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., 2014a). A classifier was developed based on lexical, speech, disfluency, physician demographic, cognitive, and diagnostic difficulty features to categorize diagnostic narratives as intuitive vs. analytical; the model improved on the baseline by over 30%. The introduced computational model provides construct validity for the dual process theory. Eventually, such modeling may be incorporated into instructional systems that teach clinicians to become more effective decision makers.

In addition, metacognition, or self-assessment and

self-management of cognitive processes, has been shown beneficial to decision-making (Batha & Carroll, 2007; Ewell-Kumar, 1999). This study measured physicians' metacognitive awareness, an online component of metacognition, based on the confidence-accuracy relationship, and also exploited the corpus annotation of decision style to derive decision metrics. These metrics were used to examine the relationships between decision style, metacognitive awareness, expertise, case difficulty, and diagnostic accuracy. Based on statistical analyses, intuitive reasoning was associated with greater diagnostic accuracy, with an advantage for expert physicians. Case difficulty was associated with greater user of analytical decision-making, while metacognitive awareness was linked to decreased diagnostic accuracy. These results offer a springboard for further research on the interactions between decision style, metacognitive awareness, physician and case characteristics, and diagnostic accuracy.

Library of Congress Subject Headings

Metacognition; Decision making; Physicians--Psychology

Publication Date

9-3-2014

Document Type

Thesis

Student Type

Graduate

Department, Program, or Center

Psychology (CLA)

Advisor

Esa Rantanen

Advisor/Committee Member

Cecilia O. Alm

Advisor/Committee Member

Anne Haake

Comments

Physical copy available from RIT's Wallace Library at BF311 .H63 2014

Campus

RIT – Main Campus

Plan Codes

EXPSYC-MS

Download

Share

COinS