Korean Medical Education Review (의학교육논단)

Yonsei university college of medicine (연세대학교 의과대학)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning Method in Medical Education: Focusing on Research Case of Press Frame on Asbestos

의학교육에서 기계학습방법 교육: 석면 언론 프레임 연구사례를 중심으로

  • Kim, Junhewk (Department of Medical Ethics and Health Policy, University of Pennsylvania Perelman School of Medicine) ;
  • Heo, So-Yun (Department of Medical Humanities, Pusan National University School of Dentistry) ;
  • Kang, Shin-Ik (Department of Medical Humanities, Pusan National University School of Dentistry) ;
  • Kim, Geon-Il (Department of Radiology, Pusan National University School of Medicine) ;
  • Kang, Dongmug (Korea Research Center for Asbestos-Related Diseases)
  • 김준혁 (펜실베이니아 대학교 의료윤리 및 건강정책교실) ;
  • 허소윤 (부산대학교 치의학전문대학원 의료인문학교실) ;
  • 강신익 (부산대학교 치의학전문대학원 의료인문학교실) ;
  • 김건일 (부산대학교 의학전문대학원 영상의학교실) ;
  • 강동묵 (부산대학교 석면환경보건센터)
  • Received : 2016.12.16
  • Accepted : 2017.09.04
  • Published : 2017.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

There is a more urgent call for educational methods of machine learning in medical education, and therefore, new approaches of teaching and researching machine learning in medicine are needed. This paper presents a case using machine learning through text analysis. Topic modeling of news articles with the keyword 'asbestos' were examined. Two hypotheses were tested using this method, and the process of machine learning of texts is illustrated through this example. Using an automated text analysis method, all the news articles published from January 1, 1990 to November 15, 2016 in South Korea which included 'asbestos' in the title and the body were collected by web scraping. Differences in topics were analyzed by structured topic modelling (STM) and compared by press companies and periods. More articles were found in liberal media outlets. Differences were found in the number and types of topics in the articles according to the partisanship and period. STM showed that the conservative press views asbestos as a personal problem, while the progressive press views asbestos as a social problem. A divergence in the perspective for emphasizing the issues of asbestos between the conservative press and progressive press was also found. Social perspective influences the main topics of news stories. Thus, the patients' uneasiness and pain are not presented by both sources of media. In addition, topics differ between news media sources based on partisanship, and therefore cause divergence in readers' framing. The method of text analysis and its strengths and weaknesses are explained, and an application for the teaching and researching of machine learning in medical education using the methodology of text analysis is considered. An educational method of machine learning in medical education is urgent for future generations.

