Fig 1.
Five cases taken from the survey presented to each participant.
The top row shows the image that was passed through the model to generate a prediction. The second row shows the intrinsic explanation method (GradCAM) used to explain the prediction. The last row shows the extrinsic explanation method used to explain the prediction (SHAP).
Table 1.
The questions that were asked to the participants in the final feedback form.
Please note that Explanation A refers to the intrinsic explanation and Explanation B is the extrinsic explanation.
Fig 2.
Plots presenting some statistics about the participants included in the study.
(a) Number of active years in the medical field. (b) The degree(s) obtained by the participants. (c) The country that the participant comes from.
Fig 3.
The distribution of premuted kappa values across rater combinations.
Blue triangles indicate individual kappa values for each rater pair. The mean kappa value and its 95% CI are depicted by solid orange lines. The green dashed lines represent the global lower and upper bounds of the 95% CI for the Fleiss kappa. (a) Method A increased trust. (b) Method B increased trust. (c) Method A increased understanding. (d) Method B increased understanding. (e) Method A was spatially correct. (f) Method B was spatially correct. (g) Method A used appropriate colors. (h) Method B used appropriate colors. (i) Explanations are important.
Table 2.
Single and average ICC calculated for all explanation cases to measure the agreement between the answers of the participants.
Table 3.
The Fleiss kappa value measuring the reliability of agreement between the answers of the participants.
Fig 4.
A collection of violin plots that presents an overview of the responses collected from the Likert questions.
The answers are grouped by the number of years the person has been active in the medical field.
Fig 5.
The responses collected from the multiple-choice questions asked in the survey.
(a) Explanations during or after. (b) Prediction with or without explanation. (c) Most useful explanation in clinical practice.