ارائه مدلی برای پیش بینی بقای بیماران مبتلا به ملانوم بر اساس الگوریتم های داده کاوی
محورهای موضوعی : فناوری اطلاعات و ارتباطات
فریناز صناعی
1
,
سید عبدالله امین موسوی
2
*
,
عباس طلوعی اشلقی
3
,
علی رجب زاده قطری
4
1 - دانشجوی دکتری رشته مدیریت فناوری اطلاعات،گرایش کسب کار هوشمند ، گروه مدیریت فناوری اطلاعات ،دانشکده مدیریت واقتصاد، واحد علوم تحقیقات، دانشگاه آزاد اسلامی،تهران ،ایران
2 - عضو هیات علمی( استادیار) ،گروه مدیریت صنعتی ، دانشکده مدیریت ، واحد تهران مرکز، دانشگاه آزاد اسلامی،تهران،ایران
3 - دانشگاه آزاد اسلامی واحد علوم و تحقیقات
4 - Tarbiat Modarres University
کلید واژه: داده کاوي, پیش بیني, ملانوم, بقاي بیماري, شبکه عصبي, درخت تصمیم گیري,
چکیده مقاله :
مقدمه: ملانوم جزء شایعترین سرطان تشخیصي و دومین علت مرگ ناشي از سرطان در میان افراد است. تعداد مبتلایان به آن در حال افزایش است. ملانوم، نادرترین و بدخیم ترین نوع سرطان پوست است.در شرایط پیشرفته توانایي انتشار به ارگانهاي داخلي را دارد و ميتواند منجر به مرگ شود. طبق برآوردهاي انجمن سرطان آمریکا براي ملانوم در ایالاتمتحده براي سال 2022 عبارتاند از: حدود 99،780 ز افراد مبتلابه ملانوم تشخیص داده شدند و حدود 7،650 نفر در اثر ملانوم جان خود را از دست ميدهند. لذا هدف از این مطالعه، طراحي بهبود دقت الگوریتم براي پیش بیني بقاي این بیماران است. روش پژوهش: روش حاضر کاربردي، توصیفي- تحلیلي و گذشتهنگر است. جامعه پژوهش را بیماران مبتلابه سرطان ملانوم پایگاه داده مرکز تحقیقات کشوري سرطان دانشگاه شهید بهشتي ) 1۳87 تا 1۳91 ( که تا 5 سال مورد پیگیري قرارگرفته بودند، تشکیل داده است. مدل پیشبیني بقاي ملانوم بر اساس شاخص هاي ارزیابي الگوریتم هاي داده کاوي انتخاب شد. یافته ها: الگوریتم هاي شبکه عصبي، بیز ساده، شبکه بیزي، ترکیب درخت تصمیم گیري با بیز ساده، رگرسیون لجستیک، J48 ، ID3 بهعنوان مدل هاي استفاده شده ي پایگاه داده کشور انتخاب شدند . عملکرد شبکه عصبي در همه شاخصهاي ارزیابي ازلحاظ آماري نسبت به سایر الگوریتم هاي منتخب بالاتر بود. نتیجه گیري: نتایج مطالعه حاضر نشان داد که شبکه عصبي با مقدار 97 / 0 ازلحاظ دقت پیش بیني عملکرد بهینه دارد. بنابراین مدل پیش بیني کننده بقاي ملانوم، هم ازلحاظ قدرت تمایز و هم ازلحاظ پایایي، عملکرد بهتري از خود نشان داد؛ بنابراین، این الگوریتم به عنوان مدل پیش بیني بقاي ملانوم پیشنهاد شد
Background/Purpose: Among the most commonly diagnosed cancers, melanoma is the second leading cause of cancer-related death. A growing number of people are becoming victims of melanoma. Melanoma is also the most malignant and rare form of skin cancer. Advanced cases of the disease may cause death due to the spread of the disease to internal organs. The National Cancer Institute reported that approximately 99,780 people were diagnosed with melanoma in 2022, and approximately 7,650 died. Therefore, this study aims to develop an optimization algorithm for predicting melanoma patients' survival. Methodology: This applied research was a descriptive-analytical and retrospective study. The study population included patients with melanoma cancer identified from the National Cancer Research Center at Shahid Beheshti University between 2008 and 2013, with a follow-up period of five years. An optimization model was selected for melanoma survival prognosis based on the evaluation metrics of data mining algorithms. Findings: A neural network algorithm, a Naïve Bayes network, a Bayesian network, a combination of decision tree and Naïve Bayes network, logistic regression, J48, and ID3 were selected as the models used in the national database. Statistically, the studied neural network outperformed other selected algorithms in all evaluation metrics. Conclusion: The results of the present study showed that the neural network with a value of 0.97 has optimal performance in terms of reliability. Therefore, the predictive model of melanoma survival showed a better performance both in terms of discrimination power and reliability. Therefore, this algorithm was proposed as a melanoma survival prediction model.
