This paper introduces a novel approach for detecting and prognosing stator inter-turn faults in induction motors, addressing an important aspect of motor health monitoring. The most commonly employed method for fault detection in this context is Motor Current Signature Analysis (MCSA). By leveraging this method, the paper focuses on the generation of periodic Magneto Motive Force (MMF) waves in the balanced current signal as a result of inter-turn faults. These MMF waves serve as crucial indicators for identifying the presence of such faults. To achieve early detection and prognostic capability for inter-turn faults, the paper proposes a numerical model that relies on analyzing the forward and backward currents. This model offers a promising approach to effectively detect and prognose these faults before they escalate into more severe issues. The obtained results from applying the proposed method demonstrate its efficiency in fault detection and prognostic accuracy for stator inter-turn faults. To validate the effectiveness of the proposed approach, an experimental setup is implemented. This setup provides a real-world context for evaluating the performance and reliability of the method in detecting and prognosing inter-turn faults. Through this validation process, the paper strengthens the credibility and applicability of the proposed technique in practical motor maintenance and fault management scenarios.