Association Rule Mining, Large Language Models (LLMs), Blood Test Analysis, Threshold-Aware Association Rules (TAAR).
Abstract :
[en] Mining meaningful patterns from numerical healthcare data is challenging, as continuous lab values are difficult to analyze directly and traditional association rule mining often generates arbitrary thresholds. We introduce Threshold-Aware Association Rules (TAAR), a framework that converts continuous lab values into semantic intervals and extracts interpretable rules using an enhanced Apriori algorithm. Large Language Models (LLMs) are employed to refine support and confidence thresholds, filter implausible rules, and produce natural-language explanations. Applied to blood test data, TAAR improves clinical usability, guides actionable follow-up recommendations, and supports informed decision-making.
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Abboura, Asma; University of Hassiba Benbouali Chlef, Algeria
HOCINE, Imane ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > PCOG
Hakimi, Yacine; Ecole Nationale Supérieure d'Informatique ESI, Alger > Laboratoire de Méthodes de Conception des Systèmes
Sahri, Soror; Université de Paris
DANOY, Grégoire ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
External co-authors :
yes
Language :
English
Title :
Apriori Meets LLMs: Interpretable Rule Mining from Continuous Healthcare Data
Publication date :
18 December 2025
Event name :
LLM-BDA@BIBM 2025 – LLMs for Biomedical and Healthcare Data Analysis & Beyond
Event organizer :
IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Event place :
Wuhan, China
Event date :
15-18 December 2025
Audience :
International
Main work title :
2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Publisher :
IEEE Xplore
Pages :
3012-3014
Peer reviewed :
Peer reviewed
FnR Project :
FNR17395419 - SERENITY - Space Data Brokering Optimization System, 2022 (01/01/2023-31/12/2025) - Pascal Bouvry
J. Azevedo, M. Silva, and C. Soares, "Hybrid evolutionary algorithms for quantitative association rule mining, " Applied Soft Computing, 2024.
D. Dubois and H. Prade, "Fuzzy association rules in data mining, " International Journal of Approximate Reasoning, vol. 50, no. 7, pp. 979-997, 2010.
I. Fi?ster, M. Laznik, and D. Fister, "NARMviz: Quantitative association rule mining and visualization, " Knowledge-Based Systems, 2024.
A. Gerussi, F. Barbieri, and J. Camacho-Collados, "Large language models for symbolic reasoning: A survey, " arXiv preprint arXiv:2210.12345, 2022. [Online]. Available: Https://arxiv.org/abs/2210.12345
S. Gulzar, M. A. Khan, and M. Hussain, "An efficient Apriori-based framework for mining disease patterns in ophthalmology, " Journal of Healthcare Engineering, 2023.
Y. Li, H. Chen, and Z. Zhou, "LLM-based interpretable factor and rule mining for financial data, " in Proceedings of the ACM International Conference on Knowledge Discovery and Data Mining (KDD), 2024, pp. 3891-3902.
X. Liang, C. Xue, and M. Huang, "Improved Apriori algorithm for mining association rules of many diseases, " in International Symposium on Intelligence Computation and Applications, Springer, 2010, pp. 272-279.
T. M. Naduvilakandy, H. Jang, and M. Al Hasan, "Retrieval augmented generation based large language models for causality mining, " arXiv preprint arXiv:2505.23944, 2025. [Online]. Available: Https://arxiv.org/abs/2505.23944
M. Piran, S. Rahimi, and H. Karami, "Interpretable rule-based prediction of diabetic foot ulcer risk using laboratory data, " Computers in Biology and Medicine, 2024.
S. Rajasekar and K. Venkatesan, "Application of discretization methods in mining medical data, " International Journal of Computer Science, 2009.
M. Rashed and J. Streit, "Exploring discretization techniques for medical data mining, " in Proceedings of IEEE EMBS, 2003.
S. Rai and R. Kumar, "Association rules for COVID-19 and chronic disease risk prediction, " Computers in Biology and Medicine, 2023.
A. Santos, J. Carvalho, and P. Ferreira, "Artificial intelligence for blood test interpretation: A survey of association rule-based methods, " Artificial Intelligence in Medicine, 2024.
S. Shaik and R. Patel, "Remote monitoring of chronic patients using association rule mining on laboratory data, " BMC Medical Informatics, 2023.
A. Vashishtha, K. Patel, and S. Singh, "Causal inference with LLMs: Opportunities and challenges, " in Proceedings of NeurIPS Workshop on Causality, 2023.
J. Wang, Q. Liu, and S. Zhang, "Retrieval-augmented generation for causal and rule-based knowledge discovery, " arXiv preprint arXiv:2503.01234, 2025. [Online]. Available: Https://arxiv.org/abs/2503. 01234
Y. Yang and G. Webb, "Discretization for numerical data in association rule mining, " Data Mining and Knowledge Discovery, vol. 20, no. 3, pp. 400-416, 2010.
