Endocrinol Metab.  2019 Dec;34(4):349-354. 10.3803/EnM.2019.34.4.349.

Medical Big Data Is Not Yet Available: Why We Need Realism Rather than Exaggeration

• Kim HS
• Kim DJ
• Yoon KH

• KMID: 2466253
• DOI: http://doi.org/10.3803/EnM.2019.34.4.349

Abstract

Most people are now familiar with the concepts of big data, deep learning, machine learning, and artificial intelligence (AI) and have a vague expectation that AI using medical big data can be used to improve the quality of medical care. However, the expectation that big data could change the field of medicine is inconsistent with the current reality. The clinical meaningfulness of the results of research using medical big data needs to be examined. Medical staff needs to be clear about the purpose of AI that utilizes medical big data and to focus on the quality of this data, rather than the quantity. Further, medical professionals should understand the necessary precautions for using medical big data, as well as its advantages. No doubt that someday, medical big data will play an essential role in healthcare; however, at present, it seems too early to actively use it in clinical practice. The field continues to work toward developing medical big data and making it appropriate for healthcare. Researchers should continue to engage in empirical research to ensure that appropriate processes are in place to empirically evaluate the results of its use in healthcare.

Keyword

Artificial intelligence; Big data; Data science; Medical informatics; Deep learning; Machine learning

MeSH Terms

Artificial Intelligence
Delivery of Health Care
Empirical Research
Humans
Learning
Machine Learning
Medical Informatics
Medical Staff

Figure

• 

  Fig. 1 Example of the conceptual [23] and operational definitions of diabetes mellitus. HbA1c, hemoglobin A1c; OGTT, oral glucose tolerance test; ICD-10, International Classification of Diseases 10th Revision; OHA, oral hypoglycemic agents.

• 

  Fig. 2 Examples of real cases requiring data quality management. (A) Various written data. Even though the laboratory test result is “<3,” it is also written as “1.” The physicians' role is defining and classifying data, and staff who are most familiar with the data should do so. (B) Example of incorrectly entered data. AST, aspartate aminotransferase; GOT, glutamate oxaloacetate transaminase; ALT, aspartate aminotransferase; GPT, glutamate pyruvate transaminase; HBsAg, hepatitis B surface antigen; HBsAb, hepatitis B surface antibody; HDL, high-density lipoprotein; LDL, low-density lipoprotein.

Reference

1. Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017; 69S:S36–S40.

2. Miller DD, Brown EW. Artificial intelligence in medical practice: the question to the answer? Am J Med. 2018; 131:129–133.

3. Kantarjian H, Yu PP. Artificial intelligence, big data, and cancer. JAMA Oncol. 2015; 1:573–574.

4. Kim HS, Kim JH. Proceed with caution when using real world data and real world evidence. J Korean Med Sci. 2019; 34:e28.

5. Kim HS, Lee S, Kim JH. Real-world evidence versus randomized controlled trial: clinical research based on electronic medical records. J Korean Med Sci. 2018; 33:e213.

6. Obermeyer Z, Emanuel EJ. Predicting the future: big data, machine learning, and clinical medicine. N Engl J Med. 2016; 375:1216–1219.

7. Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: review, opportunities and challenges. Brief Bioinform. 2018; 19:1236–1246.

8. 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; 21:4–21.

9. Sun C, Shrivastava A, Singh S, Gupta A. Revisiting unreasonable effectiveness of data in deep learning era. In : 2017 IEEE International Conference on Computer Vision (ICCV); 2017 Oct 22–29; Venice, IT. Piscataway, NJ: IEEE;1997. p. 843–852.

10. Rubin DB. Estimating causal effects from large data sets using propensity scores. Ann Intern Med. 1997; 127:757–763.

11. Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, et al. Scalable and accurate deep learning with electronic health records. NPJ Digit Med. 2018; 1:18.

12. Deo RC. Machine learning in medicine. Circulation. 2015; 132:1920–1930.

13. Bastanlar Y, Ozuysal M. Introduction to machine learning. Methods Mol Biol. 2014; 1107:105–128.

14. Williams H. Microsoft's teen chatbot has gone wild [Internet]. Surry Hills: Gizmodo;2016. cited 2019 Dec 9. Available from: https://www.gizmodo.com.au/2016/03/microsofts-teen-chatbot-has-gone-wild.

