Data-driven prognostic models have been extensively utilized in current structural health monitoring (SHM) practices. They are designed to provide the health indicator (HI) - a representation of the system’s current health state - through sensor data. To enhance performance, online learning is often used to take care of uncertainties that arise from the run-to-failure process. The inverse solution, though demonstrated in online uncertainty quantification applications, remains unexplored in the context of online data-driven prognostics. Therefore, this work proposes a generic inverse solution for a deep prognostic model to online address uncertainties. The proposed method is tested using the open-access XJTU-SY bearing datasets, showcasing its capacity to online enhance the performance of a given model.