Weighted Compact Tree for Discovery of Association among Frequent and Rare Attributes: Acute Inflammation Case Study

Shwetha Rai; M. Geetha; K. Nakul Shetty; Preetham Kumar; Vaishak Vidyadhar; Roopashri Shetty

doi:10.57159/jcmm.5.3.25437

Authors

Shwetha Rai Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India https://orcid.org/0000-0002-5714-2611
M. Geetha Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India https://orcid.org/0000-0002-6150-7601
K. Nakul Shetty Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India https://orcid.org/0000-0002-4842-211X
Preetham Kumar Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India https://orcid.org/0000-0002-0736-7687
Vaishak Vidyadhar Royal College of Physicians, London, United Kingdom
Roopashri Shetty Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India https://orcid.org/0000-0003-4145-620X

DOI:

https://doi.org/10.57159/jcmm.5.3.25437

Keywords:

Association Rule Mining, Data Mining, Frequent Itemsets, Rare Itemsets, WC-Tree

Abstract

Data analytics has gained popularity due to its ability to extract valuable insights from large amounts of data, allowing businesses to make appropriate decisions and improve overall performance. Expediting this process requires the entire dataset to reside in the main memory. This study proposes a novel Weighted Compact Tree (WC-Tree), a tree data structure that represents the complete dataset in abstract form in the RAM, leading to fast data retrieval. Its significance is analyzed by executing it on publicly available datasets and comparing it against existing algorithms. The analysis indicates that WC-Tree is efficient on datasets of any size with varying attributes. The efficacy of WC-Tree is further analyzed by executing it on acute inflammation data containing patient records on acute cystitis and pyelonephritis, two urological diseases commonly caused by urinary tract infections. Early detection of these diseases using a cost and time-effective method is useful in their diagnosis. WC-Tree aims to discover the association among various attributes in predicting these urological diseases using association rule mining. Association rules are identified based on null-invariant: Cosine, Kulczynski, and null-variant: Conviction, Confidence, and Lift evaluation measures. The rules discovered show that if lumbar pain, pain during micturition, straining to void, inflammation of the urinary bladder, a rare symptom, is detected, then there are chances of the patient experiencing high body temperature and pyelonephritis.

References

[1] D. Sharma, V. Kudva, V. Patil, A. Kudva, and R. S. Bhat, "A convolutional neural network based deep learning algorithm for identification of oral precancerous and cancerous lesion and differentiation from normal mucosa: A retrospective study," Engineered Science, vol. 18, no. 15, pp. 278–287, 2022.

[2] N. Naik, Y. Rallapalli, M. Krishna, A. S. Vellara, D. K. Shetty, V. Patil, et al., "Demystifying the advancements of big data analytics in medical diagnosis: An overview," Engineered Science, vol. 19, no. 2, pp. 42–58, 2021.

[3] X. Yang, H. Chen, Y. Zheng, S. Qu, H. Wang, and F. Yi, "Disease burden and long-term trends of urinary tract infections: A worldwide report," Frontiers in Public Health, vol. 10, p. 888205, 2022.

[4] T. K. Mattoo, N. Shaikh, and C. P. Nelson, "Contemporary management of urinary tract infection in children," Pediatrics, vol. 147, no. 2, 2021.

[5] Y. Li, Y. Shi, L. Jia, Y. Li, Z. Xingwang, and G. Xue, "Risk factors for urinary tract infection in patients with urolithiasis: Primary report of a single center cohort," BMC Urology, vol. 18, no. 1, p. 45, 2018.

[6] F. Jansåker, P. O. Forsberg, X. Li, and K. Sundquist, "The relation of body mass index, body height, and parity to pyelonephritis: A nationwide population-based cohort study of over one million parous women (1997–2018)," International Journal of Infectious Diseases, vol. 125, pp. 67–73, 2022.

[7] M. Belyayeva and J. M. Jeong, "Acute pyelonephritis," in StatPearls [Internet], Treasure Island, FL, USA: StatPearls Publishing, 2022.

[8] M. Hahsler, "A probabilistic comparison of commonly used interest measures for association rules," tech. rep., Southern Methodist University, Dallas, TX, USA, 2015.

