A comparison of statistical and connectionist models for the prediction of chronicity in a surgical intensive care unit

T. G. Buchman*, K. L. Kubos, A. J. Seidler, M. J. Siegforth

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

85 Scopus citations

Abstract

Objective: To compare statistical and connectionist models for the prediction of chronicity which is influenced by patient disease and external factors. Design: Retrospective development of predictive criteria and subsequent prospective testing of the same predictive criteria, using multiple logistic regression and three architecturally distinct neural networks; revision of predictive criteria. Setting: Surgical intensive care unit (ICU) equipped with a clinical information system in a ±1000-bed university hospital. Patients: Four hundred ninety-one patients with ICU length of stay 3 days who survived at least an additional 4 days. Interventions: None. Measurements and Main Results: Chronicity was defined as a length of stay >7 days. Neural networks predicted chronicity more reliably than the statistical model regardless of the former's architecture. However, the neural networks' ability to predict this chronicity degraded over time. Conclusions: Connectionist models may contribute to the prediction of clinical trajectory, including outcome and resource utilization, in surgical ICUs.

Original languageEnglish
Pages (from-to)750-762
Number of pages13
JournalCritical Care Medicine
Volume22
Issue number5
DOIs
StatePublished - 1994

Keywords

  • artificial intelligence
  • connectionist model
  • cost-effectiveness
  • critical illness
  • length of stay
  • models, statistical
  • neural network
  • outcome prediction
  • prognostication
  • severity of illness

Fingerprint

Dive into the research topics of 'A comparison of statistical and connectionist models for the prediction of chronicity in a surgical intensive care unit'. Together they form a unique fingerprint.

Cite this