Scholars Central

Conference abstractPublished 12 Sep 2011

Color-coded Z scores for the display and analysis of biomedical data

Authors: Robert A. Warner

Ask about this article

Abstract

Select any words in the title or abstract, or press this and choose a sentence.

The ability to review and analyze large amounts of data reliably, rapidly and cost-eff ectively is important in research, industrial applications and clinical care. We hypothesized that converting raw digital data to standard scores (Z scores) and color-coding them based on their corresponding P values can be used to accomplish this. For each member of a population of data, the calculation of Z scores uses the formula: Z Score = (Individual Data Point ? Population Mean)/Population Standard Deviation We illustrate the use of the technique with continuously recorded data by showing the simultaneous changes that occur in fi ve relevant parameters during acute myocardial infarction (MI). In addition, using digital electrocardiographic (ECG) data obtained from 1138 subjects, we used color-coded Z scores to develop criteria for prior inferior and anterior MI that gave diagnostic performances that were statistically signifi cantly superior to those of two widely used commercial ECG diagnostic algorithms. Since each Z score is associated with a P value, color- coded Z scores indicate if an individual data point diff ers statistically signifi cantly from the mean of a relevant population of data. Also, since the method expresses all parameters on the same scale (the standard deviation), it facilitates the meaningful simultaneous monitoring of multiple parameters. Our fi ndings show that color-coded Z scores provide a highly intuitive, accurate, statistically meaningful and widely applicable method of interpreting data that is generated either by continuous recording or by individual tests

Ask about this article

Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.

Try:

Follow

New articles from what you follow go into your email digest, once you agree to alert emails.

  • JournalJournal of Molecular Biomarkers & Diagnosis
  • SubjectGenetics & Molecular Biology
  • SubjectPathology & Lab Medicine
  • BylineArticles whose byline prints “Robert A. Warner”