Skip to content

Learning Graph for Modeling Healthcare Data with Graphs

This section contains the learning graph for this intelligent textbook. A learning graph is a graph of the concepts used in this textbook. Each concept is represented by a node in a network graph. Concepts are connected by directed edges that indicate which concepts each node depends on before that concept can be understood by the student.

A learning graph is the foundational data structure for intelligent textbooks that can recommend learning paths. It is like a roadmap of concepts that helps students arrive at their learning goals.

At the left of the learning graph are the prerequisite or foundational concepts. They have no outbound edges — they only have inbound edges from other concepts that depend on understanding these foundational prerequisites. At the far right are the most advanced concepts in the course. To master these concepts you must understand all of the concepts that they point to.

Learning Graph Statistics

  • Total Concepts: 200
  • Total Dependencies: 299
  • Taxonomy Categories: 13
  • Foundational Concepts: 4
  • Average Dependencies per Concept: 1.50
  • Maximum Dependency Chain: 11 levels
  • Quality Score: 90/100 (Excellent)

Source Documents and Data Files

Course Description

We use the Course Description as the source document for the concepts that are included in this course. The course description uses the 2001 Bloom taxonomy to order its learning objectives.

List of Concepts

We use generative AI to convert the course description into a Concept List. Each concept is a short Title Case label, with most labels under 32 characters long. The 200 concepts span graph theory, healthcare domain knowledge, analytics, AI/ML, security, and practical applications.

Concept Dependency List

We next use generative AI to create a Directed Acyclic Graph (DAG). DAGs do not have cycles in which concepts depend on themselves. We provide the DAG in two formats: a CSV file and a JSON file that uses the vis-network JavaScript library format. The vis-network format uses nodes, edges, and metadata elements, with edges containing from and to properties. This makes it easy to view and edit the learning graph using an editor built with the vis-network tools.

Analysis & Documentation

Course Description Quality Assessment

This report rates the overall quality of the course description for the purpose of generating a learning graph.

  • Course description fields and content depth analysis
  • Validates that the course description has sufficient depth to generate 200 concepts
  • Compares the course description against similar courses
  • Identifies content gaps and strengths
  • Suggests areas of improvement

The course description scored 100/100, confirming readiness for learning graph generation.

View the Course Description Quality Assessment

Learning Graph Quality Validation

This report gives an overall assessment of the quality of the learning graph. It uses graph algorithms to look for specific quality patterns in the graph.

  • Graph structure validation — all concepts are connected
  • DAG validation (no cycles detected)
  • No self-dependencies detected
  • Foundational concepts: 4 entry points (Graph Theory Basics, Relational Database, Healthcare System, Artificial Intelligence)
  • Indegree distribution analysis (most depended-upon concept: Healthcare Provider)
  • Longest dependency chains (maximum chain length: 11)

The learning graph scored 90/100 (Excellent).

View the Learning Graph Quality Validation

Concept Taxonomy

In order to see patterns in the learning graph, it is useful to assign colors to each concept based on the concept type. We use generative AI to create about a dozen categories for our concepts and then place each concept into a single primary classifier.

  • A concept classifier taxonomy with 13 categories
  • Category organization — foundational elements first, capstone project ideas last
  • Balanced categories, all well under the 30% threshold
  • Clear 3-5 letter abbreviations for use in the CSV file

The 13 categories are: Foundation Concepts (FOUND), Graph Technologies (GTECH), Healthcare Domain (HCARE), Patient Data (PAT), Provider Operations (PROV), Payer & Insurance (PAYER), Financial & Business (FIN), Fraud & Compliance (FRAUD), Graph Analytics (ANAL), AI & Machine Learning (AI), Security & Privacy (SEC), Data Governance (GOV), and Capstone & Career (CAP).

View the Concept Taxonomy

Taxonomy Distribution

This report shows how many concepts fit into each category of the taxonomy. Our goal is a somewhat balanced taxonomy where each category holds an equal number of concepts. We also don't want any category to contain over 30% of our concepts.

  • Statistical breakdown
  • Detailed concept listing by category
  • Visual distribution table
  • Balance verification

The largest categories (Patient Data and Provider Operations) each hold 25 concepts (12.5%), well within the acceptable range.

View the Taxonomy Distribution Report

Key Features

Multi-Perspective Learning

The learning graph incorporates three critical healthcare perspectives:

  1. Patient Perspective: Clinical data, diagnoses, treatments, care plans
  2. Provider Perspective: Hospitals, clinics, schedules, referrals, performance
  3. Payer Perspective: Claims, policies, coverage, reimbursement

Comprehensive Coverage

Topics span from foundational concepts to advanced applications:

  • Graph database fundamentals
  • Healthcare domain knowledge
  • Query languages (Cypher, GQL, GSQL)
  • Clinical analytics and decision support
  • Fraud detection and compliance
  • AI/ML integration and LLMs
  • Security (HIPAA, RBAC)
  • Data governance and explainability

Pedagogically Sound Structure

The learning graph follows established educational principles:

  • Clear prerequisite relationships
  • Progressive complexity
  • Multiple learning pathways
  • Foundation → Application → Synthesis progression
  • Capstone projects for knowledge integration

Using the Learning Graph

For Students

  • Use the concept list to understand the full scope of the course
  • Follow dependency paths to identify prerequisite knowledge
  • Track your progress through the 200 concepts
  • Navigate personalized learning pathways based on your goals

For Instructors

  • Understand the logical structure of the course content
  • Identify critical foundational concepts
  • Design lesson plans that respect dependency relationships
  • Create assessments aligned with the concept taxonomy

For Developers

  • Import the learning-graph.json into visualization tools
  • Build adaptive learning systems using the dependency data
  • Create personalized recommendations based on concept relationships
  • Integrate with learning management systems

Technical Details

  • Format: Learning Graph JSON v1.0
  • Schema: learning-graph-schema.json
  • Creator: Dan McCreary
  • License: CC BY-NC-SA 4.0 DEED
  • Version: 1.0
  • Generated: November 6, 2025
  • Last Updated: June 5, 2026

For questions or feedback about the learning graph, please refer to the course description or contact the course creator.