Home About us Editorial board Ahead of print Current issue Search Archives Submit article Instructions Subscribe Contacts Login 
  • Users Online: 589
  • Home
  • Print this page
  • Email this page

 Table of Contents  
Year : 2017  |  Volume : 3  |  Issue : 3  |  Page : 123-128

Republication: Application of financial analysis techniques to clinical laboratory data – A novel method of trend interpretation in the Intensive Care Unit

OPUS 12 Foundation, Bethlehem, PA, USA

Date of Web Publication21-Apr-2017

Correspondence Address:
Stanislaw P Stawicki
Department of Research and Innovation, St. Luke's University Health Network, EW2 Research Administration, 801 Ostrum Street, Bethlehem, PA 18015
Login to access the Email id

Source of Support: None, Conflict of Interest: None

DOI: 10.4103/IJAM.IJAM_22_17

Rights and Permissions

Modern critical care medicine depends on constant flow of massive amounts of information. This information has limited usefulness unless it is appropriately gathered, stored, displayed, and interpreted. Despite such wealth of data in the modern Intensive Care Units (ICUs), intensivists often rely on very fragmentary “snapshot” information to make important clinical decisions. In an attempt to improve the understanding of clinical data trends, application of financial analysis (FA) methods to clinical laboratory data samples were performed. Three randomly chosen, anonymized laboratory datasets of patients who spent at least 30 days in the ICU were retrospectively examined. Regularly obtained laboratory values were retrieved and recorded for each patient. Variables examined included white blood cell count, hemoglobin level, platelet count, and blood glucose levels. These variables were then entered into specialized FA software and subjected to computer-based processing. Trends in the recorded data were examined using (1) the stochastic oscillator, (2) the Relative Strength Index tool, (3) price envelope analysis, and (4) moving average analysis. All clinical laboratory parameter analyses demonstrated that laboratory data could be successfully “trended” using FA techniques. Not only were the laboratory data clearly readable and transparent when displayed in FA fashion but also some trends that were not apparent on “gross” inspection of the numeric data became very apparent after FA. Much like with financial patterns and vital sign data, trends noted within laboratory parameters appeared to be more significant when more than one indicator identified or “confirmed” them, utilizing the concept of a confirmatory variable. Laboratory data, much like financial and vital sign data, were subject to trend reversals. Such reversals in laboratory parameters appeared to follow patterns similar to those followed by financial vehicles and markets. This report demonstrates that laboratory data can be subjected to the same manipulations as financial market data. Furthermore, FA tools appear to provide the interpreter with means to define, confirm, and possibly predict trends and trend reversals. Assumptions for the use of FA methods in biologic parameter analysis are also presented.
The following core competencies are addressed in this article: Medical knowledge, Practice-based learning and improvement, Systems-based practice.
Republished with permission from: Stawicki SP. Application of financial analysis techniques to clinical laboratory data: A novel method of trend interpretation in the Intensive Care Unit. OPUS 12 Scientist. 2007;1:1-4.

Keywords: Financial analysis software, Intensive Care Unit, laboratory data, technical indicators, trending methods for stocks and bonds, Wall Street

How to cite this article:
Stawicki SP. Republication: Application of financial analysis techniques to clinical laboratory data – A novel method of trend interpretation in the Intensive Care Unit. Int J Acad Med 2017;3, Suppl S1:123-8

How to cite this URL:
Stawicki SP. Republication: Application of financial analysis techniques to clinical laboratory data – A novel method of trend interpretation in the Intensive Care Unit. Int J Acad Med [serial online] 2017 [cited 2022 Jun 27];3, Suppl S1:123-8. Available from: https://www.ijam-web.org/text.asp?2017/3/3/123/204953

