Implementing Analytics Projects in a Hospital: Successes, Failures, and Opportunities

Abstract

Healthcare lags decades behind other industries in terms of operational analytics. Numerous technical proof-of-concept projects in the use of optimization, machine learning, and other analytical methods to solve clinical and operational problems in hospitals and other healthcare settings have been published, but relatively few have been shown to provide sustained value. For a project to provide sustained value, it must succeed in each of four successive stages: stakeholder engagement, technical performance, implementation, and sustained use. We describe recent work on a variety of analytical projects that we have carried out at Lucile Packard Children’s Hospital Stanford with a focus on key reasons why projects failed or succeeded at each stage. We discuss lessons learned, and we present principles and best practices for the design of analytical projects intended for implementation in healthcare settings.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 35 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.