According to dual process models of reasoning, reasoning styles can be characterized as tending towards intuitive and analytical. This framework has been applied to clinical decision-making, where There are two methods of clinical decision-making: the intuitive process that relies on exemplar-based pattern recognition, which is typically shorter; and the analytic process that steps through all available information, which is typically longer. The intuitive process is less reliable because it relies on heuristics and pattern-matching, and is therefore more subjective; whereas the analytic process takes longer but is more objective.
Being able to automatically determine whether a physician is using the intuitive or analytical style of reasoning could be useful to indicate where a physician might be going down a path of reasoning that will not lead them to the correct diagnosis; this could also be used to predict a physician's confidence in the final diagnosis.
Current work in progress examines the linguistic markers of intuitive v. analytical styles of in speech data during image-based reasoning. Other common narrative structures (in terms of order of information considered) are also being examined.
Womack K*., McCoy W*., Ovesdotter Alm C., Calvelli C., Pelz J., Shi P., Haake A. Disfluencies as extra-propositional indicators of cognitive processing (pp. 1-9). Proceedings of Workshop on Extra-propositional aspect of meaning in computational linguistics; 50th Ann. Meeting of the Assoc. for Computational Linguistics 2012, Korea.
Hochberg, L., Alm, C.O., Rantanen, E.M., Yu, Q., DeLong, C.M., & Haake, A. (2014). Towards automatic annotation of clinical decision-making style. In Proceedings of the 8th Linguistic Annotation Workshop at the 25th International Conference on Computational Linguistics (pp. 129-138). Dublin, Ireland: International Committee on Computational Linguistics.