[9] P. D. McNicholas, T. B. Murphy, and M. O'Regan, "Standardising the lift of an association rule," Computational Statistics & Data Analysis, vol. 52, no. 10, pp. 4712–4721, 2008.

[10] F. Liu and X. Zhang, "Hypertension and obesity: Risk factors for thyroid disease," Frontiers in Endocrinology, vol. 13, p. 939367, 2022.

[11] B. Xiao and G. Piao, "Analysis of influencing factors and enterprise strategy of online consumer behavior decision based on association rules and mobile computing," Wireless Communications and Mobile Computing, vol. 2022, no. 1, p. 6849017, 2022.

[12] X. Li and C. E. Jimenez, "Application analysis of nursing students' grades in course relevance based on association rule mining algorithm apriori," Journal of Contemporary Educational Research, vol. 8, no. 2, pp. 213–223, 2024.

[13] R. Agrawal and R. Srikant, "Fast algorithms for mining association rules," in Proc. 20th Int. Conf. Very Large Data Bases (VLDB), (Santiago, Chile), pp. 487–499, Sept. 1994.

[14] J. Han, J. Pei, Y. Yin, and R. Mao, "Mining frequent patterns without candidate generation: A frequent-pattern tree approach," Data Mining and Knowledge Discovery, vol. 8, no. 1, pp. 53–87, 2004.

[15] A. Borah and B. Nath, "Rare association rule mining from incremental databases," Pattern Analysis and Applications, vol. 23, no. 1, pp. 113–134, 2020.

[16] M. Geetha and R. D'Souza, "An efficient discovery of frequent concepts using weighted count tree," in Inst. Comput. Sci., Social Informat. Telecommun. Eng., vol. 539, pp. 367–370, 2012.

[17] S. Sawangarreerak and P. Thanathamathee, "Detecting and analyzing fraudulent patterns of financial statement for open innovation using discretization and association rule mining," Journal of Open Innovation: Technology, Market, and Complexity, vol. 7, no. 2, p. 128, 2021.

[18] W. Altaf, M. Shahbaz, and A. Guergachi, "Applications of association rule mining in health informatics: A survey," Artificial Intelligence Review, vol. 47, no. 3, pp. 313–340, 2017.

[19] C. C. Aggarwal, "An introduction to data classification," in Data Classification: Algorithms and Applications, vol. 125, p. 142, 2014.

[20] M. Kaur and S. Kang, "Market Basket Analysis: Identify the changing trends of market data using association rule mining," Procedia Computer Science, vol. 85, pp. 78–85, 2016.

[21] S. Stilou, P. D. Bamidis, N. Maglaveras, and C. Pappas, "Mining association rules from clinical databases: An intelligent diagnostic process in healthcare," Studies in Health Technology and Informatics, vol. 2, pp. 1399–1403, 2001.

[22] B. S. dos Santos, M. T. A. Steiner, A. T. Fenerich, and R. H. P. Lima, "Data mining and machine learning techniques applied to public health problems: A bibliometric analysis from 2009 to 2018," Computers & Industrial Engineering, vol. 138, p. 106120, 2019.

[23] K. Pazhanikumar and S. Arumugaperumal, "Association rule mining and medical application: A detailed survey," International Journal of Computer Applications, vol. 80, no. 17, 2013.

[24] G. Sarıyer and C. Ö. Taşar, "Highlighting the rules between diagnosis types and laboratory diagnostic tests for patients of an emergency department: Use of association rule mining," Health Informatics Journal, vol. 26, no. 2, pp. 1177–1193, 2020.

[25] A. R. Kulkarni and D. S. D. Mundhe, "Data mining technique: An implementation of association rule mining in healthcare," International Advanced Research Journal in Science, Engineering and Technology, vol. 4, no. 7, pp. 62–65, 2017.

[26] A. Ramezankhani, O. Pournik, J. Shahrabi, F. Azizi, and F. Hadaegh, "An application of association rule mining to extract risk pattern for type 2 diabetes using Tehran lipid and glucose study database," International Journal of Endocrinology and Metabolism, vol. 13, no. 2, p. e25389, 2015.

