Odds ratios in MLR for predictive models using CDC data as gold standard – original and ensemble models.

AIC = Akaike information criterion; considers both model fit and complexity, used to assess goodness-of-fit.°For Lyme Disease Risk, 0 = minimal/no risk, 1 = low risk/Lyme disease reported, 2 = medium risk, 3 = high risk. For Tick Presence, 0 = absent/none, 1 = reported, 2 = established.∧N = 1750: Some counties had no deciduous forest; thus, patch size and patch isolation could not be calculated.*Significant positive OR estimate: 95% CI excludes the null (1.0) and OR estimate is >1.0 (p