  Introduction Top

The success of modern critical care medicine is largely dependent on contemporary research, and technological advances that bring about an increasingly greater flow of clinical information. This information includes vital signs, laboratory values, pressure measurements (arterial pressure, central venous pressure, pulmonary artery pressure, intracranial pressure, bladder pressure, etc.,), and various types of input (intravenous, enteral, etc.,) and output (urine, suction drains, etc.,) parameters. Every conceivable device in the modern ICU provides the intensivist with a certain amount of information although utilization of this information tends to be largely episodic and fragmentary.[1] It is well known that the ubiquitous clinical information requires a significant amount of interpretation before it truly becomes clinically useful.[1] The ICUs have not capitalized on the huge amount of streaming data. Unlike the financial market specialists, intensivists still rely only on cursory data and trend analyses. An examination of analytic methods previously used by the author to “trend” vital sign data was conducted on clinical laboratory variables in an attempt to find ways to improve the poor data-trend utilization in the ICU.[1]

Technical indicators have long been used in analyzing the past trends and patterns in an attempt to predict future financial market events. It is also well established that nearly all variables in biology are nonstationary stochastic.[1],[2] Numerous complicated approaches have been used in the past to describe vital sign trends.[2],[3] For example, Fourier spectral analysis has been shown to work well for strictly periodic or stationary random time functions, and a stochastic exponential dispersion model was shown to describe regional animal organ blood flows.[2],[3]

Various indicators are used to signal potential financial market trend reversals, and when used in conjunction with other information (such as company earnings, sector earnings, or stock market “sentiment”) can contribute to the overall decision-making process regarding purchase or sale of a given security. Some of the most commonly used stock market technical indicators include the Relative Strength Index (RSI) and the stochastic oscillator (SO).[4],[5]

The advantage of indicators used in this study is that their understanding requires only a rudimentary knowledge of mathematics. In addition, all of the indicators used in this report (RSI, SO, price envelope [PE], and moving average [MA]) can be used equally well in both second-to-second [Figure 1] and month-to-month data analyses, making them applicable across a broad range of clinical variables and data “resolution” ranges. Moreover, these indicators work just as well for small measurement units (fractions and decimals) as they work for large measurement units. [Figure 2]a demonstrates financial-like graphical representation of serum glucose levels. [Figure 2]b demonstrates how financial analysis [FA] indicators can be used to demonstrate trend reversals.
Figure 1: Example of stochastic oscillator and Relative Strength Index indicators used in short-term (minute-to-minute) analysis. Each vertical bar represents one calendar day

Click here to view
Figure 2: (a) Graphical representation of serum glucose levels, with the various trends indicated by financial analysis software indicators. Note the Relative Strength Index indicator in the upper field, with the stochastic oscillator indicator in the middle field, and the stock bar graph of serum glucose levels in the bottom window, along with price envelope dashed lines. (b) The graphical representation of serum glucose levels with parts of the graph highlighted according to trend interpretation. Please note the ovals indicating lower trend reversals and the boxes indicating upper trend reversals in serum glucose levels. The shaded area toward the latter part of the recording period indicates a relative lack of trending due to stabilization of glucose levels within the desired range. Such “obliteration” of the trend indicates lack of significant change either on the upside or on the downside and points to clinical “stability”

Click here to view

Much like the author's previous examination of trends in vital sign data, it was hypothesized that use of RSI, SO, MA, and PE can effectively describe trends in clinical laboratory parameters and open a possibility that these indicators could be used in conjunction with vital sign data trends and clinical findings to improve global patient care and clinical decision-making.[1] The goal of this report is to describe the use of existing and proven methods of financial data “trending” in a novel way.

Laboratory data were obtained retrospectively from three randomly selected, completely anonymized, ICU datasets. Clinical laboratory data were recorded at least twice daily over a period of weeks. Laboratory information was then transformed into the open-high-low-close format used in FA. In order for this format to be used, the data had to be arranged into 24 h epochs. For each epoch, the opening value (the first value in the epoch), the high and low values, as well as the closing value (the last value in the epoch) were ascertained over each 24 h period. Data were then entered sequentially for each epoch into MetaStock™ (Equis International, Salt Lake City, UT, USA) FA software. Following data entry, a graphical interpretation, much like a stock price graph, emerged. Data analysis included observational inspection of the stock-like charts, examining for the presence or absence of variability and/or trends.

