Suspected adverse drug reaction detection using association rules mining and fuzzy sets

• Autorzy: Mansour Ayman M. , Khazalah Fayez , Obeidat Mohammad A.

Identyfikatory

DOI

10.15199/48.2022.01.05

Warianty tytułu

PL

Wykrywanie podejrzeń niepożądanych reakcji na lek za pomocą eksploracji reguł asocjacyjnych i zbiorów rozmytych

• Języki publikacji: EN

Abstrakty

EN

Finding adverse drug reaction ADRs is vital to sustaining human life. The effect of the drug under several factors such as age, drug quantity, laboratory results, sex and drug duration are necessary to improve the quality of human body treatment has not been used previously. The paper uses real databases collected from US hospitals to validate the developed detection system. This paper presents an intelligent system based on association rule mining rules and fuzzy set theory. The developed system has the potential to determine the relationships between a drug and its adverse reactions. This is done by extracting several rules with high support and confidence. Two physicians review the results of the proposed system to validate the results. The results matches the ADRs defined by medical associations and drug companies.

PL

Znalezienie niepożądanych reakcji na leki ADR ma kluczowe znaczenie dla podtrzymania życia ludzkiego. Wpływ leku na kilka czynników, takich jak wiek, ilość leku, wyniki laboratoryjne, płeć i czas trwania leku są niezbędne do poprawy jakości leczenia ludzkiego ciała, nie były wcześniej stosowane. W artykule wykorzystano rzeczywiste bazy danych zebrane ze szpitali w USA do walidacji opracowanego systemu wykrywania. W artykule przedstawiono inteligentny system oparty na regułach eksploracji reguł asocjacyjnych i teorii zbiorów rozmytych. Opracowany system ma potencjał do określenia zależności między lekiem a jego działaniami niepożądanymi. Odbywa się to poprzez wyodrębnienie kilku reguł z dużym wsparciem i pewnością. Dwóch lekarzy dokonuje przeglądu wyników proponowanego systemu, aby je zweryfikować. Wyniki są zgodne z ADR-ami zdefiniowanymi przez stowarzyszenia medyczne i firmy farmaceutyczne.

Słowa kluczowe

EN

association rule; fuzzy set; adverse drug reaction; medical cues

PL

niepożądana reakcja na leki; reguła asocjacji; zbiór rozmyty

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2022
• Tom: R. 98, nr 1
• Strony: 34--43
• Opis fizyczny: Bibliogr. 20 poz., rys., tab.

Twórcy

autor

Mansour Ayman M.

• Department of Communication, Electronics and Computer Engineering, Faculty of Engineering, Tafila Technical University, Tafila 66110, Jordan

• https://orcid.org/0000-0001-7086-1613

autor

Khazalah Fayez

• Department of Information Systems, Information Technology College, Al al-Bayt University, Mafraq 25113, Jordan

• https://orcid.org/0000-0002-7448-156X

autor

Obeidat Mohammad A.

• Department of Electrical Power and Mechatronics Engineering, Faculty of Engineering, Tafila Technical University, Tafila 66110, Jordan

