The meaning of diagnostic test results: A spreadsheet for swift data analysis

AIMS: To design a spreadsheet program to: (a) analyse rapidly diagnostic te st result data produced in local research or reported in the literature; (b ) correct reported predictive values for disease prevalence in any populati on; (c) estimate the post-test probability of disease in individual patient s. MATERIALS AND METHODS: Microsoft Excel(TM) was used, Section A: a contingen cy (2 x 2) table was incorporated into the spreadsheet. Formulae for standa rd calculations [sample size, disease prevalence, sensitivity and specifici ty with 95% confidence intervals, predictive values and likelihood ratios ( LRs)] were linked to this table. The results change automatically when the data in the true or false negative and positive cells are changed. Section B: this estimates predictive values in any population, compensating for alt ered disease prevalence. Sections C-F: Bayes' theorem was incorporated to g enerate individual post-test probabilities. The spreadsheet generates 95% c onfidence intervals, LRs and a table and graph of conditional probabilities once the sensitivity and specificity of the test are entered. The tatter s hows the expected post-test probability of disease for any pre-test probabi lity when a test of known sensitivity and specificity is positive or negati ve, RESULTS: This spreadsheet can be used on desktop and palmtop computers. The MS Excel(TM) version can be downloaded via the Internet from the URL ftp:/ /radiography.com/pub/Rad-data99.xls CONCLUSION: A spreadsheet is useful for contingency table data analysis and assessment of the clinical meaning of diagnostic test results. (C) 2000 Th e Royal College of Radiologists.