Тhe Self-Service Semantic Suite (S4) provides text analytics services for news, life science and healthcare articles, as well as social media messages. They analyze textual content, find concepts such as people, organizations, and locations, or diseases, interactions, genes and sequences, and link them to entities from popular Linked Open datasets.
A good example of a text analytic service within the healthcare/pharmaceutical domain is the Semantic Biomedical Tagger (SBT) – an information extraction tool, designed to create semantic annotation in biomedical texts and link them to the Linked Life Data (LLD) dataset.
Today we proudly introduce a brand-new, powerful S4 text analytics service for biomedical content extraction – the Healthcare Tagger. It obtains biomedical knowledge from clinical notes, discharge summaries, epicrises, medical case histories, medical prescriptions and a variety of other types of medical records. S4’s Healthcare Tagger service provides a quick and easy text analysis of medical documents, which can further enhance your semantic analysis.
In comparison to the Semantic Biomedical Tagger, the Healthcare Tagger is more focused on recognizing named entities related to drug components (including brand and generic names; quantity and measurement units; frequency and period of intake; administration route; and population group), diseases, medical conditions, and extracting relationships such as drug dosing, adverse events reports, side effects, etc.
While the Semantic Biomedical Tagger is useful for identifying a wide variety of entity types and linking them specifically to LLD, the new service improves on entity disambiguation and high recall by semantically enriching your text with additional knowledge systems. In addition to the conventional exact matching of names, relaxed matching mechanism is used. It allows the discovery of entities with non-adjacent words that are typical for the normal speech.
The extracted information is then mapped to standard public terminology systems:
All you need to do is follow these simple steps:
Here’s a quick practical example using S4’s demo UI. We will use the following paragraph as an example to be annotated:
All x-rays including left foot, right knee, left shoulder and cervical spine showed no acute fractures. The left shoulder did show old healed left humeral head and neck fracture with baseline anterior dislocation. CT of the brain showed no acute changes, left periorbital soft tissue swelling. CT of the maxillofacial area showed no facial bone fracture. Echocardiogram showed normal left ventricular function, ejection fraction estimated greater than 65%.
Open the S4 website, click “Try now”, paste the example text, select the Healthcare Tagger and click “Execute”.
You can start using it on your own by registering for an S4 developer account. A registration gives you a 250mb free text analysis per month.
More samples and demos can be found in the documentation.
For latest news about our service subscribe to S4’s twitter account.