DOI QR코드

DOI QR Code

Medical Data Based Clinical Pathway Analysis and Automatic Ganeration System

임상데이터기반 표준진료지침 자동 생성 시스템 분석 및 연구

  • Park, Hanna (College of Medicine Yonsei University Department of Plastic Surgery) ;
  • Bae, In Ho ;
  • Kim, Yong Oock (College of Medicine Yonsei University Department of Plastic Surgery)
  • Received : 2014.02.28
  • Accepted : 2014.06.12
  • Published : 2014.06.30

Abstract

In general, all physicians have some standardized diagnosis and treatment methods. However, there are differences in the precise order and examination depending on the hospital size, system, medical equipment, etc. To reduce this difference, the interest about standardized guidelines recently increased and a variety of research is being conducted. The uniform guideline cannot reflect the differences of each situation and environment to meet the hospitals. Therefore, standardized medical guidelines(=clinical pathway) should provide customized guidelines based on the relevant medical data to ensure the quality of the medical service and the doctor's autonomy. In this paper, we will analyze medical data made by two thyroid specialists in the same hospitals. Moreover, this paper mentions the implement of automatic generating clinical pathway system which consider its real hospital situation and result.

일반적으로 모든 전문분야 의사들은 어느 정도 표준화된 진단, 치료 방식을 취하고 있다. 그러나 세부적인 처방 및 검사, 입원일수 등은 병원 규모 및 시스템, 의료 장비 구축정도에 따라 차이가 발생할 수 있다. 이러한 차이를 줄이기 위해 최근 진료지침의 표준화에 대한 관심이 높아지면서 다양한 연구가 진행되고 있다. 표준화된 진료지침은 의료의 질을 보장하고 의사의 자율성을 보장하기 위해 병원규모 및 구축된 시스템 등에 상관없이 똑같은 진료지침을 제공하는 것이 아니라 각 병원의 상황과 환경에 맞도록 임상데이터를 기반으로 진단 및 처치, 검사 등을 제공할 수 있어야 한다. 따라서 본 논문에서는 병원 내 같은 과의 두 전문의의 임상데이터를 분석하고 이를 기반으로 해당 질병 및 병원에 맞춘 표준 진료지침을 자동으로 생성할 수 있는 시스템을 연구 및 구현하여 적용 가능한 표준 진료지침을 제시하고자 한다.

Keywords

References

  1. S. Kim, "Editor's postscript: Medical-Bio IT Convergence," J. KICS, vol. 38, no. 7, pp. 621-662, Jul. 2013.
  2. E. Shin, "Trends in the development of and emerging tasks of clinical practice guidelines in Korea," J. Korean Med. Assoc., vol. 55, no. 4, pp. 371-378, Apr. 2012. https://doi.org/10.5124/jkma.2012.55.4.371
  3. N. Kim, S. Kim, and E. Park, "Promoting the Quality of Medicine: Based on Clinical Practice Guidelines," KIHASA Research report, May 2004.
  4. R. E. Nathan, H. Judith, B. Richard, K. Steve, and P. C. Christopher, "Critical Pathways: A Review," J. American Heart Association, 101, pp. 461-465, 2000.
  5. I. Bae, J. Kim, S. Choi, and Y. Kim, "An Association Rule Mining Approach to Extract Clinical Pathways from EMR," in Proc. KPIS, vol. 12, no. 1, pp. 577-580, May 2005.
  6. I. Bae, H. Park, E. Kang, and Y. Kim, "A Method about Generation of clinical data structure and Document and Its Management for Efficient Medical Research in the Electronic Medical Record," in Proc. KOSMI Conf. Daegu, Korea, Oct. 2012.
  7. T. Shusaku, I. Haruko, and H. Shoji, "Construction and Maintenance of Clinical Pathways using Data mining methods," in Proc. MIXHS, pp. 47-52, 2012
  8. I. Choe and E. Chung, "Predictive Bayesian Network Model Using Electronic Patient Records for Prevention of Hospital-Acquired Pressure Ulcers," J. Korean Acad. Nurs., vol. 41, no. 3, pp. 423-431, Jun. 2011. https://doi.org/10.4040/jkan.2011.41.3.423
  9. D. D. Lee and H. S. Seung, "Learning the parts of objects by non-negative matrix factorization," J. Nature, vol. 401, pp. 788-791, Oct. 1999. https://doi.org/10.1038/44565
  10. P. Hoyer, "Non-negative matrix factorization with sparseness constraints," J. Machine Learning Research, vol. 5, pp. 1457-1469, 2004.
  11. P. Paatero and U. Tapper, "Positive matrix factorization: A non‐negative factor model with optimal utilization of error estimates of data values," J. Environmetrics, vol. 5, no. 2, pp. 111-126, Jun. 1994. https://doi.org/10.1002/env.3170050203
  12. Z. Hu, J.S. Li, T.S. Zhou, H.Y. Yu, M. Suzuki, and K. Araki, "Ontology-based clinical pathways with semantic rules," J. Med. Syst., vol. 36, no. 4, pp. 2203-2212, Aug. 2012. https://doi.org/10.1007/s10916-011-9687-0