[27] J. Nahar, T. Imam, K. S. Tickle, and Y. P. P. Chen, "Association rule mining to detect factors which contribute to heart disease in males and females," Expert Systems with Applications, vol. 40, no. 4, pp. 1086–1093, 2013.

[28] J. Nahar, K. S. Tickle, A. S. Ali, and Y. P. P. Chen, "Significant cancer prevention factor extraction: An association rule discovery approach," Journal of Medical Systems, vol. 35, no. 3, pp. 353–367, 2011.

[29] D. G. Lee, K. S. Ryu, M. Bashir, J. W. Bae, and K. H. Ryu, "Discovering medical knowledge using association rule mining in young adults with acute myocardial infarction," Journal of Medical Systems, vol. 37, no. 2, p. 9896, 2013.

[30] C. W. Cheng, N. Chanani, J. Venugopalan, K. Maher, and M. D. Wang, "icuARM: An ICU clinical decision support system using association rule mining," IEEE Journal of Translational Engineering in Health and Medicine, vol. 1, pp. 4400110–4400110, 2013.

[31] M. Harahap, A. M. Husein, S. Aisyah, F. R. Lubis, and B. A. Wijaya, "Mining association rule based on the diseases population for recommendation of medicine need," in Journal of Physics: Conference Series, vol. 1007, p. 012017, Apr. 2018.

[32] E. Ruiz, J. Ramirez, J. M. Górriz, J. Casillas, and Alzheimer's Disease Neuroimaging Initiative, "Alzheimer's disease computer-aided diagnosis: Histogram-based analysis of regional MRI volumes for feature selection and classification," Journal of Alzheimer's Disease, vol. 65, no. 3, pp. 819–842, 2018.

[33] I. U. Said, A. H. Adam, and A. B. Garko, "Association rule mining on medical data to predict heart disease," International Journal of Science Technology and Management, vol. 4, no. 8, pp. 26–35, 2015.

[34] A. M. Venkatesan, A. Oto, B. C. Allen, O. Akin, L. F. Alexander, J. Chong, et al., "ACR appropriateness criteria recurrent lower urinary tract infections in females," Journal of the American College of Radiology, vol. 17, no. 11, pp. S487–S496, 2020.

[35] L. Dalla-Palma, F. Pozzi-Mucelli, and R. S. Pozzi-Mucelli, "Delayed CT findings in acute renal infection," Clinical Radiology, vol. 50, no. 6, pp. 364–370, 1995.

[36] J. R. Johnson and T. A. Russo, "Acute pyelonephritis in adults," New England Journal of Medicine, vol. 378, no. 1, pp. 48–59, 2018.

[37] A. D. Smith, P. Nikolaidis, G. Khatri, S. T. Chong, A. D. D. Leon, D. Ganeshan, et al., "ACR Appropriateness Criteria acute pyelonephritis: 2022 update," Journal of the American College of Radiology, vol. 19, no. 11, pp. S224–S239, 2022.

[38] P. Nikolaidis, V. S. Dogra, S. Goldfarb, J. L. Gore, H. J. Harvin, M. E. Heilbrun, et al., "ACR appropriateness criteria acute pyelonephritis," Journal of the American College of Radiology, vol. 15, no. 11, pp. S232–S239, 2018.

[39] Y. D. Choi, W. J. Yang, S. H. Do, D. S. Kim, H. Y. Lee, and J. H. Kim, "Vesicoureteral reflux in adult women with uncomplicated acute pyelonephritis," Urology, vol. 66, no. 1, pp. 55–58, 2005.

[40] R. M. Rosdan, W. S. W. Awang, and W. A. W. A. Bakar, "Comparison of affinity degree classification with four different classifiers in several data sets," International Journal of Advanced Technology and Engineering Exploration, vol. 8, no. 75, p. 247, 2021.

[41] D. J. Park, M. W. Park, H. Lee, Y. J. Kim, Y. Kim, and Y. H. Park, "Development of machine learning model for diagnostic disease prediction based on laboratory tests," Scientific Reports, vol. 11, no. 1, p. 7567, 2021.

[42] A. T. Chowdhury, A. Salam, M. Naznine, D. A. Abdalla, L. Erdman, M. E. Chowdhury, and T. O. Abbas, "Artificial intelligence tools in pediatric urology: A comprehensive review of recent advances," Diagnostics, vol. 14, no. 18, p. 2059, 2024.

