Tremor extraction techniques are considered as the central component of several rehabilitative and compensatory robotic technologies, and the accuracy of such filters can directly affect the performance of the aforementioned technologies. Motivated by this fact, the paper proposes an adaptive estimation framework, referred to as Multiple Adaptive Reduced-order Kalman filtering (KFE-BMFLC), for extraction of pathological hand tremors. The proposed KFE-BMFLC framework is designed with the goal of improving the performance of an existing state-of-the-art filtering technique, i.e. Enhanced Band-limited Fourier Linear Combiner (E-BMFLC), which has shown a promising potential in extracting involuntary hand motions but uses embedded least mean square (LMS) estimation approach. The proposed technique is capable of reducing the computational overhead in comparison to that of the conventional BMFLC technique, while increasing the estimation accuracy.