Aims: Heart Failure (HF) is a global health challenge that is often associated with reduced left ventricular ejection fraction (EF). Current EF assessments rely on echocardiography exams performed by specialists. This study explores the feasibility of predicting EF using cardiac intervals derived from synchronous phonocardiography (PCG) and single-lead electrocardiography (ECG) recorded with a bimodal Rijuven CardioSleeve stethoscope. Methods: 84 pairs of synchronous PCG and ECG signals were collected from 42 patients. Signal pairs were categorized into three different EF groups: EF<40% (N=4), 40%≤EF<49% (N=26), EF≥50% (N=54), using echocardiography as reference. The cardiac intervals included in this study were the QT, S1S2, QS1, and QS2. Those were manually annotated in MATLAB. Logistic regression and non-parametric tests were conducted. Results: Logistic regression with both QT and QS2 demonstrates the potential of separating patients with EF below or above 40% (p=0.00112), and 50% (p=0.0197). In both models, only the QS2 interval was a significant individual predictor (p=0.0186 and p=0.0090). The Kruskal-Wallis test showed significant group differences for QS2 (p=0.008) and S1S2 (p=0.009), but not for QT (p=0.299) or QS1 (p=0.673). Mann-Whitney U-test confirmed that QS2 and S1S2 intervals differed significantly between EF <40% group and both 40%≤EF<49% and EF≥ 50% groups. No significant differences were found between 40%≤EF<49% and EF≥ 50%. Bonferroni correction did not alter the findings. Conclusions: These results highlight the potential of cardiac time intervals for EF prediction. Of particular relevance, the superior performance of QS2 indicates that combining the PCG and ECG modalities is key to obtaining better predictions, even when considering the limitations of opportunistic ECG recordings obtained with a bimodal stethoscope. These findings open the way to non-invasive, low-cost estimation of EF.