Natural Language Processing (NLP) in Healthcare
Extract meaningful information from your unstructured data
WELCOME TO HEALTH DISCOVERY
Extract meaningful information from your unstructured data
Health Discovery is a AI driven text mining platform for analyzing large amounts of patient data. It allows you to automate tedious routine tasks and gain near real-time insights into your data. With Health Discovery, diagnoses, symptoms, prescriptions, special findings and many other criteria can be extracted from medical documents and made available for further analysis and searching.
Health Discovery enables meaningful predictions regarding diagnoses and therapeutic course. Patient cohorts can be assembled with just a few mouse clicks — be it for your clinical research, to optimize feasibility studies and patient recruitment for clinical trials, or to support diagnosis, or to support medical coding specialists in medical service billing.
TriNetX is a global health research network that facilitates clinical research and enables discoveries through the generation of real-world evidence. TriNetX combines real time access to longitudinal clinical data with state-of-the-art analytics to answer complex research questions at the speed of thought. TriNetX chose Averbis as its NLP partner because of Averbis’ experience applying NLP within healthcare, the accuracy of their solution across various data domains including oncology, and the ability to work with multiple languages.
The German Cancer Prevention and Registration Act (KFRG, 2013) has led to the establishment of clinical cancer registries throughout Germany. The aim is to collect pathology data from all cancer patients who have been treated at a particular facility, within a particular healthcare network, (or ideally) in a defined catchment area. A number of state cancer registries use Health Discovery to automate data collection and to extract relevant information from pathology reports. This extracted information includes tumor type, diagnosis, morphology, topography, TNM and grading, as well as tumor-specific receptor status. The main objectives of this assessment are quality assurance and representation of the quality of results of the treatment of cancer patients as a whole.
Rhenus Office Systems GmbH offers systems services for national and international document logistics: ranging from incoming mail to digitalisation and archiving and even data destruction and making available specialist personnel. The Rhenus Group is a logistics specialist with global operations and generates annual turnover of EUR 4.8 billion. Rhenus employs 29,000 people at 610 business sites. Rhenus chose Averbis to classify large amounts of archived hospital records (up to 100 million sheets per year) and extract medical information such as diagnoses, procedures and medication.
Cerner Germany cooperates with Averbis in the field of automatic DRG (Diagnosis Related Groups) coding using NLP. Averbis Health Discovery analyzes content from all important documents - doctor's letters, OR reports, histology reports and other documents - and subsequently suggests ICD and OPS codes to the medical controller for billing purposes. Medical controllers save a lot of time in their work, hospitals can increase their revenues by several million.
More reasons for HEALTH DISCOVERY
The utilization of electronic health data has a great impact on health care research. Medical routine data can be used to conduct observational and outcomes research using longitudinal clinical data combined with advanced analytic. Much of the information needed in clinical research, such as diagnoses and symptoms, therapy courses, functional scores, etc., is often only available in free text. If this data is extracted from the texts and made available in a structured and semantically normalized form, many of these studies will only become possible because significantly more clinical parameters are available and more patients can be included in the studies.
With the introduction of Diagnoses Related Groups (DRGs), the coding and billing of medical and nursing services has changed considerably. The documentation and coding of medical and nursing services is complex and error-prone. At the same time, it is a highly repetitive and time-consuming process, since many patients with the same diagnoses are coded the same way many times per year. Health Discovery makes it possible to quickly and accurately identify missing codes and documentation gaps. It enables an automated search for diagnoses and procedures and provides corresponding evidence in the texts. You do not have to manually work through large amounts of clinical data any more and can concentrate on the essentials of your work.
Access to Electronic Health Records can be used to help refine inclusion and exclusion criteria for clinical trials, reducing the time and costs required to fully recruit the study and increasing the speed to market access. By instantly listing patient counts matching the study criteria, clinical trial protocols can be designed with direct feedback about their feasibility. Embedding NLP to mine Electronic Health Records provides a significant step toward attracting more clinical trial activity for your patient population. The benefits of NLP for Clinical Trials allow to expose important clinical data to more accurately define and identify patient cohorts, to wide your population database and to enhance your value to collaborative networks
Medical knowledge doubles every year. Doctors can no longer keep all knowledge about diseases, therapies, drugs and their interactions in mind. Artificial intelligence coupled with proliferating sources of data (datasets) pertinent to health and medicine, offer the promise of new and more powerful ways to augment human intelligence and expertise in health care. Electronic health data contains a great deal of knowledge about diseases and their treatment options on the part of physicians. This knowledge can be made available with NLP and powerful machine learning models can be trained that are able to make decisions like human experts.