Healthcare building infrastructure in Canada is currently facing two problems: Aging and Deferred Maintenance, leading to an increase in unexpected failures causing interruptions in the hospital operation which in turn affects the health and safety of its occupants. Despite the efforts exerted to overcome this, solutions cannot be easily implemented as they are often faced with limited and insufficient funds. Therefore, previous researches have experimented ways targeting a reduction in the rehabilitation costs while sustaining an acceptable physical condition of hospital assets. However, there is more to a building's performance than its physical condition. Hence, this study assesses the hospital performance by including functional parameters of components rather than solely evaluating their physical condition on the basis of an integration between Neutrosophic Logic and Analytic Hierarchy Process, and accordingly improves the rehabilitation decisions by utilizing the output from the previous model as an objective for a genetic algorithm optimization model to prioritize rehabilitation activities within a limited funding allowance. The developed model was validated by applying it to a real hospital situation where the results obtained from the model were compared to the actual output attained from rehabilitation works inside the hospital facility, and the model developed in this study outperformed the current practice by an improvement of 34%. This framework is expected to aid decision-makers in efficiently allocating rehabilitation funds to the most critical hospital building systems which in turn improves the performance and availability of hospital assets.