Fig. 1

Heat map of p values for pathology Artificial Intelligence analysis data comparing parous women overall, and stratified by ≤ 5 years since birth (n = 103) and > 5 years since birth (n = 77) versus nulliparas (n = 545; referent). p values result from negative binomial or linear regression models that were adjusted for age as well as any variable that differed between parous and nulliparous women with a p value < 0.15 (race, BMI, percent fat, and relative with breast or ovarian cancer). p values < 0.0045 are considered as statistically significant after applying a Bonferroni correction for multiple testing. “ + Parous” means the given outcome measure was higher for parous compared to nulliparous women. “−Parous” means that the given outcome measure was lower for parous compared to nulliparous women