Keywords

References

  1. Nichols T. The death of expertise: the campaign against established knowledge and why it matters. New York (NY): Oxford University Press; 2017.
  2. Susskind RE, Susskind D. The future of the professions: how technology will transform the work of human experts. Oxford: Oxford University Press; 2017.
  3. Choi YS. Artificial intelligence: will it replace human medical doctors? Korean Med Educ Rev. 2016;18(2):47-50. https://doi.org/10.17496/kmer.2016.18.2.47
  4. Ellaway RH, Pusic MV, Galbraith RM, Cameron T. Developing the role of big data and analytics in health professional education. Med Teach. 2014;36(3):216-22. https://doi.org/10.3109/0142159X.2014.874553
  5. Tighe PJ, Harle CA, Hurley RW, Aytug H, Boezaart AP, Fillingim RB. Teaching a machine to feel postoperative pain: combining highdimensional clinical data with machine learning algorithms to forecast acute postoperative pain. Pain Med. 2015;16(7):1386-401. https://doi.org/10.1111/pme.12713
  6. Howe D, Costanzo M, Fey P, Gojobori T, Hannick L, Hide W, et al. Big data: the future of biocuration. Nature. 2008;455(7209):47-50. https://doi.org/10.1038/455047a
  7. Deo RC. Machine learning in medicine. Circulation. 2015;132(20):1920-30. https://doi.org/10.1161/CIRCULATIONAHA.115.001593
  8. Lee M. Big data and utilization of public data. Internet Inf Secur. 2011;2(2):47-64.
  9. Kang B, Song M, Jho W. A study on opinion mining of newspaper texts based on topic modeling. J Korean Soc Libr Inf Sci. 2013;47(4):315-34. https://doi.org/10.4275/KSLIS.2013.47.4.315
  10. Park JH, Park E, Jo DJ. Automated text analysis of North Korean new year addresses, 1946-2015. Korean Polit Sci Assoc. 2015;49(2):27-61. https://doi.org/10.18854/kpsr.2015.49.2.002
  11. Jockers ML. Text analysis with R for students of literatures. New York (NY): Springer; 2014.
  12. An JJ. Asbestos, a silent killer. Paju: Hanul; 2008.
  13. Park EK. Environmental molecular epidemiological mechanism studies on asbestos-related diseases. Environ Health Toxic. 2012;10:87-9.
  14. Jung JS, Jung HS, Lee JY, Lee WS, Kwon OS, Kim SM. A study of asbestos characteristics and correlation of environmental factors in naturally occurring asbestos areas. Korean Soc Living Environ Syst. 2015;22(5):639-46. https://doi.org/10.21086/ksles.2015.10.22.5.639
  15. Ham T, Jeong M. A review of legal issues over relief of damages resulting from asbestos. Environ Law Policy. 2011;6:179-216. https://doi.org/10.18215/envlp.6..201105.179
  16. Coleman S. New mediation and direct representation: reconceptualizing representation in the digital age. New Media Soc. 2005;7(2):177-98. https://doi.org/10.1177/1461444805050745
  17. Wilkerson JD, Casas A. Large-scale computerized text analysis in political science: opportunities and challenges. Annu Rev Polit Sci. 2017;20:529-44. https://doi.org/10.1146/annurev-polisci-052615-025542
  18. Jacobi C, van Atteveldt W, Welbers K. Quantitative analysis of large amounts of journalistic texts using topic modelling. Digit Journal. 2016;4(1):89-106. https://doi.org/10.1080/21670811.2015.1093271
  19. Lakoff G. Don't think of an elephant!: know your values and frame the debate. White River Junction (VT): Chelsea Green Publishing; 2014.
  20. Lakoff G. Moral politics: how liberals and conservatives think. 2nd ed. Chicago (IL): University of Chicago Press; 2002.
  21. Scheufele DA. Framing as a theory of media effects. J Commun. 1999;49(1):103-22. https://doi.org/10.1111/j.1460-2466.1999.tb02784.x
  22. Kim SJ, Cheong YG. Non-reporting, media ethics and ideological conflicts in South Korea: focus on media coverage relating to surveillance of civilians by the National Intelligence Service and the Defense Security Command. Korean J Commun Inf. 2011;53:5-28.
  23. Castillo C. Effective web crawling. ACM SIGIR Forum. 2005;39(1):55-6. https://doi.org/10.1145/1067268.1067287
  24. Myers D, McGuffee JW. Choosing Scrapy. J Comput Sci Coll. 2015;31(1):83-9.
  25. Park EL, Cho S. KoNLPy: Korean natural language processing in Python. Proceedings of the 26th Annual Conference on Human & Cognitive Language Technology; 2014 Oct 10; Chuncheon, Korea. Seoul: Korean Society of Speech Sciences; 2014.
