Looker

Marketplace

Develop for Marketplace

Blocks

Looker Healthcare NLP API

By Looker
After converting unstructured clinical data into structured results via GCP’s Healthcare NLP API, this Looker Block creates an interactive user interface, providing simplified access to intelligent insights for healthcare providers, payers, pharma companies, and more.
After converting unstructured clinical data into structured results via GCP’s Healthcare NLP API, this Looker Block creates an interactive user interface, providing simplified access to intelligent insights for healthcare providers, payers, pharma companies, and more.

Version

v1

Release Notes

Category

Blocks

Overview

Install this block for free by importing the project(s) from the GitHub repository linked at the top of the listing.

The GCP Healthcare NLP API is part of the Cloud Healthcare API that uses natural language models to extract healthcare information from medical text using JSON requests and responses. This includes medical concepts, such as medications, procedures, medical conditions, and more. Once loaded to BigQuery, utilize this Block to rapidly unnest the results and begin to unlock insights from unstructured data sources for patient/provider insights, including patient family history, known allergies, missed coding opportunities, patient cohorting, and more.

Provides a LookML data model that unnests the NLP API results, plus includes two key dashboard views with an easily accessible, exploratory interface for hospital administrators, providers, coders, data scientists, and analysts. This is also compatible with the FHIR schema.

  • The NLP Patient View allows users to review a single selected patient of interest, surfacing their clinical notes history over time. With a unique highlighting feature, you can view the relevant patient problems/conditions, medications, and clinical history related terms from the original text. For deeper insights, we recommend that this be joined with structured data, such as EMR claims data so that developers can use this information as a new input or feature in future machine learning modeling, such as classification or regression models, either through BQML or traditional data science methods. Some examples of potential added value includes:

    • Inform clinical diagnosis with family history insights, which is not currently captured in claims

    • Capture additional procedure coding for revenue cycle purposes

  • The NLP Term View allows users to focus on chosen medical terms across the entire patient population in the dataset. They can start to view trends and patterns across groups of patients. This view also sets the stage for secondary machine learning modeling, such as K Means clustering. Some examples of potential added value includes:

    • Enhance patient matching for clinical trials

    • Identify re-purposed medications

    • Drive advancements for research in cancer and rare diseases

    • Identify how social determinants of health impact access to care

Related Content

Amazon Redshift Administration

GoogleFine-tune your Redshift deployment with a comprehensive view of performance and query analysis.Blocks

BigQuery Information Schema Performance Monitoring

GoogleMonitor and Explore your BigQuery Usage and PerformanceBlocks

© 2025 Looker Data Sciences, Inc.
Privacy | Terms | Cookies