| Title: | Transferring black-box decision making to a white-box model |
|---|
| Authors: | ID Žlahtič, Bojan (Author)
ID Završnik, Jernej (Author)
ID Blažun Vošner, Helena (Author)
ID Kokol, Peter (Author) |
|---|
| Files: |  electronics-13-01895.pdf (12,25 MB)
MD5: D497C4F8DA07EB2DD861681D62816259
 https://www.mdpi.com/2079-9292/13/10/1895
|
|---|
| Language: | English |
|---|
| Work type: | Article |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FERI - Faculty of Electrical Engineering and Computer Science
FNM - Faculty of Natural Sciences and Mathematics
|
|---|
| Abstract: | In the rapidly evolving realm of artificial intelligence (AI), black-box algorithms have exhibited outstanding performance. However, their opaque nature poses challenges in fields like medicine, where the clarity of the decision-making processes is crucial for ensuring trust. Addressing this need, the study aimed to augment these algorithms with explainable AI (XAI) features to enhance transparency. A novel approach was employed, contrasting the decision-making patterns of black-box and white-box models. Where discrepancies were noted, training data were refined to align a white-box model’s decisions closer to its black-box counterpart. Testing this methodology on three distinct medical datasets revealed consistent correlations between the adapted white-box models and their black-box analogs. Notably, integrating this strategy with established methods like local interpretable model-agnostic explanations (LIMEs) and SHapley Additive exPlanations (SHAPs) further enhanced transparency, underscoring the potential value of decision trees as a favored white-box algorithm in medicine due to its inherent explanatory capabilities. The findings highlight a promising path for the integration of the performance of black-box algorithms with the necessity for transparency in critical decision-making domains. |
|---|
| Keywords: | explainable artificial intelligence, XAI, machine learning, deep learning, white box, black box |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 05.04.2024 |
|---|
| Article acceptance date: | 10.05.2024 |
|---|
| Publication date: | 12.05.2024 |
|---|
| Publisher: | MDPI |
|---|
| Year of publishing: | 2024 |
|---|
| Number of pages: | 16 str. |
|---|
| Numbering: | Vol. 13, iss. 10, [article no.] 1895 |
|---|
| PID: | 20.500.12556/DKUM-96749  |
|---|
| UDC: | 004.5 |
|---|
| ISSN on article: | 2079-9292 |
|---|
| COBISS.SI-ID: | 195146755 |
|---|
| DOI: | 10.3390/electronics13101895 |
|---|
| Copyright: | © 2024 by the authors |
|---|
| Publication date in DKUM: | 27.01.2026 |
|---|
| Views: | 305 |
|---|
| Downloads: | 3 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