A definitive trend was defined as one with the SO and the RSI indicator moving in tandem and one indicator “confirming” the trend demonstrated by the other. Envelopes were added at times as secondary confirmatory trending tools. In addition, two moving averages were used to see whether the “trended” variable was above or below the overall “long-term trend” indicated by the moving average. Ordinary stock market parameters of “oversold” and “overbought” were used with respect to SA and RSI. The “oversold” state represented a potential trend reversal on the low side, whereas the “overbought” state represented a potential trend reversal on the high side. A detailed description of stock trending methods was discussed by the author previously.[1]

Three “public-domain” indicators used mainly in stock and bond market analysis were utilized in this study. The first one, called RSI, developed by J. Welles Wilder, signals overbought and oversold conditions.[6] The RSI is a very useful and popular momentum oscillator. It compares the magnitude of a security's recent gains to the magnitude of its recent losses and turns that information into a number that ranges from 0 to 100. In General, numbers <20 indicate “oversold” condition and numbers over 80 indicate “overbought” condition. The formula for RSI has several parts and is derived as follows:

RSI = 100 − (100/1 + RS)

Average gain = (Total gains/n)

Average loss = (Total losses/n)

First RS = (Average gain/Average loss)

"Smoothed” RS = ([(previous average gain) × 13 + current gain]/14)/([(previous average loss) × 13 + current loss]/14)

where n = number of RSI periods.

The SO, moving average convergence divergence (MACD), PE, and MA parameters were discussed previously.[1],[7],[8],[9] All of these investment tools can be used to attempt identification of stock or bond price trend reversals. In addition, these indicators can be applied to “bundles” or “baskets” of stocks and/or bonds, wherein they help to identify the overall trend of the entire group (or index) of securities just as accurately as they do for an individual stock or bond.

As one can see, the graphs in [Figure 1] and [Figure 2] are not much different from heart rate [Figure 3]a and blood pressure [Figure 3]b charts processed with the same FA software. In fact, nearly identical reversal patterns can be seen in both types of graphs, and temporal patterns that would be difficult to detect by examining the purely numerical representation of vital sign or laboratory data emerge.
Figure 3: (a) Heart rate data shown in the format of a stock chart. The lower field shows heart rate in the open-high-low-close format grouped in 4 h intervals (each bar). Above the bar graph are, from bottom to top: Moving average convergence-divergence, stochastic oscillator indicator, and envelope indicators (uppermost). (b) Blood pressure data shown in the format of a stock chart. The lower field shows systolic blood pressure in the open-high-low-close format grouped in 4 h intervals (each bar). Above the bar graph are, from bottom to top: Moving average convergence-divergence, stochastic indicator, and envelope indicators (uppermost)

Click here to view

Good “trending” characteristics can also be seen with white blood cell count [Figure 4], platelet count [Figure 5], and hemoglobin concentration data [Figure 6]. Here, the stock-type charts very nicely demonstrate both short- and long-term trends in laboratory parameter trends and trend reversals.
Figure 4: White blood cell count data displayed using the stock chart-like open-high-low-close format. Again, note the excellent “trending” characteristics of the data as well as the normalization of white blood cell count leading to trend “obliteration”

Click here to view
Figure 5: Platelet count data displayed using the stock chart-like open-high-low-close format. Note the excellent “trending” characteristics of the data

Click here to view
Figure 6: Hemoglobin data displayed using the open-high-low-close stock chart format. Please note the “obliteration” of trend as the hemoglobin level stabilizes

Click here to view

Based on this limited application of stock trending techniques to clinical laboratory variables, it appears that these simple and easy-to-use investor tools (SO, MACD, RSI, MA, and PE) may be useful in analyzing a broad range of clinical variables. Similar analyses using vital sign data, intracranial pressure data, and bladder pressure data have been previously performed by the author, with good results.[1]

What is the usefulness and relevance of such charting trends and their interpretation? Quite frankly, the answer to this question is unclear. Certainly, application of these charts and trends to financial market data does not guarantee excellent investment results. To elucidate the full extent of any potential benefit to biologic data interpretation and/or eventual patient care, one must proceed with extreme caution, and the overall patient clinical picture has to be taken into consideration first.

