Agile Machine Learning Model Development Using Data Canyons in Medicine - A Step toward Explainable Artificial Intelligence and Flexible Expert-Based Model Improvement

Aug 2, 2026

Machine learning has become a key asset in medicine as medical data grows, yet many widely used methods remain black-box systems with limited transparency and visualization. This opacity prevents medical experts from effectively trusting and applying model outputs in high-stakes decisions. The work addresses this gap by advancing explainable artificial intelligence (XAI) and enabling transparent white-box learning. A Data Canyons white-box algorithm is integrated with a web framework so clinicians transfer expertise into an agile development process, can flexibly adjust outputs, and validate results visually even without machine-learning expertise, strengthening collaboration between domains.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Explainable AI and the need for transparency in medicine

Black-box limitations and white-box advantages

Data Canyons as a foundation for a flexible model improvement approach

applied sciences Article Agile Machine Learning Model Development Using Data Canyons in Medicine: A Step towards Explainable Artiﬁcial Intelligence and Flexible Expert-Based Model Improvement Bojan Žlahtiˇc 1, *, Jernej Završnik 2,3,4,5, Helena Blažun Vošner 2,3,6, Peter Kokol 1, David Šuran 7 and Tadej Završnik 7 Citation: Žlahtiˇc, B.; Završnik, J.; Blažun Vošner, H.; Kokol, P.; Šuran, D.; Završnik, T. Agile Machine Learning Model Development Using Data Canyons in Medicine: A Step towards Explainable Artiﬁcial Intelligence and Flexible ExpertBased Model Improvement. Appl. Sci. 2023, 13, 8329. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.3390/app13148329](10.3390/app13148329) Academic Editor: Jan Egger Received: 3 July 2023 Revised: 13 July 2023 Accepted: 17 July 2023 Published: 19 July 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Faculty of Electrical Engineering and Computer Science, University of Maribor, 2000 Maribor, Slovenia 2 Community Healthcare Center Dr. Adolf Drolc Maribor, 2000 Maribor, Slovenia 3 Alma Mater Europaea—ECM, 2000 Maribor, Slovenia 4 Science and Research Center Koper, 6000 Koper, Slovenia 5 Faculty of Natural Sciences and Mathematics, University of Maribor, 2000 Maribor, Slovenia 6 Faculty of Health and Social Sciences Slovenj Gradec, 2380 Slovenj Gradec, Slovenia 7 University Clinical Centre Maribor, 2000 Maribor, Slovenia * [Correspondence: bojan.zlahtic@um.si](Correspondence: bojan.zlahtic@um.si) Featured Application: In the ﬁeld of medicine, daily high-stake decision-making scenarios arise. To enhance these decision-making processes, the utilization of modern machine learning techniques and their infusion with expert knowledge in a seamless manner while adhering to agile principles enables swift action and facilitates an understanding of the obtained knowledge, fostering trust in the decision-making process. Abstract: Over the past few decades, machine learning has emerged as a valuable tool in the ﬁeld of medicine, driven by the accumulation of vast amounts of medical data and the imperative to harness this data for the betterment of humanity. However, many of the prevailing machine learning algorithms in use today are characterized as black-box models, lacking transparency in their decisionmaking processes and are often devoid of clear visualization capabilities. The transparency of these machine learning models impedes medical experts from effectively leveraging them due to the highstakes nature of their decisions. Consequently, the need for explainable artiﬁcial intelligence (XAI) that aims to address the demand for transparency in the decision-making mechanisms of black-box algorithms has arisen. Alternatively, employing white-box algorithms can empower medical experts by allowing them to contribute their knowledge to the decision-making process and obtain a clear and transparent output. This approach offers an opportunity to personalize machine learning models through an agile process. A novel white-box machine learning algorithm known as Data canyons was employed as a transparent and robust foundation for the proposed solution. By providing medical experts with a web framework where their expertise is transferred to a machine learning model and enabling the utilization of this process in an agile manner, a symbiotic relationship is fostered between the domains of medical expertise and machine learning. The ﬂexibility to manipulate the output machine learning model and visually validate it, even without expertise in machine learning, establishes a crucial link between these two expert domains. Keywords: XAI; explainable

FAQs

Why is explainable artificial intelligence (XAI) important in medical machine learning?

Because many machine learning models are black boxes, their decision logic is not transparent, which makes medical experts hesitate to rely on outputs for high-stakes decisions. XAI adds transparency and explanation to improve trust and usability.

What problem does the Data Canyons approach address?

It provides a transparent and robust white-box foundation for solutions in medicine. It also supports expert involvement through a web framework and an agile process to improve models flexibly.

How does agile expert-based development work in the proposed solution?

Medical experts can transfer their expertise into a machine learning model via a web framework, while the development process follows agile principles. This enables flexible manipulation of outputs and visual validation even without machine-learning expertise.

Aug 2, 2026

Upload by Emma Wilson