[43] A. B. Chen, T. Haque, S. Roberts, S. Rambhatla, G. Cacciamani, P. Dasgupta, and A. J. Hung, "Artificial intelligence applications in urology: Reporting standards to achieve fluency for urologists," Urologic Clinics, vol. 49, no. 1, pp. 65–117, 2022.

[44] B. Z. Hameed, A. V. S. Dhavileswarapu, S. Z. Raza, H. Karimi, H. S. Khanuja, D. K. Shetty, et al., "Artificial intelligence and its impact on urological diseases and management: A comprehensive review of the literature," Journal of Clinical Medicine, vol. 10, no. 9, p. 1864, 2021.

[45] R. Barua, S. Das, and J. Mondal, "Emerging applications of artificial intelligence (AI) and machine learning (ML) in modern urology," in Exploring the Convergence of Computer and Medical Science Through Cloud Healthcare, pp. 117–133, 2023.

[46] E. Checcucci, S. D. Cillis, S. Granato, P. Chang, A. S. Afyouni, and Z. Okhunov, "Applications of neural networks in urology: A systematic review," Current Opinion in Urology, vol. 30, no. 6, pp. 788–807, 2020.

[47] I. A. Ozkan, M. Koklu, and I. U. Sert, "Diagnosis of urinary tract infection based on artificial intelligence methods," Computer Methods and Programs in Biomedicine, vol. 166, pp. 51–59, 2018.

[48] J. K. Soler, D. Corrigan, P. Kazienko, T. Kajdanowicz, R. Danger, M. Kulisiewicz, and B. Delaney, "Evidence-based rules from family practice to inform family practice; the learning healthcare system case study on urinary tract infections," BMC Family Practice, vol. 16, no. 1, p. 63, 2015.

[49] J. Czerniak and H. Zarzycki, "Application of rough sets in the presumptive diagnosis of urinary system diseases," in Proc. 9th Int. Conf. Artificial Intelligence and Security in Computing Systems (ACS 2002), (Międzyzdroje, Poland), pp. 41–51, Oct. 2002.

[50] J. Czerniak and H. Zarzycki, "Acute inflammations." https://archive.ics.uci.edu/dataset/184/acute+inflammations. Accessed: Nov. 13, 2024.

[51] P. Fournier-Viger, J. C. W. Lin, A. Gomariz, T. Gueniche, A. Soltani, Z. Deng, and H. T. Lam, "The SPMF open-source data mining library version 2," in Joint European Conf. Machine Learning and Knowledge Discovery in Databases, (Cham, Switzerland), pp. 36–40, Springer, Sept. 2016.

[52] S. Rai, M. Geetha, P. Kumar, and B. Giridhar, "Partial weighted count tree for discovery of rare and frequent itemsets," Engineered Science, vol. 20, no. 2, pp. 284–295, 2022.

[53] S. Rai, M. Geetha, P. Kumar, and B. Giridhar, "Binary count tree: An efficient and compact structure for mining rare and frequent itemsets," Engineered Science, vol. 17, no. 2, pp. 185–194, 2022.

[54] S. Chugh, A. Pietropaolo, E. Montanari, K. Sarica, and B. K. Somani, "Predictors of urinary infections and urosepsis after ureteroscopy for stone disease: A systematic review from EAU section of urolithiasis (EULIS)," Current Urology Reports, vol. 21, no. 4, p. 16, 2020.

[55] A. Pietropaolo, R. M. Geraghty, R. Veeratterapillay, A. Rogers, P. Kallidonis, L. Villa, et al., "A machine learning predictive model for post-ureteroscopy urosepsis needing intensive care unit admission: A case-control YAU endourology study from nine European centres," Journal of Clinical Medicine, vol. 10, no. 17, p. 3888, 2021.

[56] V. Patil, D. K. Singhal, N. Naik, B. Z. Hameed, M. J. Shah, S. Ibrahim, et al., "Factors affecting the usage of wearable device technology for healthcare among Indian adults: A cross-sectional study," Journal of Clinical Medicine, vol. 11, no. 23, p. 7019, 2022.