{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:14:06Z","timestamp":1780766046075,"version":"3.54.1"},"reference-count":30,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T00:00:00Z","timestamp":1739404800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>This work deals with the investigation and optimization of the MINDWALC node classification algorithm with a focus on its ability to learn human-interpretable decision trees from knowledge graph databases. For this, we introduce methods to optimize MINDWALC for a specific use case, in which the processed knowledge graph is strictly divided into its inner background knowledge (knowledge about a given domain) and instance knowledge (knowledge about given instances). We present the following improvement approaches, whereby the basic idea of MINDWALC\u2014namely, to use discriminative walks through the knowledge graph as features\u2014remains untouched. First, we apply relation-tail merging to give MINDWALC the ability to take relation-modified nodes into account. Second, we introduce walks with flexible walking depths, which can be used together with MINDWALC\u2019s original walking strategy and can help to detect more similarities between node instances. In some cases, especially with hierarchical, incomplete tree-like structured graphs, our presented flexible walk can improve the classification performance of MINDWALC significantly. However, on mixed knowledge graph structures, the results are mixed. In summary, we were able to show that our proposed methods significantly optimize MINDWALC on tree-like structured graphs, and that MINDWALC is able to utilize background knowledge to replace missing instance knowledge in a human-comprehensible way. Our test results on our medical toy datasets indicate that our MINDWALC optimizations have the potential to enhance decision-making in medical diagnostics, particularly in domains requiring interpretable AI solutions.<\/jats:p>","DOI":"10.3390\/make7010016","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T04:03:35Z","timestamp":1739419415000},"page":"16","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Investigating and Optimizing MINDWALC Node Classification to Extract Interpretable Decision Trees from Knowledge Graphs"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2730-1068","authenticated-orcid":false,"given":"Maximilian","family":"Legnar","sequence":"first","affiliation":[{"name":"Institute of Pathology, University Hosptial Heidelberg, Medical Faculty Heidelberg, Heidelberg University, 69123 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joern-Helge Heinrich","family":"Siemoneit","sequence":"additional","affiliation":[{"name":"Institute of Pathology, University Medical Centre Mannheim, Medical Faculty Mannheim, Heidelberg University, 68167 Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gilles","family":"Vandewiele","sequence":"additional","affiliation":[{"name":"IDLab\u2014imec, Ghent University, 9052 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Hesser","sequence":"additional","affiliation":[{"name":"Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, 69120 Heidelberg, Germany"},{"name":"Data Analysis and Modeling, MIISM, Medical School, Central Institute for Computer Engineering (ZITI), CZS Heidelberg Center for Model-Based AI, Heidelberg University, 68167 Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zoran","family":"Popovic","sequence":"additional","affiliation":[{"name":"Institute of Pathology, University Medical Centre Mannheim, Medical Faculty Mannheim, Heidelberg University, 68167 Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7647-7265","authenticated-orcid":false,"given":"Stefan","family":"Porubsky","sequence":"additional","affiliation":[{"name":"Department of Pathology, University Medical Center, Johannes Gutenberg University Mainz, 55131 Mainz, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cleo-Aron","family":"Weis","sequence":"additional","affiliation":[{"name":"Institute of Pathology, University Hosptial Heidelberg, Medical Faculty Heidelberg, Heidelberg University, 69123 Heidelberg, Germany"},{"name":"Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, 69120 Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1944","DOI":"10.1038\/s41375-023-01962-5","article-title":"The 5th edition of The World Health Organization Classification of Haematolymphoid Tumours: Lymphoid Neoplasms","volume":"37","author":"Alaggio","year":"2023","journal-title":"Leukemia"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Smith, O. (2017). Mind Maps for Medical Students Clinical Specialties, CRC Press. [1st ed.].","DOI":"10.1201\/9781315385235"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Vandewiele, G., Steenwinckel, B., Turck, F.D., and Ongenae, F. (2020). MINDWALC: Mining interpretable, discriminative walks for classification of nodes in a knowledge graph. BMC Med. Inform. Decis. Mak., 20.","DOI":"10.1186\/s12911-020-01134-w"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103627","DOI":"10.1016\/j.artint.2021.103627","article-title":"Knowledge graphs as tools for explainable machine learning: A survey","volume":"302","author":"Tiddi","year":"2022","journal-title":"Artif. