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

OBJECTIVETo compare statistical and connectionist models for the prediction of chronicity which is influenced by patient disease and external factors. DESIGNRetrospective 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. SETTINGSurgical intensive care unit (ICU) equipped with a clinical information system in a 1000-bed university hospital. PATIENTSFour hundred ninety-one patients with ICU length of stay 3 days who survived at least an additional 4 days. INTERVENTIONSNone. MEASUREMENTS AND MAIN RESULTSChronicity was defined as a length of stay >7 days. Neural networks predicted chronicity more reliably than the statistical model regardless of the formerʼs architecture. However, the neural networksʼ ability to predict this chronicity degraded over time. CONCLUSIONSConnectionist models may contribute to the prediction of clinical trajectory, including outcome and resource utilization, in surgical ICUs. (Crit Care Med 1994; 22:750–762)