Markov Model Assessment of Subjects' Clinical Skill Using the E-Pelvis Physical Simulator

Abstract

Inherent difficulties evaluating clinical competence of physicians has led to the widespread use of subjective skill assessment techniques. Inspired by an analogy between spoken language and surgical procedure, a generalized methodology using Markov models (MMs), independent of the modality under study, was developed. The methodology applied to an endoscopic experiment in "Generalized approach for modeling minimally invasive surgery as a stochastic process using a discrete Markov model" by J. Rosen et al. (IEEE Trans. Biomed. Eng., Vol. 53, No. 3, pp. 399-413, Mar. 2006) is modified and applied to data collected with the E-Pelvis physical simulator. The simulator incorporates five contact pressure sensors located in key anatomical landmarks. Two 32-state fully connected MMs are used, one for each skill level. Each state corresponds to a unique five-dimensional signature of contact pressures. Statistical distances measured between models representing subjects with different skill levels are sensitive enough to provide an objective measure of medical skill level. The method was tested with 41 expert subjects and 41 novice subjects in addition to the 30 subjects used for training the MM. Of the 82 subjects, 76 (92%) were classified correctly. Unique state transitions as well as pressure magnitudes for corresponding states were found to be skill dependent. The "white box" nature of the model provides insight into the examination process performed.