Hanyang Med Rev.  2017 Nov;37(2):86-92. 10.7599/hmr.2017.37.2.86.

Status and Direction of Healthcare Data in Korea for Artificial Intelligence

• Park YR
• Shin SY

• KMID: 2424833
• DOI: http://doi.org/10.7599/hmr.2017.37.2.86

Abstract

Recent rapid advances in artificial intelligence (AI), especially in deep learning methods, have produced meaningful results in many areas. However, to achieve meaningful results for healthcare through AI, it is important to understand the meaning and characteristics of data in that area. For medical AI, a simple approach that accumulates massive amounts of data based on existing big data concepts cannot provide meaningful results in the healthcare field. We need well-curated data as opposed to a simple aggregation of data. The purpose of this study is to present the types and characteristics of healthcare data and future directions for the successful combination of AI and medical care.

Keyword

AI; Machine Learning; Healthcare Data; Smart Data

MeSH Terms

Artificial Intelligence*
Delivery of Health Care*
Korea*
Learning
Machine Learning

Figure

• 

  Fig. 1 Healthcare data and human health Genomic data could be regarded as a blueprint, and SDOH can change the blueprint as we live. These two types of health data can be the input of a health condition. Clinical data and PGHD are the outcomes of a health condition.

• 

  Fig. 2 Most useful sources of healthcare data today and in 5 years. Modified from the figure on page 1 of [9] by selecting the healthcare data types matched in this paper.

Reference

1. Ravi D, Wong C, Deligianni F, Berthelot M, Andreu-Perez J, Lo B, et al. Deep Learning for Health Informatics. IEEE J Biomed Health Inform. 2017; 21(1):4–21.

2. Miotto R, Li L, Kidd BA, Dudley JT. Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records. Sci Rep. 2016; 6:26094.

3. Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA. 2016; 316(22):2402.

4. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542(7639):115–118.

5. Goodfellow I, Bengio Y, Courville A. Deep learning. MIT Press;2017. p. 168–177.

6. Gold M, McLaughlin C. Assessing HITECH Implementation and Lessons: 5 Years Later. Milbank Q. 2016; 94(3):654–687.

7. Kim YG, Jung K, Park YT, Shin D, Cho SY, Yoon D, et al. Rate of electronic health record adoption in South Korea: A nation-wide survey. Int J Med Inform. 2017; 101:100–107.

8. Weber G, Mandl K, Kohane I. Finding the Missing Link for Big Biomedical Data. JAMA. 2014; 311:2479–2480.

9. Compton-Phillips A. Care Redesign Survey: What Data Can Really Do for Health Care [Internet]. New England Journal of Medicine;2017. cited 2017 July 13. Available from: http://catalyst.nejm.org/effectiveness-healthcaredata-survey-analysis/.

10. National Center for Biotechnology Information. All Resources - Site Guide - NCBI [Internet]. cited 2017 July 8. Available from: https://www.ncbi.nlm.nih.gov/guide/all/.

11. European Bioinformatics Institute. Bioinformatics services [Internet]. cited 2017 July 8. Available from: https://www.ebi.ac.uk/service.

12. HealthIT.gov. Patient-Generated Health Data [Internet]. cited 2017 July 8. Available from: https://www.healthit.gov/policy-researchersimplementers/patient-generated-health-data.

13. World Health Organization. Social Determinants of Health [Internet]. cited 2017 July 8. Available from: http://www.who.int/social_determinants/en/.

14. Kho AN, Pacheco JA, Peissig PL, Rasmussen L, Newton KM, Weston N, et al. Electronic Medical Records for Genetic Research: Results of the eMERGE Consortium. Sci Transl Med. 2011; 3(79):79re1.

15. Yun JH, Ahn SJ, Kim Y. Development of clinical contents model markup language for electronic health records. Healthc Inform Res. 2012; 18(3):171–177.

16. Martínez-Costa C, Menárguez-Tortosa M, Fernández-Breis JT. Towards ISO 13606 and openEHR archetype-based semantic interoperability. Stud Health Technol Inform. 2009; 150:260–264.

17. The CEN/ISO EN13606 standard [Internet]. cited 2017 July 7. Available from: http://www.en13606.org/the-ceniso-en13606-standard 2017].

18. Goossen W, Goossen-Baremans A, van der Zel M. Detailed Clinical Models: A Review. Healthc Inform Res. 2010; 16(4):201.

19. OpenCIMI. Mission and Goals | www.opencimi.org [Internet]. cited 2017 July 7. Available from: https://www.opencimi.org/.

