Exploratory data analysis of hyperlipidemia on the Macintosh: software tools for analysis of biochemical, clinical,...

Exploratory data analysis (EDA) software facilitates unstructured, iterative open exploration of complex datasets with the aid of multiple linked graphical displays. We are investigating relationships between plasma lipoproteins and coronary artery disease by retrospective analysis of 1677 consecutive UCSF Lipid Clinic patients. Our preliminary experience is with Data Deck 3.0 although several additional software programs (JMP 2.0, Systat 5.1, Minitab 8.0, StatView 4.0) are mentioned. Lipid diagnosis (751 women and 925 men) was 22% primary hypercholesterolemia, 19% combined hyperlipidemia, 3% dysbetalipoproteinemia, 15% endogenous lipemia, 4% mixed lipemia, 5% elevated Lp(a) and 32% with no major lipid abnormality. We found the Macintosh platform (68030) to be flexible and powerful for analysis of moderate size (less than 1 Mb) clinical datasets. High resolution color monitors (1024 x 768 pixels), fast hard disks (< 18 msec) and moderate amounts of system memory (8 + Mb) facilitate exploratory analysis.