Health Discovery at a glance
Health Discovery is the text mining and machine learning platform for analyzing large amounts of patient data.
With Health Discovery, medical documents can be analyzed and searched for diagnoses, symptoms, prescriptions, special findings and other criteria. Heterogeneous patient data in a structured and unstructured form are harmonized, the content analyzed using text mining and natural language processing and made searchable using a uniform interface.
Health Discovery enables meaningful predictions about diagnoses and therapy courses. Supported by natural language processing, patient cohorts can be compiled with just a few clicks of the mouse – be it for feasibility studies and patient recruitment for clinical studies, for diagnostic support for rare diseases or to support medical coding specialists in medical billing.
Medical errors are among the most common causes of death in Western countries. One of the reasons is the lack of relevant information at the right time. In the meantime, medical knowledge doubles every 100 days. Doctors can no longer keep all knowledge about diseases, therapies, drugs and their interactions in mind. The use of information technology is therefore indispensable in hospitals and medical practices. However, existing information systems are often isolated and health data cannot be systematically evaluated. A solution is provided by the use of artificial intelligence in combination with NLP (Natural Language Processing): large amounts of health-related information from different sources and formats can be linked and analyzed. This knowledge can be made available wherever medical decisions have to be made.
Customer Success Story:
Averbis is used by all four consortia of the Medical Informatics Initiative for the analysis of unstructured data. The medical informatics initiative creates the conditions for research and care to move closer together. All university hospitals in Germany are currently working together with research institutions, companies, health insurance companies and patient representatives to develop the framework conditions so that research findings can directly reach patients. The Federal Ministry of Education and Research will initially invest around 160 million euros in the funding program until 2021.
The medical informatics initiative aims to make the best possible use of the opportunities offered by digitization in medicine for healthcare and research. In a first step, data integration centers will be set up and networked at university hospitals and partner institutions. In these centers, the prerequisites are created to be able to link research and supply data across locations. At the same time, innovative IT solutions are being developed for specific medical applications that are intended to show the possibilities of modern digital services and infrastructures in the health sector.
And it will improve patient care and help combat diseases more effectively. Specifically, the initiative is about harnessing the flood of data generated every single day in healthcare and research environments – to the benefit of individual patients, to better understand illnesses, and to tailor treatments to the needs of the individual. The goal is to establish a way to exchange research and care data across university hospitals. If it proves successful – with the help of funding from BMBF – it will open up entirely new horizons. The solutions that will be developed are expected to create added value across the health system.
© BMBF / Hans-Joachim Rickel
With the introduction of Diagnoses Related Groups (DRGs), the coding and billing of medical and nursing services has changed significantly. The documentation and coding of medical and nursing services is complex and prone to errors. At the same time, this is a very repetitive and time-consuming process since many patients with the same diagnoses are coded in the same way several times a year.
With Health Discovery, missing codes and documentation gaps can be identified quickly and accurately. It enables an automated search for diagnoses and procedures and provides corresponding documents in the texts. You no longer have to manually process large amounts of clinical data and can concentrate on the essentials of your work.
Customer Success Story:
Averbis collaborates with Compugroup and Meta IT in coding support in hospitals – for revenue security and MDK security.
The jointly developed software MetaText is programmed profit! Averbis Health Discovery analyzes medical documents such as doctor’s letters, pathology reports, surgery reports etc. and extracts revenue-relevant information. In doing so, the most modern methods from the field of Artificial Intelligence are combined with detailed rules and regulations in order to deliver the best possible results. In this way, we support coding specialists and medical controllers in finding out from the plethora of specifications the coding that represents the correct revenue for the services provided.
Averbis Health Discovery is fully integrated into the MetaText coding software, a solution that serves to optimally and correctly map services rendered in the DRG system, to harmonize the length of stay with the determined DRGs and to support the creation of MDK-compliant documentation by warning of possible scope for interpretation during coding. Customers’ experiences show that MetaText can significantly improve coding quality and therefore results.
Clinical studies are the key to medical progress. The use of NLP to determine patient populations is an important step towards obtaining more precise case numbers and more complete medical information about patients. Health Discovery enables the identification of larger patient cohorts, the refinement of inclusion and exclusion criteria, reduces the time and cost of recruitment, and thus increases the value of clinical trials many times over.
Customer Success Story:
Through its global network of 150 clinics, our partner TriNetX provides current medical data at patient level. This enables supportive, curative and preventive therapies to be developed for the disease. The TriNetX NLP service powered by Averbis utilizes sophisticated algorithms to extract clinical facts from physician notes, clinical and pathology reports, links them with other Electronic Medical Record (EMR) data, and makes the combined data available for assessing study feasibility, protocol design, site selection, and subsequent identification of patients for clinical trials.
The TriNetX NLP service powered by Averbis mines unstructured data, such as measurements and observation on ECOG performance status for oncology, NYHA classification, Ejection Fraction, and Corrected QT Interval for cardiac studies. NLP also collects information from clinician notes for patients whose hospital medical records may be incomplete due to visits to multiple healthcare facilities. Extracted data is subsequently mapped to standardized clinical terminologies that can be easily analyzed by researchers using the TNX platform.
TriNetX chose Averbis as NLP partner for the following reasons:
Medical errors are among the most common causes of death in Western countries. One of the reasons is the lack of relevant information at the right time. At the meantime, medical knowledge doubles every 100 days. Doctors can no longer keep all knowledge about diseases, therapies, drugs and their interactions in mind. The use of information technology is therefore indispensable in hospitals and medical practices. However, existing information systems are often isolated and health data cannot be systematically evaluated. A solution is provided by the use of artificial intelligence in combination with NLP (Natural Language Processing): large amounts of health-related information from different sources and formats can be linked and analyzed. This knowledge can be made available wherever medical decisions have to be made.
Customer Success Story:
Averbis Health Discovery was successfully applied to help diagnosing rare neurologic diseases. Diagnosis of rare neurogenetic disorders is often challenging, particularly adult-onset presentations, with long diagnostic delays and misdiagnosis. As therapies become available, it is increasingly important to identify patients with rare neurologic diseases.
This multicenter project on ten rare neurogenetic diseases was run at six German University medical centers. Averbis Health Discovery structured medical data by ranking documents according to probability of disease, based on disease-specific lists of weighted signs and symptoms. Existing electronic medical records from the Department of Neurology of each center, corresponding to 10 years of activity, were screened, and patients ranked by probability of having the respective disease.
An experienced team of physicians reviewed the data for the top ranked patients and those without a confirmed diagnosis were contacted for testing for the respective disease.
In the pilot phase, 4 patients with Pompe disease and 4 heterozygous NPC1 mutation carriers were identified in Munich. More than 400.000 datasets from four centers were analysed for three diseases:
Niemann-Pick type C disease, Pompe disease and Fabry disease. Four novel Pompe patients and 3 heterozygous NPC1 or NPC2 mutation carriers were identified, who had not previously been diagnosed.
What our customers say
Averbis Health Discovery is a valuable contribution to data protection-compliant, networked medical research.
Health Discovery is an effective tool to prepare textual information for research quickly and in accordance with data protection regulations.
In this video, we show you how you can configure Health Discovery as a text mining and machine learning platform and analyze large amounts of medical documents and patient data according to diagnoses, symptoms, prescriptions, special findings and other criteria in just a few minutes.