Objective To evaluate the efficacy of complete blood count indices for the prediction of miscarriage. Materials and Methods A retrospective case-control study was conducted in a tertiary hospital. This study consisted of 389 cases (32 elective and 193 spontaneous abortions, 164 healthy pregnancies). Maternal demographic characteristics, complete blood cell (CBC) parameters, neutrophil-lymphocyte ratio (NLR), derived NLR, systemic inflammatory immune index (SII), platelet-to-lymphocyte ratio (PLR), and delta neutrophil index (DNI) that were in the routine first trimester CBC were compared between groups. Results There were no significant differences among groups in terms of demographic and obstetric characteristics. Statistically significant differences were observed for Hb, white blood cell (WBC), lymphocyte (L), NLR, SII, and PLR between the subgroups (p=0.003, p=0.045, p=0.000, p=0.002, p=0.043, p=0.010, respectively). There were no significant differences among groups in terms of the remaining parameters. When healthy pregnancies and spontaneous abortions were compared, statistically significant differences were detected for NLR, SII, PLR (p=0.001, p=0.039, and p=0.000, respectively). Moreover, when healthy pregnancies and elective abortions were compared, only NLR was found as statistically different (p=0.050). Area under curve (AUC) was calculated for PLR as 0.659 (%95 CI: 0.582-0.735) and a cut-off value of 158.1 was found with highest sensitivity and specificity (60.6 % and 61.6%, respectively) according to the results obtained from Youden's index. AUC was calculated for NLR as 0.591 (%95 CI: 0.507-0.675) and a cut-off value of 3.135 was found with highest sensitivity and specificity (56% and 54.5%) according to the results obtained from Youden's index. Conclusion In conclusion, decreased PLR and NLR levels may be used as practical and cost-effective markers for the prediction of miscarriages.