While graphs and trends of individual variables (i.e., white blood cell count, heart rate, or hemoglobin) may be valuable from the standpoint of clarity of the graphical representation of these variables, the most useful clinical information will most likely come from “indices” of multiple variables, much like the stock indices. In such arrangement, multiple components of a biologic “index” would be used to create a “composite index.” Based on certain assumptions [Table 1], this “composite index” would then be used to estimate the overall patient “physiologic-economic” condition, and it could be analyzed for significant trends and trend reversals much like its individual components. In a way, we would be estimating the overall state of the “physiologic economy of the patient.” These assumptions are partially based on the Dow theory, formulated from a series of Wall Street Journal editorials authored by Charles H. Dow from 1900 to 1902.[10]
Table 1: Physiologic economy of the patient - model assumptions

Click here to view

  Conclusions Top

Indicators used in this manuscript provide a new way of describing and interpreting clinical laboratory data. When a trend was present, these indicators tended to demonstrate it quite well. When no trend was present, the indicators tended to “wonder around” until the next trend was clearly identified. Further research on this topic is necessary to determine the usefulness (if any) of this model in clinical applications. Minimizing the subjective component of patient data interpretation and maximizing the objective component may provide us with a better way of assessing patients, and when correlated with clinical data may provide useful adjunctive confirmatory or possibly even predictive value. In addition, the author proposes that multiple biologic parameters, when used in conjunction and combined into “patient physiologic indices,” could offer a glimpse into the overall “economy” of the human body.


Justifications for re-publishing this scholarly content include: (a) The phasing out of the original publication after a formal merger of OPUS 12 Scientist with the International Journal of Academic Medicine and (b) Wider dissemination of the research outcome(s) and the associated scientific knowledge.

Financial support and sponsorship


Conflicts of interest

There are no conflicts of interest.

  References Top

Stawicki SP. Application of financial analysis techniques to vital sign data: A novel method of trend interpretation in the Intensive Care Unit. OPUS 12 Sci 2007;1:14-6.  Back to cited text no. 1
Huang W, Shen Z, Huang NE, Fung YC. Engineering analysis of biological variables: An example of blood pressure over 1 day. Proc Natl Acad Sci U S A 1998;95:4816-21.  Back to cited text no. 2
Kendal WS. A stochastic model for the self-similar heterogeneity of regional organ blood flow. Proc Natl Acad Sci U S A 2001;98:837-41.  Back to cited text no. 3
Barnes RM. Trading in Choppy Markets: Breakthrough Techniques for Exploiting Nontrending Markets. Chicago, IL: Irwin Professional Pub.; 1997.  Back to cited text no. 4
Obstfeld M, Rogoff K. New Directions for Stochastic Open Economy Models. Cambridge, MA: National Bureau of Economic Research; 1999.  Back to cited text no. 5
Relative Strength Index (RSI). Available from: http://www.stockcharts.com/school/doku.php?id=chart_school:technical_indicators: relative_strength_index_rsi. [Last accessed on 2007 Oct 03].  Back to cited text no. 6
Lane GC. Lane's Stochastics. Technical Analysis of Stocks and Commodities Magazine. 1984;2:87-90.  Back to cited text no. 7
Hurst JM. The Profit Magic of Stock Transaction Timing. Greenville, SC: Traders Press Inc.; 2000.  Back to cited text no. 8
Bollinger JA. Bollinger on Bollinger Bands. New York: McGraw-Hill Trade; 2001.  Back to cited text no. 9
Dow Theory. Investopedia. Available from: http://www.investopedia.com/university/Dowtheory/default.asp. [Last accessed on 2007 Oct 08].  Back to cited text no. 10


  [Figure 1], [Figure 2], [Figure 3], [Figure 4], [Figure 5], [Figure 6]

  [Table 1]


Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
 Related articles
Access Statistics
Email Alert *
Add to My List *
* Registration required (free)

  In this article
Article Figures
Article Tables

 Article Access Statistics
    PDF Downloaded56    
    Comments [Add]    

Recommend this journal