1. Zamanian Azodi M, Azizi Jalilian F. Early detection of cancer and proteomics. Journal of Ilam University of Medical Sciences 2013; 21 (1): 112-22. (Persian)
2. Shariatzadeh MA, Hamta A, Solimani M, et al. Determination of chromosomal changes in DMBA-induced skin cancer in SD rat strains. J Arak Uni Med Sci 2009; 12 (2): 73-87. (Persian)
3. Howlader N, N.A., Krapcho M, Miller D, Brest A, Yu M, Ruhl J, Tatalovich Z, Mariotto A, Lewis DR, Feuer EJ, Cronin KA. SEER Cancer Statistics Review, 19752016. 2018 December, 11, 2019 2020].
4. Seyed Elham Hosseini Fadafen, Emad Fatemizadeh, “Diagnosis of skin cancer by extracting features from images“Shhab Dansh Institute(2016)
5 Hoseini. (25/06/1391). Available: http://www.fbme.ir/category/6. [1] A. Hoseini. (25/06/1391). Available: http://www.fbme.ir/category/6
6. David A. Kirchar DA, Mark R, et al. Melanoma brain metastasis: mechanisms, models and medicine. J Mol Sci 2016; 17 (7): 1-29.
7 .Wrobel, S., M. Przybylo, and E. Stepien, The Clinical Trial Landscape for Melanoma Therapies. J Clin Med, 2019. 8(3).
8. Longo D, Casper D, Jameson L, et al. Harrison’s principles of internal medicine.18th ed. New york; Mc Graw-Hill 2012; 1945-65.
9. L. Sophia, and M. S. Pallavi. “Predicting Protein in Cancer Diagnosis Using Effective Classification and Feature Selection Technique,” IEEE International Conference on Communication and Signal Processing (ICCSP), pp. 156-159, 2018
10. Burd, C.E., et al., Mutation-Specific RAS Oncogenicity Explains NRAS Codon 61 Selection in Melanoma. Cancer Discovery, 2014. 4(12): p. 1418.
11. S. Winiarti, H. Yuliansyah, and A. A. Purnama, “Identification of Toddlers’ Nutritional Status using Data Mining Approach,” International Journal of Advanced Computer Science and Applications, Vol. 9, No. 1, pp. 164 - 169, 2018.
12. Kim, R. H. & Meehan, S. A. Immunostain use in the diagnosis of melanomas referred to a tertiary medical center: a 15-year retrospective review (2001–2015). J. Cutan. Pathol. 44, 221–227 (2017).
13. Roebuck H, Moran K, MacDonald DA, Shumer S, McCune RL. Assessing Skin Cancer Prevention and Detection Educational Needs: An Andragogical Approach. The Journal for Nurse Practitioners. 2015;11(4):40916
14. Alizadeh S, Ghazanfari M & Teimorpour B. Data mining and knowledge discovery. 2nd ed. Tehran: Publication of Iran University of Science and Technology; 2011: 70-250[Book in Persian].
15. Witten I. Frank E.Hall M. Data mining : Practical machin learning tools techniques: Morgan Kaufinann: 2011
16. Habif, T.P., Campbell, J.L., Chapman, S., and Dinulos, J., Skin disease: diagnosis and treatment, Elsevier Mosby, 2010 .
17. Han J. Kamber M,Pei J. Data mining: Concepts and techniques: Publishers Inc.: 2011
18. Razavi AR Applications of knowledge discovery in quality registries - predicting recurrence of breast cancer and analyzing non-compliance with a clinical guideline: Institutionen för medicinsk teknik; 2015.
19 Masilamani, G. D. Praveenkumar, and R.Gayathri. “Comparative Study on Skin Cancer Using the Approach of Data Mining,” Int. J. Res. Appl. Sci. Eng. Tech, no. 4, 2016
20. Liu Peng LL. A review of missing data treatment methods .2005
21 Ameri H, Alizadeh S & Barzegari A. Knowledge extraction of diabetics’ data by decision tree method. Health Management
2013; 16(53): 58-72[in Persian]
22. Magnani M. Techniques for dealing with missing . Data in knowledge discovery Department of Computer Science, Universitiy of Bologna.2004
23 K. Q. Kanaan. “Classification of human skin diseases using data mining,” International Journal of Advanced Engineering Research and Sci, Vol. 4, no. 1, 2017.
24. Aftarczuk K, Kozierkiewicz A. Evaluation of selected data mining algorithms implemented in Medical Decision Support Systems. Report of Institute of Information Science & Engineering, University of Technology. Wroclaw 2009; (1).
25. Mahmoodi MS, Mahmoodi SA, Haghighi F, Mahmoodi SM. Determining the stage of breast cancer by data mining algorithms. ijbd. 2014;7(2):36-44.
26. Sarafi Nejad A, Saeid AH, Rose I.M, Rowhanimanesh AR. Modeling a Data Mining Decision Tree and Propose a New Model for the Diagnosis of Skin Cancer by Immunohistochemical Staining Methods. Journal of Health and Biomedical Informatics 2014; 1(1): 54-62.[Persian].
27. Dehghan P, Mogharabi M, Zabbah I, Layeghi K & Maroosi A. Modeling Breast cancer using data mining methods. Journal of Health and Biomedical Informatics 2018; 4(4): 266-78[Article in Persian].
