In pregnancy, diabetes is known to increase the risk of adverse maternal and neonatal outcomes. Moreover, it seems that children of diabetic mothers are more exposed to the risk of developing diabetes and other chronic diseases later in life. It would be beneficial to find techniques that allow early investigation of the physio-pathological mechanisms underlying adverse outcomes to provide the clinicians with tools for prevention and therapies. Cardiotocography (CTG) is a widely used test in antepartum pregnancy evaluation. Several indices can be computed from the fetal heart rate series (fHR), some of which appear to vary in diabetic pregnancies. However, the evidence is still scarce and had little impact on clinical practice. We focused our study on gestational diabetes (GDM). To investigate the changes it induced on the fHR we performed a retrospective cohort study on a CTG dataset containing more than 20000 recordings. We identified 852 recordings belonging to 301 GDM-diagnosed patients. We then divided the recordings by gestational age (G.A.) into 4 groups (weeks: 31 - 35, 36, 37, 38 to delivery) and for each we identified a control population of equal size matched by comorbidities. We analyzed 22 validated parameters from the time domain, frequency domain and non-linear analysis. Through statistical tests we assessed variations in median values on each feature. For all G.A. below the 38th week, we found a significant increase in the power in the movement frequency band (p<0.01) and an increase in the absolute value of Deceleration Reserve (p<0.01) in GDM vs control. Other significant values were also identified and are discussed in more detail in the paper. A specific protocol focused on diabetic pregnancies is still in progress. Our final goal is to use the discussed methods to track pregnancies complicated by GDM supporting the early identification of possible life-threatening events.