Abstract
Clinical decision-making has high-stakes outcomes for both physicians and patients, yet little research has attempted to model and automatically annotate such decision-making. The dual process model (Evans, 2008) posits two types of decision-making, which may be ordered on a continuum from intuitive to analytical (Hammond, 1981). Training clinicians to recognize decision-making style and select the most appropriate mode of reasoning for a particular context may help reduce diagnostic error (Norman, 2009). This study makes preliminary steps towards detection of decision style, based on an annotated dataset of image-based clinical reasoning in which speech data were collected from physicians as they inspected images of dermatological cases and moved towards diagnosis (Hochberg et al., 2014). A classifier was developed based on lexical, speech, disfluency, physician demographic, cognitive, and diagnostic difficulty features. Using random forests for binary classification of intuitive vs. analytical decision style in physicians’ diagnostic descriptions, the model improved on the baseline by over 30%. The introduced computational model provides construct validity for decision styles, as well as insights into the linguistic expression of decision-making. Eventually, such modeling may be incorporated into instructional systems that teach clinicians to become more effective decision makers.
Highlights
Diagnostic accuracy is critical for both physicians and patients, but there is insufficient training on clinical decision-making strategy in medical schools, towards avoiding diagnostic error (Graber et al, 2012; Croskerry & Norman, 2008). Berner and Graber (2008) estimate that diagnostic error in medicine occurs at a rate of 5-15%, and that two-thirds of diagnostic errors involve cognitive root causes.The dual process model distinguishes between intuitive and analytic modes of reasoning (Kahneman & Frederick, 2002; Evans, 1989)
These results suggest that decision style can be quantified and classified on a binary scale; the percent error reduction for both classifiers is substantial
A study of feature combinations was performed on the final test set with Random Forest (Table 5) to explore the contribution of each feature type towards automatic annotation
Summary
Diagnostic accuracy is critical for both physicians and patients, but there is insufficient training on clinical decision-making strategy in medical schools, towards avoiding diagnostic error (Graber et al, 2012; Croskerry & Norman, 2008). Berner and Graber (2008) estimate that diagnostic error in medicine occurs at a rate of 5-15%, and that two-thirds of diagnostic errors involve cognitive root causes.The dual process model distinguishes between intuitive and analytic modes of reasoning (Kahneman & Frederick, 2002; Evans, 1989). Use of the intuitive system, while efficient, may lead to cognitive errors based on heuristics and biases (Graber, 2009). Croskerry (2003) distinguished over 30 such biases and heuristics that underlie diagnostic error, including anchoring, base-rate neglect, and hindsight bias. Hammond’s (1981) Cognitive Continuum Theory proposes that decision-making lies on a continuum from intuitive to analytical reasoning. Intuitive reasoning is described as rapid, unconscious, moderately accurate, and employing simultaneous use of cues and pattern recognition (Hammond, 1981). Analytical decision-making is described as slow, conscious, task-specific, more accurate, making sequential use of cues, and applying logical rules (Hammond, 1996). Much reasoning is quasirational: between the two poles of purely intuitive and purely analytical decision-making (Hamm, 1988; Hammond, 1981)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
