Skip to main content

IBM Watson Annotator for Clinical Data


IBM Watson Annotator for Clinical Data Is Now Generally Available on May 12, 2020

 Explore healthcare insights from unstructured data with this new service on IBM Cloud.

The practice of medicine is intertwined with patient data that allows doctors and nurses to diagnose illnesses. What symptoms does a patient have, and how does a healthcare worker describe a set of symptoms for others to treat? In today’s globalized world, the treatment can even be carried out by doctors and nurses on the other side of the globe.

IBM Watson Annotator for Clinical Data—now generally available on IBM Cloud—delivers natural language processing (NLP) that is tailored for healthcare and life sciences and designed to enable organizations to utilize insights derived from unstructured text. 

The medical domain NLP service features a variety of annotators for detecting metadata (such as entities, concepts, concept values, negated spans, hypothetical spans) and a collection of annotators that detect, normalize, and code medical and social findings from unstructured clinical data. Multiple annotators can be employed to analyze unstructured data from a single request.

Get started with IBM Watson Annotator for Clinical Data.


Clinical insights provide critical context to improve usability of annotations

The volume of annotations returned by health natural language processing can be overwhelming, and only a fraction of those annotations may be relevant to the clinical question at hand. The clinical insights feature is a ready-to-use annotation capability within Watson Annotator for Clinical Data that provides critical contextual information for problems, procedures, and medications identified in the text. 

For example, this context enables the user to differentiate a patient's problem list from their family history, procedures performed therapeutically from those performed diagnostically, and medications taken from those mentioned hypothetically.

Navigational search to derive COVID-19 insights

IBM Watson Annotator for Clinical Data powers the COVID-19 Navigator—an NLP search aid to help researchers derive insights from data related to COVID-19—drawing from thousands of articles, studies, trials, and patents that may be pertinent for research. Using Watson Annotator for Clinical Data, IBM pre-enriched the corpus by drawing from the more than 10 million terms in the Unified Medical Language System (UMLS®).

Learn more about IBM Watson Annotator for Clinical Data.






Comments

Post a Comment

Popular posts from this blog

Web App Scaling with Flask Blueprint and Namespaces

A real-world Flask-RESTX-based API  may have multiple namespaces. The best practice for scaling a web application is to use a blueprint along with multiple namespace. The namespace is used to group a set of CRUD operations for a specific resource.  Blueprint can be used to combine (mixing) multiple namespaces. Here’s an example directory structure: project\ ├── app.py # Application file ├── apis #    ├── v20 # API directory    │   ├── __init__.py    │   ├── specs.py # API namespaces and REST methods    │   ├── steps.py # API namespaces and REST methods    └── v20bp.py # API blueprint file Here is an example app.py. Using a blue print allow you to mount your API on any url prefix. from flask import Flask from apis.v20bp import blueprint as api app = ...
Post a Comment
Read more

Documenting REST API with Flask-Restx

This tutorial aims to use the Flask-restx library to implement and to document the REST API. Other similar libraries in the Flask framework include the   flask_resful and  Flask-restplus libraries.  The generated document is shown below.  All the operations are group into a default namespace. All the CRUD operations get, create, and update (except for the the delete operation) are displayed  below.  References -  https://flask-restx.readthedocs.io/en/latest/ -  https://preslav.me/2018/12/02/designing-well-structured-rest-apis-with-flask-restplus-part-1/ -  https://www.freecodecamp.org/news/structuring-a-flask-restplus-web-service-for-production-builds-c2ec676de563/ -  https://github.com/cosmic-byte/flask-restplus-boilerplate
1 comment
Read more