Figure 3 : Individual and cumulative contribution of each factor to CRC predictive accuracy.

From: Risk Model for Colorectal Cancer in Spanish Population Using Environmental and Genetic Factors: Results from the MCC-Spain study

Figure 3

The area under the ROC curve (AUROC), as indicator of predictive accuracy for each variable in the risk model, is shown. The left discontinuous (red) line indicates the individual contribution of each variable, and the right continuous (black) line indicates the cumulative contribution, bottom to top. Environmental variables are sorted by increasing AUROC. CRC: colorectal cancer; NSAID: nonsteroidal anti-inflammatory drugs; ASA: acetylsalicylic acid; BMI: body mass index.