20.500.12556/DKUM-96749 Transferring black-box decision making to a white-box model 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. explainable artificial intelligence XAI machine learning deep learning white box black box umetna inteligenca globoko učenje strojno učenje true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/journal/electronics © 2024 by the authors Članek v reviji 2026-01-27 12:30:30 2026-01-27 12:30:31 2026-01-28 03:13:08 0000-00-00 00:00:00 2024 0 0 16 str. iss. 10, [article no.] 1895 Vol. 13 2024 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2024-04-05 2024-05-10 2024-05-12 004.5 195146755 10.3390/electronics13101895 2079-9292 electronics-13-01895.pdf electronics-13-01895.pdf 1 D497C4F8DA07EB2DD861681D62816259 352296bf2ffc4def61374fa8ebd5219ca9b58c770a234b9f9456760440477103 ef7cf7fb-fb73-11f0-9c79-00155d00018d https://dk.um.si/Dokument.php?lang=slv&id=202617 https://www.mdpi.com/2079-9292/13/10/1895 1 9a6a42a8-fb73-11f0-9c79-00155d00018d https://dk.um.si/Dokument.php?lang=slv&id=202616 Fakulteta za elektrotehniko, računalništvo in informatiko Fakulteta za naravoslovje in matematiko 0 0 0