Introduction: Heart failure (HF) is a cardiovascular condition diagnosed via combination of tests and clinical evaluations, including a blood test, chest X-ray, magnetic resonance, and echocardiogram as a gold standard for the assessment of ejection fraction (EF). This study explores the utility of combination of the electrocardiogram (ECG) and photoplethysmogram (PPG) for estimating systolic time intervals (STIs), with a focus on their role in classifying HF presence and subtypes. Key features include the pre-ejection period (PEP), left ventricular ejection time (LVET), and their ratio (PEP/LVET), along with age, sex, heart rate, heart rate variability, and EF. Method: The analysis uses an interim database from the ongoing SensSmart clinical study comprising 407 recordings from 82 subjects (46 HF patients, 36 healthy). HF patients were further categorized into three subtypes: preserved, mid-range, and reduced EF. PPG recordings, acquired at the brachial artery simultaneously with the ECG, were preprocessed, and each recording was represented by its median beat waveform. Fiducial points were extracted to derive STI-based features. To assess the contribution of each feature, we applied machine learning techniques: Pearson correlation, logistic regression, random forests, and permutation feature importance within a nested 10-fold cross-validation. Feature selection was performed via recursive feature elimination. Results: EF consistently ranked as the most important feature, followed by PEP, the PEP/LVET ratio, and age. Features like heart rate variability and standard deviations of STIs had negligible impact. Binary classification (healthy vs. HF) achieved an accuracy of 80.9%, while multiclass classification (HF subtype recognition) achieved 69.5%. Conclusions: These results demonstrate the potential of using STIs derived from ECG and PPG and demographic data in HF diagnostics. Importantly, both the ECG and PPG signals can be acquired via non-invasive, wearable solutions—highlighting the promise of integrating machine learning with accessible health technologies for early cardiovascular risk screening.