• https://orcid.org/0000-0002-0288-962X

Bibliografia

• [1] I. R. Edwards and J. K. Aronson, "Adverse drug reactions: definitions, diagnosis, and management," Lancet, vol. 356, pp. 1255-9, Oct 7 2000.
• [2] Gu, Lifang and Li, Jiuyong and He, Hongxing and Williams, Graham and Hawkins, Simon and Kelman, Chris, Association rule discovery with unbalanced class distributions, Australasian Joint Conference on Artificial Intelligence, Springer, (2003),221- 232.
• [3] Chen, Jie and He, Hongxing and Li, Jiuyong and Jin, Huidong and McAullay, Damien and Williams, Graham and Sparks, Ross and Kelman, Chris, Representing association classification rules mined from health data, International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, Springer, (2005), 1225-1231.
• [4] Harpaz, Rave and Chase, Herbert S and Friedman, Carol, Mining multi-item drug adverse effect associations in spontaneous reporting systems, BMC bioinformatics, Springer 11(2010), No.9,1-8
• [5] Sindhu, MS and Kannan, B, Detecting signals of drug-drug interactions using association rule mining methodology, Int J Comput Sci Inf Technol, Citeseer, 4 (2013), No.4 , 590-594.
• [6] Ibrahim, Heba and Saad, Amr and Abdo, Amany and Eldin, A Sharaf, Mining association patterns of drug-interactions using post marketing FDA’s spontaneous reporting data, Journal of biomedical informatics, Elsevier, 60(2016),294-308
• [7] Guo, Kai and Lin, Hongfei and Xu, Bo and Yang, Zhihao and Wang, Jian and Sun, Yuanyuan and Xu, Kan, Detecting potential adverse drug reactions using association rules and embedding models, International Symposium on Bioinformatics Research and Applications, Springer, (2017), 373-378.
• [8] Lee, Chang-Hung and Chen, Ming-Syan and Lin, Cheng-Ru, Progressive partition miner: an efficient algorithm for mining general temporal association rules , IEEE Transactions on Knowledge and Data Engineering, 15 (2003), No. 4, 1004- 1017.
• [9] Shanmugapriya, K and Shanmugapriya, D and Parveen, H Summia and Niranjani, V, N-Unexpected temporal association rule for diagnosing adverse drug reaction from health database, International Proceedings of Computer Science and Information Technology (IPCSIT),18 (2011).
• [10] Wang, Chao and Guo and et al, Exploration of the association rules mining technique for the signal detection of adverse drug events in spontaneous reporting systems, PloS one, Public Library of Science San Francisco, 7 (2021), No.7, e40561
• [11] Reps, Jenna M and Aickelin, Uwe and Ma, Jiangang and Zhang, Yanchun , Refining adverse drug reactions using association rule mining for electronic healthcare data, IEEE International Conference on Data Mining Workshop, (2014), 763-770.
• [12] Cai, Ruichu and Liu, Mei and Hu, Yong and Melton, Brittany L and Matheny, Michael E and Xu, Hua and Duan, Lian and Waitman, Lemuel R , Identification of adverse drug-drug interactions through causal association rule discovery from spontaneous adverse event reports, Artificial intelligence in medicine, Elsevier, 76 (2017), 7-15.
• [13] Nikfarjam, Azadeh and Gonzalez, Graciela H, Pattern mining for extraction of mentions of adverse drug reactions from user comments, AMIA annual symposium proceedings, American Medical Informatics Association, (2011), 1019-1026.
• [14] Segura-Bedmar, Isabel and de la Pena Gonzalez, Santiago and Martinez, Paloma , Extracting drug indications and adverse drug reactions from Spanish health social media, Proceedings of BioNLP, (2014), 98-106.
• [15] Dingwei Dai and Chris Feudtner , Association Rule Mining of Polypharmacy Drug Utilization Patterns in Health Care Administrative Data Using SAS Enterprise Miner, sas-globalforum- proceedings, (2018),1-17.
• [16] Mansour, Ayman M, Decision tree-based expert system for adverse drug reaction detection using fuzzy logic and genetic algorithm, International Journal of Advanced Computer Research, 8(2018), No. 36,110-128.
• [17] Mansour, Ayman and Ying, Hao and Dews, Peter and Ji, Yanqing and Massanari, R Michael , Fuzzy Rule-Based Approach for Detecting Adverse Drug Reaction Signal Pairs, 8th Conference of the European Society for Fuzzy Logic and Technology, (2013), 384-391.
• [18] Agrawal, Rakesh and Srikant, Ramakrishnan and others , Fast algorithms for mining association rules, Proc. 20th int. conf. very large data bases, Citeseer, 1215 (1994), 487-499.
• [19] University of Waikato. Weka Software. https://www.cs.waikato.ac.nz/ml/weka/. Accessed 27 September 2021.
• [20] R. Orchard, "Fuzzy reasoning in Jess: the Fuzzy J toolkit and Fuzzy Jess," 2001.