Examples of network graphs used to help identify unexpected associations and form hypotheses about the meaning of the associations.

<p><a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0005203#pone-0005203-g003" target="_blank">Figure 3A</a> shows a network graph with selected associations for the diagnosis “vulvodynia” using a threshold for edges as odds ratio of 2.5 or more and p-value of 1.0×10⁻³ or less. “Fibromyalgia” and “irritable bowel” are associated with “vulvodynia” independently from the other inter-related gynecologic diagnoses. <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0005203#pone-0005203-g003" target="_blank">Figure 3B</a> displays a network graph showing the associations between “shingles”, “hypothyroidism”, and other cancer-related diagnoses, using a threshold for edges as odds ratio of 1.75 or more and p value of 1.0×10⁻⁴ or less. Use of such a network helps to determine that the relationship between “shingles” and “hypothyroidism” may be due to cancer therapies. Node size represents the approximate number of diagnoses in the database. Node colors are designated according to the legend in <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0005203#pone-0005203-g001" target="_blank">Figure 1</a>.