Figures & data
Table 1 Sample attrition table
Table 2 Demographic characteristics of the evaluated cohorts
Figure 1 The ten most important variables for predicting a diagnosis of fibromyalgia identified from random forest models.
Abbreviation: ER, emergency room.
![Figure 1 The ten most important variables for predicting a diagnosis of fibromyalgia identified from random forest models.](/cms/asset/9b785694-d79a-43ac-ab94-4330ebd16df1/djpr_a_8256_f0001_c.jpg)
Figure 2 Receiver operating characteristic curve modeled using the test dataset.
![Figure 2 Receiver operating characteristic curve modeled using the test dataset.](/cms/asset/577f5577-dc97-4c8c-9654-fbc196ce81c0/djpr_a_8256_f0002_c.jpg)
Figure 3 Cumulative distribution functions for the variables identified in the random forest model.
![Figure 3 Cumulative distribution functions for the variables identified in the random forest model.](/cms/asset/12ca8129-634f-4dc4-9023-31fb9418e212/djpr_a_8256_f0003_b.jpg)
Table 3 Rules for identifying FM and no-FM subjects based on results of the predictive modeling using a technique known as C5.0 rules
Table S1 Variables put into random forest model