Empowering Your Medical Content with the New Healthcare Tagger on the Self-Service Semantic Suite (S4)

Text Analytics with the Self-service Semantic Suite (S4)

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.

Biomedical Knowledge Even More Accessible with S4’s New Healthcare Tagger

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:

  • RxNorm – dataset for clinical drugs, distributed by the U.S. National Library of Medicine
  • SNOMED CT – health terminology product, developed and distributed by the International Health Terminology Standards Development Organisation (IHTSDO)
  • Unified Medical Language System (UMLS) – distributed by U.S. National Library of Medicine

Using S4 Healthcare Tagger is Easy

All you need to do is follow these simple steps:

  1. Submit the document.
  2. Select the Healthcare Tagger service.
  3. S4 service annotates the document in seconds.
  4. S4 send back the annotated text.

S4 Healthcare Tagger Workflow

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”.

S4 Healthcare Tagger AnnotationWhat’s Next?

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.

Yavor Petkov

Yavor Petkov

Senior Software Developer at Ontotext
Since joining Ontotext three years ago, Yavor has piled up compelling amount of technical experience by his direct involvement in the development of the Self-Service Semantic Suite Platfrom (S4) as well as the DataGraft, proDataMarket and KConnect projects. He is deservingly on his way of becoming a senior software developer. His interest in semantics in addition to his academic pursuit in AI render him an invaluable source of knowledge and expertise.
Yavor Petkov

Related Posts

Back to top