Data mining in medical time series.

This article proposes a modular, computer-based methodology to describe and compare medical problems using data mining methods. The methodology focuses on a mathematical formulation of typical classification problems, systematic extraction of interpretable features from time series, and an evaluation adapted to problem-specific preferences and limitations (computational power, interpretability, etc.). The approach is applied to instrumented gait analysis and to the individual design of myoelectric controllers for hand prostheses.