Clustering Theory and Data-Driven Health Care Strategies

Abstract

DoD health care requires reform with growing costs causing concerns of decreased military capability. One proposed radical strategy to fix current health care delivery systems is to organize medical teams around patients with similar treatment requirements. This is a clustering problem; how do you partition the set of patients so that each group has similar treatment needs? We provide advances in clustering theory relevant to this new health care strategy. In particular, we create fast certifiably optimal k-means clustering using what is known as Probably Certifiably Correct (PCC) algorithms which achieves state-of-the-art performance under certain models. Inspired by the health care clustering problem, we pay particular attention to a Bipartite Stochastic Block Model and produce an alternative PCC algorithm specific to this model. We conclude by demonstrating the potential utility of applying these clustering methods in health care. Using conditional entropy as a metric, clusters obtained from our methods vastly outperform partitions prescribed by subject matter experts.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 24, 2016
Accession Number
AD1053610

Entities

People

  • Takayuki Iguchi

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Air Force Personnel
  • Algorithms
  • Computational Science
  • Data Science
  • Department Of Defense
  • Disease Attributes
  • Governments
  • Health Care
  • Health Services
  • Hospitals
  • Information Science
  • Machine Learning
  • Medical Personnel
  • Probability Distributions
  • Random Variables
  • United States Government

Fields of Study

  • Computer science
  • Medicine

Readers

  • Computer Vision.
  • Rehabilitation and Prosthetic Care for Military Service Members and Veterans with Limb Loss or Disability.
  • STEM Education