This study demonstrates a discrimination of endometrial cancer versus (non-cancerous) benign controls based on mid-infrared (MIR) spectroscopy of dried plasma or serum liquid samples. A detailed evaluation was performed using four discriminant methods (LDA, QDA, kNN or SVM) to execute the classification task. The discriminant methods used in the study comprised methods that are widely used in the statistics (LDA and QDA) and machine learning literature (kNN and SVM). Of particular interest, is the impact of discrimination when presented with spectral data from a section of the bio-fingerprint region (1430 cm-1 to 900 cm-1) in contrast to the more extended bio-fingerprint region used here (1800 cm-1 to 900 cm-1). Quality metrics used were the misclassification rate, sensitivity, specificity, and Matthew's correlation coefficient (MCC). For plasma (with spectral data ranging from 1430 cm-1 to 900 cm-1), the best performing classifier was kNN, which achieved a sensitivity, specificity and MCC of 0.865 ± 0.043, 0.865 ± 0.023 and 0.762 ± 0.034, respectively. For serum (in the same wavenumber range), the best performing classifier was LDA, achieving a sensitivity, specificity and MCC of 0.899 ± 0.023, 0.763 ± 0.048 and 0.664 ± 0.067, respectively. For plasma (with spectral data ranging from 1800 cm-1 to 900 cm-1), the best performing classifier was SVM, with a sensitivity, specificity and MCC of 0.993 ± 0.010, 0.815 ± 0.000 and 0.815 ± 0.010, respectively. For serum (in the same wavenumber range), QDA performed best achieving a sensitivity, specificity and MCC of 0.852 ± 0.023, 0.700 ± 0.162 and 0.557 ± 0.012, respectively. Our findings demonstrate that even when a section of the bio-fingerprint region has been removed, good classification of endometrial cancer versus non-cancerous controls is still maintained. These findings suggest the potential of a MIR screening tool for endometrial cancer screening.