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3447772","article-title":"Knowledge Graphs","volume":"54","author":"Hogan","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref_6","first-page":"29","article-title":"Knowledge Graphs: New Directions for Knowledge Representation on the Semantic Web (Dagstuhl Seminar 18371)","volume":"Volume 8","author":"Bonatti","year":"2019","journal-title":"Dagstuhl Reports"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Agrawal, G., Kumarage, T., Alghamdi, Z., and Liu, H. (2024). Can Knowledge Graphs Reduce Hallucinations in LLMs?: A Survey. arXiv.","DOI":"10.18653\/v1\/2024.naacl-long.219"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1886","DOI":"10.1109\/JBHI.2023.3294249","article-title":"K-PathVQA: Knowledge-Aware Multimodal Representation for Pathology Visual Question Answering","volume":"28","author":"Naseem","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Schlichtkrull, M., Kipf, T.N., Bloem, P., Berg, R.v.d., Titov, I., and Welling, M. (2017). Modeling Relational Data with Graph Convolutional Networks. arXiv.","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1007\/978-3-319-46523-4_30","article-title":"RDF2Vec: RDF Graph Embeddings for Data Mining","volume":"Volume 9981","author":"Groth","year":"2016","journal-title":"The Semantic Web \u2013 ISWC 2016"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Schramm, S., Wehner, C., and Schmid, U. (2024). Comprehensible Artificial Intelligence on Knowledge Graphs: A survey. arXiv.","DOI":"10.1016\/j.websem.2023.100806"},{"key":"ref_12","unstructured":"Barzilay, R., and Johnson, M. Random Walk Inference and Learning in A Large Scale Knowledge Base. Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing."},{"key":"ref_13","unstructured":"Wang, Z., and Li, J. (2015). RDF2Rules: Learning Rules from RDF Knowledge Bases by Mining Frequent Predicate Cycles. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1007\/s00778-015-0394-1","article-title":"Fast rule mining in ontological knowledge bases with AMIE $$+$$ +","volume":"24","author":"Teflioudi","year":"2015","journal-title":"VLDB J."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Chen, Y., Goldberg, S., Wang, D.Z., and Johri, S.S. (July, January 26). Ontological Pathfinding. Proceedings of the 2016 International Conference on Management of Data, San Francisco, CA, USA.","DOI":"10.1145\/2882903.2882954"},{"key":"ref_16","unstructured":"Ott, S., Meilicke, C., and Samwald, M. (2021, January 4\u20138). SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models. Proceedings of the 3rd Conference on Automated Knowledge Base Construction, Virtual."},{"key":"ref_17","unstructured":"Jeon, D., and Kim, W. (2011, January 24\u201326). Development of semantic decision tree. Proceedings of the The 3rd International Conference on Data Mining and Intelligent Information Technology Applications, Macao, China."},{"key":"ref_18","unstructured":"Giabbanelli, P.J., and Peters, J.G. (2015). An Algebra to Merge Heterogeneous Classifiers. arXiv."},{"key":"ref_19","unstructured":"Depeau, J. (2025, January 06). Pok\u00e9graph: Gotta Graph \u2018Em All! Neo4j Blog, 25 February 2020. Available online: https:\/\/neo4j.com\/blog\/pokegraph-gotta-graph-em-all\/."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1007\/s11560-022-00599-2","article-title":"Kidney biopsy codes for pathologists: Ein Projekt der Arbeitsgruppe Nephropathologie der Europ\u00e4ischen Gesellschaft f\u00fcr Pathologie","volume":"17","author":"Leh","year":"2022","journal-title":"Die Nephrol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"The Unified Medical Language System (UMLS): Integrating biomedical terminology","volume":"32","author":"Bodenreider","year":"2004","journal-title":"Nucleic Acids Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/j.jbi.2015.08.016","article-title":"An alternative database approach for management of SNOMED CT and improved patient data queries","volume":"57","author":"Campbell","year":"2015","journal-title":"J. Biomed. Inform."},{"key":"ref_23","first-page":"15","article-title":"A Phylogeny and Evolutionary History of the Pok\u00e9mon","volume":"18","author":"Shelomi","year":"2015","journal-title":"Res. Ann. Improbable Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1007\/978-3-319-46547-0_20","article-title":"A Collection of Benchmark Datasets for Systematic Evaluations of Machine Learning on the Semantic Web","volume":"Volume 9982","author":"Groth","year":"2016","journal-title":"The Semantic Web \u2013 ISWC 2016"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J. (2017). Classification and Regression Trees, Routledge. [1st ed.].","DOI":"10.1201\/9781315139470"},{"key":"ref_26","unstructured":"Latkowski, R. (2003). High Computational Complexity of the Decision Tree Induction with many Missing Attribute Values. Proceedings of CS&P, Institute of Computer Science, Warsaw University."},{"key":"ref_27","first-page":"191","article-title":"Computational Complexity Analysis of Decision Tree Algorithms","volume":"Volume 11311","author":"Bramer","year":"2018","journal-title":"Artificial Intelligence XXXV"},{"key":"ref_28","unstructured":"Kodratoff, Y. When does overfitting decrease prediction accuracy in induced decision trees and rule sets?. Proceedings of the Machine Learning\u2014EWSL-91."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1080\/16843703.2014.11673330","article-title":"Efficient Construction of Decision Trees by the Dual Information Distance Method","volume":"11","author":"Dana","year":"2014","journal-title":"Qual. Technol. Quant. Manag."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.pathol.2020.08.006","article-title":"Benign mimics of prostate cancer","volume":"53","author":"Egevad","year":"2021","journal-title":"Pathology"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/1\/16\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:32:37Z","timestamp":1760027557000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/1\/16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,13]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["make7010016"],"URL":"https:\/\/doi.org\/10.3390\/make7010016","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,13]]}}}