Skip to main content

Table 1 Diagnostic accuracy, Mini-CEX, and checklist score on the pre-test and post-test (n = 79)

From: Do clinical interview transcripts generated by speech recognition software improve clinical reasoning performance in mock patient encounters? A prospective observational study

 

Intervention group (n = 39)

Control group (n = 40)

Pre test Mean

Post test Mean

p-value

Pre test Mean

Post test Mean

p-value

Diagnostic accuracy, % (n)

51.3 (20/39)

89.7 (35/39)

< 0.001

57.5 (23/40)

67.5 (27/40)

0.352

Mini-CEXa

 Medical interviewing, (SD)

5.4 (0.2)

7.4 (0.1)

< 0.001

5.6 (0.2)

6.1 (0.2)

0.031

 Physical examination, (SD)

5.0 (0.2)

6.9 (0.1)

< 0.001

4.9 (0.3)

5.7 (0.2)

0.006

 Professionalism, (SD)

5.4 (0.2)

6.9 (0.1)

< 0.001

5.9 (0.2)

6.4 (0.2)

0.007

 Organization / Efficiency, (SD)

5.2 (0.2)

7.2 (0.2)

 

5.6 (0.2)

6.1 (0.2)

0.014

 Overall clinical competence, (SD)

5.2 (0.2)

7.4 (0.2)

< 0.001

5.6 (0.2)

6.1 (0.2)

0.022

Checklist scoreb

 Medical interviewing, (SD)

6.4 (0.2)

8.3 (0.2)

< 0.001

6.8 (0.2)

7.0 (0.2)

0.590

 Physical examination, (SD)

2.9 (0.2)

3.7 (0.1)

0.001

2.9 (0.2)

3.5 (0.2)

0.001

 Professionalism, (SD)

2.9 (0.2)

3.7 (0.2)

< 0.001

3.5 (0.2)

3.4 (0.2)

0.584

 Total, (SD)

12.2 (0.4)

16.1 (0.3)

< 0.001

13.1 (0.4)

13.8 (0.4)

0.107

  1. aMini-CEX: 1 − 9
  2. bChecklist: Medical interviewing: 0 − 10, Physical examination: 0 − 5, Professionalism: 0 − 5, Total: 0 − 20