This study describes a machine learning algorithm based on multimodal signals obtained from a regular clinical patient monitor to predict late-onset sepsis (LOS) in preterm infants in a neonatal intensive care unit (NICU). The algorithm uses features that contain information on heart rate variability (HRV), respiration, and motion, based on continuously measured physiological waveforms including electrocardiogram (ECG) and chest impedance (CI). In this study, 127 preterm infants were included, of whom 59 were blood-culture-proven LOS patients and 68 were control  patients. Features in 24 hours before the onset of sepsis (for the LOS group), and an age-matched onset time point (for the control group) were extracted and fed into machine learning classifiers together with gestational age (GA) and birth weight. We compared the prediction performance of several well-known classifiers using features extracted from different signal modalities (HRV, respiration, and motion) individually as well as their combinations. The prediction performance was evaluated using the area under the receiver-operating-characteristics curve (AUC). The best performance for LOS prediction was achieved by an extreme gradient boosting classifier combining features from all signal modalities, with an AUC of 0.88, a positive predictive value of 0.80, and a negative predictive value of 0.83 during 6 hours preceding LOS onset. Our study demonstrates the complementary predictive value of motion information in addition to cardiorespiratory information for LOS prediction. Furthermore, visualizations of how each feature impacts the algorithm strengthen its clinical decision support to predict LOS for individual patients in NICUs.