Application of financial analysis techniques to vital sign data: A novel method of trend interpretation in the intensive care unit.
S. Peter Stawicki
Abstract
Modern critical care medicine is based on flow of information. This information requires significant amount of interpretation to become clinically valuable. Despite the wealth of data in the modern intensive care units, intensivists often rely on fragmentary information. In an attempt to improve data trending utilization, application of financial analysis (FA) methods to vital sign data samples was examined. Two randomly chosen vital sign datasets of patients who spent at least 30 days in the ICU were retrospectively reviewed. Hourly vital sign data was retrieved and recorded for each patient. Variables tracked included systolic blood pressure for patient 1 and heart rate for patient 2. These variables were then entered into specialized FA software and subjected to computer-based processing. Trends in the recorded data were examined using the Stochastic Oscillator, the Moving Average Convergence-Divergence tool, Price Envelope analysis and Moving Average analysis. Both blood pressure and heart rate analyses demonstrated that vital sign data could be successfully trended using financial analysis techniques. Not only was the vital sign data easy to read and interpret when formatted in financial-like fashion, but some trends that were not apparent on gross inspection of the numeric data were clearly demonstrated upon FA. Much like with financial patterns, trends noted within vital sign data appeared to be more significant when more than one indicator identified them, utilizing the concept of a confirmatory variable. Vital sign data, much like financial data, were subject to trend reversals. Such reversals in vital sign data appeared to follow rules similar to those followed by financial vehicles and markets. This report demonstrates that vital sign data can be subjected to the same manipulations as financial market data. Furthermore, financial analysis tools appear to provide the interpreter of the data with means to define, confirm, and possibly predict trends and trend reversals.
Copyright 2007 OPUS 12 Foundation, Inc.
Copyright 2007 OPUS 12 Foundation, Inc.
Full Text: PDF