Introduction: Early detection of cardiac arrest and return of spontaneous circulation in out-of-hospital settings remains challenging due to the lack of reliable, low-cost, and non-invasive monitoring tools. Cardiac output (CO) is a direct indicator of perfusion, however, its measurement typically relies on invasive and expensive techniques unsuitable for prehospital emergency scenarios. Ballistocardiography (BCG) might be a suitable non-invasive and low-cost alternative since it measures cardiac contractility and tracks CO changes. Therefore, the aim of this study was to evaluate the feasibility of estimating CO from non-invasive BCG signals acquired using piezoelectric sensors. Materials and methods: The study dataset comprised 125 segments extracted from 20 healthy subjects under test conditions simulating an emergency medicine scenario at the Oslo University Hospital. Each segment included the electrocardiogram (ECG), BCG recordings from the carotid artery and abdominal aorta, and invasive arterial pressure-derived CO. The BCG signals were processed using adaptive filtering (recursive least squares) and the stationary wavelet transform (Coiflet-3) to isolate the circulatory component. Morphological and statistical features were extracted from these components and fed into a support vector regression (SVR) model for CO estimation. A quasi-stratified and patient-wise nested cross-validation procedure was used to select the best feature subset and to optimize the SVR hyperparameters. The procedure was repeated 50 times to estimate the statistical distribution of the mean absolute error (MAE) of the model. Results: The optimal solution consisted of a 14-feature regressor that yielded a mean (standard deviation, SD) MAE of 0.96 (0.04) L/min, corresponding to a mean (SD) relative error of 14 (0.6)%. Conclusion: These results support the potential of BCG-based systems for non-invasive CO estimation in out-of-hospital emergency care. The proposed approach represents a promising step toward an automated, non-invasive, and reliable CO estimator suitable for evaluation in prehospital settings.