Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Convergence Study on Research Topics for Thyroid Cancer in Korea

국내 갑상선암 논문 토픽에 대한 융합연구

  • Yang, Ji-Yeon (Dept. of Applied Mathematics, Kumoh National Institute of Technology)
  • 양지연 (금오공과대학교 응용수학과)
  • Received : 2018.12.26
  • Accepted : 2019.02.20
  • Published : 2019.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study was to perform a convergence study for the investigation of the trend of research topics related to thyroid cancer in Korea. We collected related research papers from DBpia and employed LDA-based topic model. In result, we identified four research topics, each of which concerns "Surgery", "Disease aggressiveness", "Survival analysis", and "Well-being of patients". With multinomial logistic regression, we found significant time trend, where "Surgery"-related topic was popular before 2000, topics regarding "Disease aggressiveness" and "Survival analysis" were frequently addressed in the 2000s, and "Survival analysis" and especially "Well-being of patients" have been pursued since 2010. The findings would serve as a reference guide for research directions. Future work may examine whether the recent change in research topics is observed in other diseases.

본 연구는 통계적인 기법을 융합 활용하여 국내 갑상선암과 관련된 연구 토픽의 동향 및 변화 추세를 알아보기 위함이다. DBpia에 등록되어 있는 갑상선암 관련 논문을 대상으로 LDA(latent Dirichlet allocation) 기반의 토픽 모형을 적용한 결과, 4개의 연구 토픽을 도출하였으며 각 토픽은 "Surgery", "Disease aggressiveness", "Survival analysis", "Well-being of patients"에 관한 내용으로 확인되었다. 다범주 로짓모형을 이용하여 연구 토픽의 시대적 추이를 확인한 결과, 2000년 이전에는 "Surgery", 2000년대에는 "Disease aggressiveness"와 "Survival analysis", 2010년 이후에는 "Survival analysis"와 특히 "Well-being of patients"에 관한 연구가 많이 이루어졌음을 확인하였다. 이는 향후 갑상선암 연구의 방향 모색에 필요한 기초자료로 활용될 수 있을 것이며, 최근 환자의 복지로 크게 전환된 연구 토픽의 변화가 다른 질병에서도 관찰되는지 추후 검토할 필요가 있다.

Keywords

OHHGBW_2019_v10n2_75_f0001.png 이미지

Fig. 1. Data acquisition and data preprocessing

OHHGBW_2019_v10n2_75_f0002.png 이미지

Fig. 2. Number of topics indicated by four metrics. The metrics were standardized to range between 0 and 1.

OHHGBW_2019_v10n2_75_f0003.png 이미지

Fig. 3. Number of papers in each topic

OHHGBW_2019_v10n2_75_f0004.png 이미지

Fig. 4. The 95% confidence intervals for topic probability at each time period

Table 1. Topics and the top 10 words in each discovered by LDA analysis of abstracts

OHHGBW_2019_v10n2_75_t0001.png 이미지

Table 2. Results of multinomial logistic regression. The reference group is Topic 1(Surgery).

