Wolfram Computation Meets Knowledge

Clinical Concepts from Massive Sources of Medical Data

A dataset of medical concepts

Medical data is multimodal and comes in many forms, including free text (in medical publications and clinical notes) and billing codes for diagnoses and procedures in electronic health care records. These clinical concepts were obtained from insurance claims for 60 million Americans, 1.7 million full-text PubMed articles and clinical notes from 20 million patients at Stanford hospitals and clinics. These concepts were mapped into a common concept unique identifier (CUI) space using a thesaurus from the Unified Medical Language System.

The "ContentElements" field contains two options: "Data", structured as an association, and "Dataset", structured as a dataset.

Examples

Basic Examples

Retrieve the resource:

In[1]:=
ResourceObject["Clinical Concepts from Massive Sources of Medical \
Data"]
Out[1]=

View the data:

In[2]:=
ResourceData["Clinical Concepts from Massive Sources of Medical Data"]
Out[2]=

Analysis

Visualize the source of the data:

In[3]:=
BarChart[Sort[
  CountsBy[ResourceData[
    "Clinical Concepts from Massive Sources of Medical Data"], 
   "Source"]], ChartLabels -> Automatic, BarSpacing -> Large, 
 ColorFunction -> ColorData["BlueGreenYellow"]]
Out[3]=

Wolfram Research, "Clinical Concepts from Massive Sources of Medical Data" from the Wolfram Data Repository (2018) 

Data Resource History

Source Metadata

Publisher Information