20. Pons E, Braun LMM, Hunink MGM, Kors JA. Natural Language Processing in Radiology: A Systematic Review. Radiology. 2016; 279(2):329–343.

21. Demner-Fushman D, Elhadad N. Aspiring to Unintended Consequences of Natural Language Processing: A Review of Recent Developments in Clinical and Consumer-Generated Text Processing. Yearb Med Inform. 2016; (1):224–233.

22. Névéol A, Zweigenbaum P. Clinical Natural Language Processing in 2015: Leveraging the Variety of Texts of Clinical Interest. Yearb Med Inform. 2016; (1):234–239.

23. Shin SY, Park YR, Shin Y, Choi HJ, Park J, Lyu Y, et al. A De-identification method for bilingual clinical texts of various note types. J Korean Med Sci. 2015; 30(1):7–15.

24. Cruz-Roa A, Gilmore H, Basavanhally A, Feldman M, Ganesan S, Shih NNC, et al. Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent. Sci Rep. 2017; 7:46450.

25. Madabhushi A, Lee G. Image analysis and machine learning in digital pathology: Challenges and opportunities. Med Image Anal. 2016; 33:170–175.

26. Society for Participatory Medicine. Imagine someone had been managing your data, and then you looked [Internet]. cited 2017 July 13. Available from: https://participatorymedicine.org/epatients/2009/04/imagine-ifsomeone-had-been-managing-your-data-and-then-you-looked.html.

27. HL7. Index - FHIR v3.0.1 [Internet]. cited 2017 July 13. Available from: https://www.hl7.org/fhir/.

28. Evans JP, Powell BC, Berg JS, T M, BK R. Finding the Rare Pathogenic Variants in a Human Genome. JAMA. 2017; 317(18):1904.

29. Good BM, Ainscough BJ, McMichael JF, Su AI, Griffith OL. Organizing knowledge to enable personalization of medicine in cancer. Genome Biol. 2014; 15(8):438.

30. US FDA. PrecisionFDA [Internet]. cited 2017 July 13. Available from: https://precision.fda.gov/.

31. AACR Project GENIE Consortium. AACR Project GENIE: Powering Precision Medicine through an International Consortium. Cancer Discov. 2017; DOI: 10.1158/2159-8290.CD-17-0151. Forthcoming.

32. International Organization for Standardization. ISO/TS 20428:2017 - Health informatics -- Data elements and their metadata for describing structured clinical genomic sequence information in electronic health records [Internet]. cited 2017 July 8. Available from: https://www.iso.org/standard/67981.html.

33. US FDA. Use of Real-World Evidence to Support Regulatory Decision-Making [Internet]. cited 2017 July 18. Available from: https://www.fda.gov/downloads/medicaldevices/deviceregulationandguidance/guidancedocuments/ucm513027.pdf.

34. Harvard Business School. Evaluating New Drugs with Wearable Technology – Technology and Operations Management [Internet]. cited 2017 July 8. Available from: https://rctom.hbs.org/submission/evaluating-new-drugswith-wearable-technology/.

35. OPEN CONNECTIVITY FOUNDATION (OCF) [Internet]. cited 2017 July 11. Available from: https://openconnectivity.org/.

36. International Electrotechnical Commission. IEC - TC 124 [Internet]. cited 2017 July 11. Available from: http://www.iec.ch/dyn/www/f?p=103:7:0::::FSP_ORG_ID,FSP_LANG_ID:20537,25.

37. Andermann A. CLEAR Collaboration. Taking action on the social determinants of health in clinical practice: a framework for health professionals. CMAJ. 2016; 188(17-18):E474–E483.

38. KDDNugget. Datasets Over Algorithms [Internet]. cited 2017 July 11. Available from: http://www.kdnuggets.com/2016/05/datasets-overalgorithms.html.

39. Observational Health Data Sciences and Informatics. Common Data Model Documentation [Internet]. cited 2017 July 11. Available from: http://www.ohdsi.org/web/wiki/doku.php?id=documentation:cdm#common_data_model.

40. The National Patient-Centered Clinical Research Network. PCORnet Common Data Model (CDM) - PCORnet [Internet]. cited 2017 July 11. Available from: http://www.pcornet.org/pcornet-common-data-model/.

41. Sentinel. Distributed Database and Common Data Model | Sentinel System [Internet]. cited 2017 July 11. Available from: https://www.sentinelinitiative.org/sentinel/data/distributed-database-common-datamodel.

42. Erlich Y, Narayanan A. Routes for breaching and protecting genetic privacy. Nat Rev Genet. 2014; 15(6):409–421.