ResumirHeterogeneous Effect of Electrochemical Impedance Spectroscopy Features on Random Forest-Based Remaining Useful Life Prediction for Lithium-Ion Batteries: A Leave-One-Battery-Out Validation Study Abstract 1. Introduction 2. Methodology 2.1 Dataset 2.2 Feature Engineering and Data Alignment 2.3 Model and Validation Scheme 2.4 Robustness and Sensitivity Analyses 3. Results 3.1 Baseline vs. EIS-Augmented Performance 3.2 Feature Importance 3.3 Robustness to Training Size and Measurement Noise 3.4 Illustrative Economic Sensitivity Analysis 4. Discussion 5. Limitations 6. Conclusion Data and Code Availability (anonymous)Heterogeneous Effect of Electrochemical Impedance Spectroscopy Features on Random Forest-Based Remaining Useful Life Prediction for Lithium-Ion Batteries: A Leave-One-Battery-Out Validation Study