Using Network Analysis to Detect Kickback Schemes Among Medical Providers
summary
Builds a physician graph with edges weighted by the Jaccard index of shared patients, then runs a greedy egonet trimming algorithm that adds alters until marginal edge weight falls. On a 6,000-node, 600,000-edge graph the method cuts edges to ~1% retention (about 6,000 edges), 93% of egonets stop after adding one alter, removes ~27% of redundant egos, runs in ~2 minutes (worst ~20), and seven of the top ten flagged subgraphs are under investigation.
AI-written summary · about
chapters (8)
- 0:00Start
- 0:39Challenge
- 2:24What are Networks?
- 4:36Analyzing the Network
- 6:13Analyzing an Egonet
- 7:47Subgraph Strength Formula
- 9:29Example
- 10:59Algorithm Results
related talks
42mGraph Theory Takes on the Opioid Epidemic
17mEnhancing Benefit Adjudication Through Graph Node Embedding, Clustering, and Outlier Detection
32mGraph-based ML for Automated Health Care Services
01h 41mGraph Intelligence: Enhance Reasoning and Retrieval Using Graph Analytics
31mSimple Models and Exact Algorithms for Computing Network Modules
33mNetwork Data Integration Enables Precision Medicine
52mNew Algorithms For The Graph Alignment Problem
01h 06mComplex networks sparsification: methods and tools