15. Levesque LE, Hanley JA, Kezouh A, Suissa S. Problem of immortal time bias in cohort studies: example using statins for preventing progression of diabetes. BMJ. 2010; 340:b5087.

16. Maugis PG. Big data uncertainties. J Forensic Leg Med. 2018; 57:7–11.

17. Lee J, Lee JS, Park SH, Shin SA, Kim K. Cohort profile: the National Health Insurance Service-National Sample Cohort (NHIS-NSC), South Korea. Int J Epidemiol. 2017; 46:e15.

18. Noh J. The diabetes epidemic in Korea. Endocrinol Metab (Seoul). 2016; 31:349–353.

19. Seo GH, Chung JH. Incidence and prevalence of overt hypothyroidism and causative diseases in Korea as determined using claims data provided by the Health Insurance Review and Assessment Service. Endocrinol Metab (Seoul). 2015; 30:288–296.

20. Lee YK, Yoon BH, Koo KH. Epidemiology of osteoporosis and osteoporotic fractures in South Korea. Endocrinol Metab (Seoul). 2013; 28:90–93.

21. American Diabetes Association. Diagnosis and classification of diabetes mellitus. Diabetes Care. 2004; 27:S5–S10.

22. Ko SH, Hur KY, Rhee SY, Kim NH, Moon MK, Park SO, et al. Antihyperglycemic agent therapy for adult patients with type 2 diabetes mellitus 2017: a position statement of the Korean Diabetes Association. Diabetes Metab J. 2017; 41:337–348.

23. International Expert Committee. International Expert Committee report on the role of the A1C assay in the diagnosis of diabetes. Diabetes Care. 2009; 32:1327–1334.

24. Zhang Z. Missing data exploration: highlighting graphical presentation of missing pattern. Ann Transl Med. 2015; 3:356.

25. Kim TM, Kim H, Jeong YJ, Baik SJ, Yang SJ, Lee SH, et al. The differences in the incidence of diabetes mellitus and prediabetes according to the type of HMG-CoA reductase inhibitors prescribed in Korean patients. Pharmacoepidemiol Drug Saf. 2017; 26:1156–1163.

26. Chen PH, Loehfelm TW, Kamer AP, Lemmon AB, Cook TS, Kohli MD. Toward data-driven radiology education-early experience building multi-institutional academic trainee interpretation log database (MATILDA). J Digit Imaging. 2016; 29:638–644.

27. Matney SA, Settergren TT, Carrington JM, Richesson RL, Sheide A, Westra BL. Standardizing physiologic assessment data to enable big data analytics. West J Nurs Res. 2017; 39:63–77.

28. Kalra D. Electronic health record standards. Yearb Med Inform. 2006; 136–144.

29. Lee CH, Lim H, Kim Y, Park AH, Park EC, Kang JG. Analysis of appropriate outpatient consultation time for clinical departments. Health Policy Manag. 2014; 24:254–260.

30. Kim H, Choi J, Jang I, Quach J, Ohno-Machado L. Feasibility of representing data from published nursing research using the OMOP common data model. AMIA Annu Symp Proc. 2017; 2016:715–723.

31. Ceusters W, Blaisure J. A realism-based view on counts in OMOP’s common data model. Stud Health Technol Inform. 2017; 237:55–62.

32. Kimura E, Suzuki H. Development of a common data model facilitating clinical decision-making and analyses. Stud Health Technol Inform. 2019; 264:1514–1515.

33. Park RW. The distributed research network, observational health data sciences and informatics, and the South Korean research network. Korean J Med. 2019; 94:309–314.

34. FitzHenry F, Resnic FS, Robbins SL, Denton J, Nookala L, Meeker D, et al. Creating a common data model for comparative effectiveness with the observational medical outcomes partnership. Appl Clin Inform. 2015; 6:536–547.

35. Kim HS. Decision-making in artificial intelligence: is it always correct? J Korean Med Sci. 2020; In Press.