Chest X‐ray evaluation training: impact of normal and abnormal image ratio and instructional sequence

Abstract

Context Medical image perception training generally focuses on abnormalities, whereas normal images are more prevalent in medical practice. Furthermore, instructional sequences that let students practice prior to expert instruction (inductive) may lead to improved performance compared with methods that give students expert instruction before practice (deductive). This study investigates the effects of the proportion of normal images and practice–instruction order on learning to interpret medical images. It is hypothesised that manipulation of the proportion of normal images will lead to a sensitivity–specificity trade‐off and that students in practice‐first (inductive) conditons need more time per practice case but will correctly identify more test cases. Methods Third‐year medical students (n = 103) learned radiograph interpretation by practising cases with, respectively, 30% or 70% normal radiographs prior to expert instruction (practice‐first order) or after expert instruction (instruction‐first order). After training, students performed a test (60% normal) and sensitivity (% of correctly identified abnormal radiographs), specificity (% of correctly identified normal radiographs), diagnostic performance (% of correct diagnoses) and case duration were measured. Results The conditions with 30% of normal images scored higher on sensitivity but the conditions with 70% of normal images scored higher on specificity, indicating a sensitivity and specificity trade‐off. Those who participated in inductive conditions took less time per practice case but more per test case. They had similar test sensitivity, but scored lower on test specificity. Conclusions The proportion of normal images impacted the sensitivity–specificity trade‐off. This trade‐off should be an important consideration for the alignment of training with future practice. Furthermore, the deductive conditions unexpectedly scored higher on specificity when participants took less time per case. An inductive approach did not lead to higher diagnostic performance, possibly because participants might already have relevant prior knowledge. Deductive approaches are therefore advised for the training of advanced learners.

Corrigendum

“…In this paper, Table 2 was published with errors on the values under the columns ‘Main effect of proportion of normal images’, ‘Main effect of instructional sequence’, and ‘Interaction effect’. The subheading for ‘Practice‐first order (inductive)’ and ‘Instruction‐first order (deductive)’ have also been modified along with the Table caption.…”

Image interpretation: Learning analytics–informed education opportunities

“…Prior work in image interpretation has focused on the proportions of normal and abnormal radiographs and how this impacts diagnostic sensitivity and specificity trade‐offs. Specifically, higher proportions of abnormal cases optimize sensitivity but compromise specificity and vice versa 41‐43 . A high prevalence of abnormal cases can also overestimate the ability of observers to identify abnormalities and limits the opportunity to identify challenging radiographs without pathology 41 .…”

Undergraduate Radiology Education During the COVID-19 Pandemic: A Review of Teaching and Learning Strategies

“…Students studying from case libraries containing at least 30% normal radiographs performed better at radiographic interpretation. 34 The ratio of normal to pathological images did not affect learners’ diagnostic accuracy but did affect learners’ sensitivity and specificity. 34,40 Students studying from the 30% normal chest radiograph library had higher sensitivity, while students studying from the 70% normal library had higher specificity.…”

“…34,40 Students studying from the 30% normal chest radiograph library had higher sensitivity, while students studying from the 70% normal library had higher specificity. 34 Practically, this suggests that case libraries for novice learners, where sensitivity is more important, should contain less normal images than those for intermediate/advanced learners, where specificity is more important.…”

“…In a recent study, a deductive approach was found to be more effective than an inductive approach for teaching medical students to discern normal from abnormal chest radiographs. 34…”