynecology.

For further informations:

Forschung averbis semcare

The two-year research project SEMCARE ”Semantic Data Platform for Healthcare” is subsidized by the European Union. The aim of the project is the development of a software platform that facilitates the diagnosis of rare diseases for clinics and aids in the selection of appropriate patients for clinical studies, the basis being the automated, contextual evaluation of existing patient data. For purposes of developing solutions for typical problems with technical medical terminology, e.g. ambiguities, abbreviations, spelling variations or typos, SEMCARE will combine current text-mining technologies with multi-lingual terminologies. Testing and optimization of the analysis software for the analysis of routine medical data in clinics will be performed in leading European health centers in Great Britain, the Netherlands and Austria.

Forschung averbis semvoice

The research project ”semanticVOICE – Semantic Language Recognition for Medicine” is one of the joint projects of the funded measure ‘KMU innovative: Information and Communication technology (ICT)” and is federally subsidized. The aim of the project is to link language recognition and text analysis methods to so-called semantic language recognition. If a computer not only recognizes the words, but understands their meaning, the most varying potential uses and extensive added-value applications arise in Medicine. semanticVOICE aims at the exhaustive compilation of physician-dictated reports and the interpretation of recorded text on the basis of digitally stored knowledge structures, resulting in derived knowledge and indications, thus significantly improving the medical documentation of patient treatment. The doctor gains a hidden aid, analyzing all aspects of his dictated texts in the background and providing him with this knowledge for better documentation and care of the patient. This project however also offers the doctor support in the administrative processes. The recognition and interpretation of the texts allow for the electronic derivation of a sort of ‘automatic pre-coding‘ or plausibility control for future coding of treatment data.

For further informations:

averbis Forschung mantra

MANTRA (Multilingual Annotation of Named Entities and Terminology Resources Acquisition) will provide multilingual terminologies and semantically annotated multilingual documents, e.g., patent texts, to improve the accessibility of scientific information. The MANTRA project capitalizes on parallel document corpora from which translational correspondences will be computed by the use of different alignment methods. Fortunately, the biomedical domain (the application scenario of MANTRA) offers a rich variety of such parallel corpora.
The project partners will exploit these multilingual document sets to harvest terms and concept representations in different languages in order to augment currently available terminological resources such as the Medical Subject Headings (MeSH).

Further information:

averbis Forschung DebugIT

The DebugIT project is part of the seventh EU research framework program. The mail aim within the project is to create IT applications which yield significant improvements in the observation and control of infectious diseases, as well as antimicrobial resistances in Europe.

This is to be realized by the establishment of a technical and semantic infrastructure which enables the linking of clinical data from different clinics in various states, rendering its distribution useful. This infrastructure analyses large amounts of clinical data with highly developed text and data mining methods for the purpose of applying the knowledge gained in clinical decisions.

Further information:

Forschung averbis THESEUS

THESEUS is a research program initiated by the Federal Ministry for Economics and Technology (Bundesministerium für Wirtschaft und Technologie, BMWi) whose aim it is to develop a new internet-based knowledge infrastructure for the purpose of better implementing and evaluating knowledge in the Internet.

Under the umbrella of THESEUS, 30 research partners from the fields of Science and Economy are developing new technologies which will facilitate access to information, link data to new knowledge and establish a foundation for the development of new services in the internet.

Within the scope of the THESEUS program, Averbis is responsible for the development of novel search and text mining technologies for improved medical-radiological diagnosis and therapies. Our cooperation partners are the Radiological Clinic at the University of Freiburg, as well as the Policlinic for Diagnostic and Interventional Radiology at the University of Leipzig.

Further information:

Forschung averbis cloud4health

With the project “cloud4health” and for the first time, a secure “Trusted-Cloud” infrastructure is being provided for eHealth applications in the Health Sector. A high level of protection of the sensitive medical data is guaranteed by the inclusion of an independent non-profit organization. This will strengthen the Health Sector’s trust in Cloud Computing, thus opening the possibility of providing data-sensitive applications in the Cloud in the future.
In a highly topical subject, the secondary use of medical raw data, cloud4health combines text analysis technologies and data warehouse approaches in concrete medical and economically relevant application scenarios. Depending on requirement, installed as a private or public cloud, cloud4Health taps into large virtual patient populations which serve the data protection-friendly evaluation of various issues from the areas of research, development and health economy and contribute to improved patient care.

Further information:

Jetzt weitere Informationen und Demo anfordern!

kostenlos & unverbindlich


Vorname (Pflichtfeld)

Name (Pflichtfeld)

Jobtitle / Rolle (Pflichtfeld)

Firma (Pflichtfeld)

E-Mail-Adresse (Pflichtfeld)



Get more Information or schedule a FREE Demo

Use case

First Name (required)

Last Name (required)

Job Title / Role (required)

Company (required)

Email (required)