  26. Jacobi C, van Atteveldt W, Welbers K. Quantitative analysis of large amounts of journalistic texts using topic modelling. Digit Journal. 2016;4(1):89-106. https://doi.org/10.1080/21670811.2015.1093271
  27. Chang J, Gerrish S, Wang C, Boyd-Graber JL, Blei DM. Reading tea leaves: how humans interpret topic models. In: Bengio Y, editor. Advances in neural information processing systems 22. New York (NY): Curran Associates Inc.; 2009. p. 288-96.
  28. Zhao W, Chen JJ, Perkins R, Liu Z, Ge W, Ding Y, et al. A heuristic approach to determine an appropriate number of topics in topic modeling. BMC Bioinformatics. 2015;16 Suppl 13:S8.
  29. Blei DM. Probabilistic topic models. Commun ACM. 2012;55(4):77-84. https://doi.org/10.1145/2133806.2133826
  30. Ahmed A, Xing EP. Staying informed: supervised and semi-supervised multi-view topical analysis of ideological perspective. In: Li H, Marquez L, editors. Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing; 2010 Oct 9-11; Cambridge, USA. Stroudsburg (PA): Association for Computational Linguistics; 2010. p. 1140-50.
  31. Blei DM, Lafferty JD. Dynamic topic models. In: Cohen W, Moore A, editors. Proceedings of the 23rd International Conference on Machine Learning; 2006 Jun 25-29; Pittsburgh, USA. New York (NY): Association of Computing Machinery; 2006. p. 113-20.
  32. Rosen-Zvi M, Griffiths T, Steyvers M, Smyth P. The author-topic model for authors and documents. In: Chickering M, Halpern J, editors. Proceedings of the 20th Conference on Uncertainty in Artificial Intelligence; 2004 Jul 7-11; Banff, Canada. Arlington (TX): Association for Uncertainty in Artificial Intelligence; 2004. p. 487-94.
  33. Roberts ME, Stewart BM, Tingley D, Airoldi EM. The structural topic model and applied social science. Proceedings of the advances in Neural Information Processing Systems workshop on topic models: computation, application, and evaluation; 2013 Dec 10; Lake Tahoe, USA. La Jolla (CA): Neural Information Processing System Foundation; 2013.
  34. R Development Core Team. R: a language and environment for statistical computing [Internet]. Vienna: R Foundation for Statistical Computing; 2008 [cited 2016 Oct 18]. Available from: http://www.R-project.org.
  35. Seward JB. Paradigm shift in medical data management: big data and small data. JACC Cardiovasc Imaging. 2017 Jan 12 [Epub]. https://doi.org/10.1016/j.jcmg.2016.10.013.
  36. Murdoch TB, Detsky AS. The inevitable application of big data to health care. JAMA. 2013;309(13):1351-2. https://doi.org/10.1001/jama.2013.393
  37. Lakoff G. The political mind: why you can't understand 21st-century politics with an 18th-century brain. New York (NY): Penguin Books; 2008.
  38. Lem SM. The argument presented by the conservative and progressive seen through controversy over the free elementary school meal project centering on the framing of the newspaper media. Korean Polit Sci Rev. 2011;45(2):251-79. https://doi.org/10.18854/kpsr.2011.45.2.011
  39. Foucault M. Power/knowledge: selected interviews and other writings 1972-1977. New York (NY): Pantheon; 1980.
  40. Feinberg M, Willer R. The moral roots of environmental attitudes. Psychol Sci. 2013;24(1):56-62. https://doi.org/10.1177/0956797612449177
  41. Walsko C, Ariceaga H, Seiden J. Red, white, and blue enough to be green: effects of moral framing on climate change attitudes and conservation behaviors. J Exp Soc Psychol. 2016;65:7-19. https://doi.org/10.1016/j.jesp.2016.02.005
  42. Chung J, Cho JJ. Use of qualitative research in the field of health. J Korean Acad Fam Med. 2008;29(8):553-62.
  43. Hong L, Davison BD. Empirical study of topic modeling in Twitter. Proceedings of the first workshop on social media analytics; 2010 Jul 25-28; Washington DC, USA. New York (NY): Association of Computing Machinery; 2010. p. 80-8.
  44. Rosenkranz SK, Wang S, Hu W. Motivating medical students to do research: a mixed methods study using Self-Determination Theory. BMC Med Educ. 2015;15:95. https://doi.org/10.1186/s12909-015-0379-1
  45. Obermeyer Z, Emanuel EJ. Predicting the future: big data, machine learning, and clinical medicine. N Engl J Med. 2016;375(13):1216-9. https://doi.org/10.1056/NEJMp1606181
  46. Kim J. Big data, health informatics, and the future of cardiovascular medicine. J Am Coll Cardiol. 2017;69(7):899-902. https://doi.org/10.1016/j.jacc.2017.01.006