OHHGBW_2019_v10n2_75_t0002.png 이미지

Table 3. Main terminologies in titles and keywords for each topic

OHHGBW_2019_v10n2_75_t0003.png 이미지

References

  1. H. G. Welch & C. B. William. (2010). Overdiagnosis in cancer. Journal of the National Cancer Institute, 102(9), 605-613. DOI : https://doi.org/10.1093/jnci/djq099
  2. H. S. Ahn & H. G. Welch. (2015). South Korea's thyroid-cancer "epidemic"-turning the tide. New England Journal of Medicine, 373(24), 2389-2390. DOI : 10.1056/NEJMc1507622
  3. S. A. Choi, J. H. Lee, D. K. Min, & C. Lee. (2015). Association between thyroid cancer incidence and health indicators in OECD 34 countries. Korean Journal of Family Practice, 5(3, suppl. 2), 714-720. http://www.kjfp.or.kr/journal/view.html?uid=354&vmd=Full
  4. J. H. Chung. (2018). Prevalence of thyroid nodules detected by ultrasonography in adults for health check-up and analysis of fine needle aspiration cytology. Journal of Korean Endocrine Society, 23(6), 391-394. DOI : https://doi.org/10.3803/jkes.2008.23.6.391
  5. S. Ezzat, D. A. Sarti, D. R. Cain, & G. D. Braunstein. (1994). Thyroid incidentalomas: prevalence by palpation and ultrasonography. Archives of internal medicine, 154(16), 1838-1840. DOI : 10.1001/archinte.1994.00420160075010
  6. J. P. Brito, H. J. Kim, S. J. Han, Y. S. Lee, & H. S. Ahn. (2016). Geographic distribution and evolution of thyroid cancer epidemic in South Korea. Thyroid, 26(6), 864-865. DOI : https://doi.org/10.1089/thy.2016.0057
  7. J. H. Chung. (2014). A Refutation against Unfounded Reports on Thyroid Cancer, International Journal of Thyroidology, 7(1), 1-6. DOI : http://dx.doi.org/10.11106/jkta.2014.7.1.1
  8. H. S. Ahn. (2017). Overdiagnosis in health care: impact of cancer screening. Journal of the Korean Medical Association, 60(4), 323-329. DOI : https://doi.org/10.5124/jkma.2017.60.4.323
  9. K. H. Yi, Y. J. Park, S. S. Koong, J. H. Kim, D. G. Na, J. S. Ryu, S. Y. Park, C. H. Baek, Y. K. Shong, & Y. D. Lee. (2011). Revised Korean thyroid association management guidelines for patients with thyroid nodules and thyroid cancer. Journal of the Korean Society of Radiology, 64(4), 389-416. DOI : https://doi.org/10.3348/jksr.2011.64.4.389
  10. D. M. Blei, A. Y. Ng, & M. I. Jordan. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan), 993-1022. DOI : 10.1162/jmlr.2003.3.4-5.993
  11. C. H. Papadimitriou, P. Raghavan, H. Tamaki, & S. Vempala. (2000). Latent semantic indexing: A probabilistic analysis. Journal of Computer and System Sciences, 61(2), 217-235. DOI : https://doi.org/10.1006/jcss.2000.1711
  12. S. Hwang & D. R. Hwang. (2018). A Study on the Research Trends in Arts Management in Korea using Topic Modeling and Semantic Network Analysis. Korean association of arts management, 47, 5-29. http://www.dbpia.co.kr/Journal/PDFViewNew?id=NODE07523972&prevPathCode= https://doi.org/10.52564/JAMP.2018.47.5
  13. J. E. Yoon & C. J. Suh. (2018). Research Trend Analysis on Smart healthcare by using Topic Modeling and Ego Network Analysis. Journal of Digital Contents Society, 19(5), 981-993. DOI : http://dx.doi.org/10.9728/dcs.2018.19.5.981
  14. N. Jang & M. J. Kim. (2017). Research Trend Analysis in Fashion Design Studies in Korea using Topic Modeling. Journal of Digital Convergence, 15(6), 415-423. DOI : http://doi.org/10.14400/JDC.2017.15.6.415
  15. K. H. Choi & J. H. Park. (2015). The Analysis of Public Awareness about Literary Therapy by Utilizing Big Data Analysis-The aspects of convergence literature and statistics. Journal of Digital Convergence, 13(4), 395-404. DOI : http://dx.doi.org/10.14400/JDC.2015.13.4.395
  16. N. H. Jo & E. Y. Na. (2017). Analysis of Domestic Research on Depression and Stress : Focused on the Treatment and Subjects. Journal of Convergence for Information Technology, 7(6), 53-59. DOI : doi.org/10.22156/CS4SMB.2017.7.6.053
  17. S. H. Choi. (2016). A Study on Smart Campus Information Services. Journal of Convergence for Information Technology, 6(3), 79-83. DOI : dx.doi.org/10.22156/CS4SMB.2016.6.3.079
  18. T. G. Lee, S. M. Heo, S. H. Shin & J. Y. Yang. (2018). Trend Analysis of Thyroid Cancer Research in Korea with Text Mining Techniques. Journal of The Korea Society of Computer and Information, 23(12), 153-161. DOI : https://doi.org/10.9708/jksci.2018.23.12.153
  19. T. L. Griffiths & M. Steyvers. (2004). Finding scientific topics. Proceedings of the National academy of Sciences, 101(suppl 1), 5228-5235. DOI : https://doi.org/10.1073/pnas.0307752101
  20. J. Cao, T. Xia, J. Li, Y. Zhang, & S. Tang. (2009). A density-based method for adaptive lda model selection. Neurocomputing, 72(7), 1775-1781. DOI : https://doi.org/10.1016/j.neucom.2008.06.011
  21. R. Arun, V. Suresh, C. V. Madhavan, & M. N. Murthy. (2010). On finding the natural number of topics with latent dirichlet allocation: Some observations. Pacific-Asia Conference on Knowledge Discovery and Data Mining, Part I, LNAI(6118), 391-402. DOI : doi.org/10.1007/978-3-642-13657-3_43
  22. R. Deveaud, E. SanJuan, & P. Bellot. (2014). Accurate and effective latent concept modeling for ad hoc information retrieval. Document numerique, 17(1), 61-84. DOI : https://doi.org/10.3166/DN.17.1.61-84