28. Tahmasebian S, Ghazisaeedi M, Langarizadeh M, Mokhtaran M, Mahdavi-Mazdeh M, Javadian P. Applying data mining techniques to determine important parameters in chronic kidney disease and the relations of these parameters to each other. J Renal Inj Prev 2017; 6(2): 83–7.
29. Martınez AM, Webb GI, Chen S, Zaidi NA. Scalable learning of Bayesian network classifiers. Journal of Machine Learning Research. 2016;17(44):1-35
30. Finkelstein J, Jeong IC. Machine learning approaches to personalize early prediction of asthma exacerbations. Ann N Y Acad Sci 2017;1387(1):153- 65.
31. Ahmed K, Jesmin T, Rahman MZ. Early Prevention and Detection of Skin Cancer Risk using Data Mining. International Journal of Computer Applications 2013;62(4):1 -6.
32. Gopalakrishnan, V. et al. Gut microbiome modulates response to anti-PD-1 immunotherapy in melanoma patients. Science 359, 97–103 (2018).
33. Hira Beenish, Muhammad Fahadad International Conference on Computing and Information Technology, University o f Tabuk, Kingdom o f Saudi Arabia. Volume: 01, Issue: ICCIT- 1441, Page No.: 44 - 47, 9 & 1 9 Sep. 2020
34. McLaughlin JM, Fisher JL, Paskett ED. Marital status and stage at diagnosis of cutaneous melanoma: results from the Surveillance Epidemiology and End Results (SEER) program, 1973–2006. Cancer. 2011;117(9):1984–
1993
35. Chen, S., et al., Targeting MC1R depalmitoylation to prevent melanomagenesis in
redheads. Nature Communications, 2019. 10(1): p. 877.
36. N. R. Aaron, and T. M. Khoshgoftaar, “Modernizing analytics for melanoma with a large-scale research dataset,” In 2017 IEEE International Conference on Information Reuse and Integration (IRI), pp. 551 - 558, 2017.
37. Thongkam J. Xu GD, Zhang YC,Huang FC Toward breast cancer survivability prediction models through improving training space. 2009 Dec:36(10):12200-9.
38. Gibert K, Sanchez-Marre M, Codina V editors . Choosing the right data mining technique: Classification of methods and intelligent recommendation. Proceeding the IEMSs fifth biennial meeting international congress on environmental modeling and software ;2015
39. Witten I. Frank E.Hall M. Data mining : Practical machine Learning tools and techniques: Morgan Kaufinann: 2011.
40 Lee, C., Collichio, F., Ollila, D. & Moschos, S. Historical review of melanoma treatment and outcomes. Clin. Dermatol. 31, 141–147 (2013).
410 Dehghan P, Mogharabi M, Zabbah I, Layeghi K & Maroosi A. Modeling Breast cancer using data mining methods. Journal of Health and Biomedical Informatics 2018; 4(4): 266-78[Article in Persian].
42. H. Safigholi, A. S. Meigooni, and W. Y. J. M. p. Song, "Comparison of 192Ir, 169Yb, and 60Co high-dose rate brachytherapy sources for skin cancer treatment," vol. 44, no. 9, pp. 4426-4436, 2017.
43. Kasạcian A, Abadi A-R ، Mehrabi Y ،Mousavi-Jarahi A-R. Estimating to relative survival of skin cancer patients referring to imam khomeini cancer institute during 1990-95 Knowledge & Health. 2009:4(3):1-7. [In Persian].
44. U.-O. Dorj, K.-K. Lee, J.-Y. Choi, M. J. M. T. Lee, and Applications, "The skin cancer classification using deep convolutional neural network," pp. 1-16, 2018.
45. Jonsdottir T. Hvannberg ET, Sigurdsson H, Sigurdsson S. The feasibility of constructing a predictive outcome model for breast cancer using the tools of data mining . Expert Systems with Applications. 2008 Jan;34(1):108-18.
46. Yu CT, Chao CM, Cheng BW. Prediction of surv using three artificial intelligence techniques. Journal of Theoretical and applied Information Technology. 2014;60(1):179-83. 99.
47. Zhe Tang, Yuancheng Su, Er Meng Joo, Fang Qi,Li Zhang, Jianyong Zhou, “A local binary pattern based texture descriptors for classification of tea leaves”, NEUCOM15529, May. 2015.
48. Maimon O.Rokach L.Data mining and knowledge discover handbook;springer Verlag New York, Inc.; 2010
49. Kim, R. H. & Meehan, S. A. Immunostain use in the diagnosis of melanomas referred to a tertiary medical center: a 15-year retrospective review (2001–2015). J. Cutan. Pathol. 44, 221–227 (2017).
550. Gopalakrishnan, V. et al. Gut microbiome modulates response to anti-PD-1 immunotherapy in melanoma patient Science 359,97-103(2018).
51. MK Keleş, Tehnički vjesnik, Breast Cancer Prediction and Detection Using Data Mining Classification Algorithms, 2019, Sarıçam Adana, Turkey