Online remaining useful life (RUL) assessment is a significant asset in prognostic and health management (PHM) in many industrial domains where safety, reliability, and cost reduction are of high importance. It is not easy to predict the breakdown state of a system when it operates under multiple operating conditions, because system degradation varies with the dynamics of the operations. This paper presents an Input-Output Hidden Markov Model (IOHMM) that estimates the RUL in real time based on available measurements. The model learns the impact of the operating condition on the RUL and allows to manage the system RUL by changing the corresponding operating conditions. A reference managing algorithm is presented to match the estimated RUL to a given target RUL. In addition, well-known algorithms are adapted from HMM to IOHMM and are used for model training and health state diagnostics. A numerical application is proposed to show the importance of obtaining good predictions from a limited amount of data sequences. Specifically, since degradation is a slow process, it is difficult to have a large amount of data sequences in order to predict the RUL more accurately until the failure. Therefore, the bootstrap method with data resampling and replacement is used to train the IOHMM model to improve estimation accuracy.