Currently Viewing:
The American Journal of Managed Care December 2015
Interest in Mental Health Care Among Patients Making eVisits
Steven M. Albert, PhD; Yll Agimi, PhD; and G. Daniel Martich, MD
The Impact of Electronic Health Records and Teamwork on Diabetes Care Quality
Ilana Graetz, PhD; Jie Huang, PhD; Richard Brand, PhD; Stephen M. Shortell, PhD, MPH, MBA; Thomas G. Rundall, PhD; Jim Bellows, PhD; John Hsu, MD, MBA, MSCE; Marc Jaffe, MD; and Mary E. Reed, DrPH
Health IT-Assisted Population-Based Preventive Cancer Screening: A Cost Analysis
Douglas E. Levy, PhD; Vidit N. Munshi, MA; Jeffrey M. Ashburner, PhD, MPH; Adrian H. Zai, MD, PhD, MPH; Richard W. Grant, MD, MPH; and Steven J. Atlas, MD, MPH
A Health Systems Improvement Research Agenda for AJMC's Next Decade
Dennis P. Scanlon, PhD, Associate Editor, The American Journal of Managed Care
An Introduction to the Health IT Issue
Jeffrey S. McCullough, PhD, Assistant Professor, University of Minnesota School of Public Health; Guest Editor-in-Chief for the health IT issue of The American Journal of Managed Care
Preventing Patient Absenteeism: Validation of a Predictive Overbooking Model
Mark Reid, PhD; Samuel Cohen, MD; Hank Wang, MD, MSHS; Aung Kaung, MD; Anish Patel, MD; Vartan Tashjian, BS; Demetrius L. Williams, Jr, MPA; Bibiana Martinez, MPH; and Brennan M.R. Spiegel, MD, MSHS
EHR Adoption Among Ambulatory Care Teams
Philip Wesley Barker, MS; and Dawn Marie Heisey-Grove, MPH
Impact of a National Specialty E-Consultation Implementation Project on Access
Susan Kirsh, MD, MPH; Evan Carey, MS; David C. Aron, MD, MS; Omar Cardenas, BS; Glenn Graham, MD, PhD; Rajiv Jain, MD; David H. Au, MD; Chin-Lin Tseng, DrPH; Heather Franklin, MPH; and P. Michael Ho, MD, PhD
E-Consult Implementation: Lessons Learned Using Consolidated Framework for Implementation Research
Leah M. Haverhals, MA; George Sayre, PsyD; Christian D. Helfrich, PhD, MPH; Catherine Battaglia, PhD, RN; David Aron, MD, MS; Lauren D. Stevenson, PhD; Susan Kirsh, MD, MPH; P. Michael Ho, MD, MPH; and Julie Lowery, PhD
Patient-Initiated E-mails to Providers: Associations With Out-of-Pocket Visit Costs, and Impact on Care-Seeking and Health
Mary Reed, DrPH; Ilana Graetz, PhD; Nancy Gordon, ScD; and Vicki Fung, PhD
Currently Reading
Innovations in Chronic Care Delivery Using Data-Driven Clinical Pathways
Yiye Zhang, MS; and Rema Padman, PhD
Characteristics of Residential Care Communities That Use Electronic Health Records
Eunice Park-Lee, PhD; Vincent Rome, MPH; and Christine Caffrey, PhD
Using Aggregated Pharmacy Claims to Identify Primary Nonadherence
Dominique Comer, PharmD, MS; Joseph Couto, PharmD, MBA; Ruth Aguiar, BA; Pan Wu, PhD; and Daniel Elliott, MD, MSCE
Physician Attitudes on Ease of Use of EHR Functionalities Related to Meaningful Use
Michael F. Furukawa, PhD; Jennifer King, PhD; and Vaishali Patel, PhD, MPH

Innovations in Chronic Care Delivery Using Data-Driven Clinical Pathways

Yiye Zhang, MS; and Rema Padman, PhD
This paper demonstrates that data-driven clinical pathways can be developed using electronic health record data to facilitate innovations in practice-based care delivery for chronic disease management.
A crucial prerequisite for success in the application of advanced machine learning methods to healthcare delivery is data quality. It is not uncommon for computational scientists to spend significant effort in cleaning EHR data before analysis. In addition, even after months of processing, there are often still missing data and errors, some arising from the mismatch between actual work flows and process assumptions, subjecting the analytical results to bias. Such inefficiency can be minimized by careful observation and understanding of the care delivery context, and planning of the data storage with a range of options available depending on the data size.49 At the same time, methods have been developed, such as imputation and approximate inference algorithms, that can accommodate missing data. For example, in this paper, we used the EM algorithm to infer the parameters of HMM. Furthermore, diversity is innate to most healthcare data, and we found it to be one of the biggest challenges in accurately inferring clinical pathways, requiring large amounts of data and robust methods for analysis and inference. In this paper, we examined encounter type, diagnosis, medication prescriptions, and biochemical measurements, but our data representation is flexible with regard to the number of clinical factors of interest. Therefore, when sufficient curated data becomes available, factors such as medical expenses and behavioral information can also be incorporated to enrich the learned pathways and personalized predictions of health and cost outcomes.

CONCLUSIONS

This paper presents additional promising evidence of the potential of machine learning applications for clinical decision making. We develop and demonstrate a methodology to facilitate more targeted management of patients with complex chronic conditions using data-driven clinical pathways. Clinical pathways are learned from a healthcare organization’s EHR data by summarizing multidimensional clinical history as chronologically organized sequences, capturing information on the co-progression of encounter types, diagnoses, medications, and biochemical measurements. Further, we link clinical pathways to a few outcomes within subgroups of patients with reasonable accuracy using hierarchical clustering and HMM. Applying our methodology to relevant EHR data on 664 patients with CKD stage 3 and hypertension, we identify clinical pathways that may be compared with current CPG recommendations in future studies, and contribute to the development of shared-baseline within hospitals. These methods and broad findings from EHR data are generalizable and can be adapted to other clinical conditions to support efficient review of treatments and outcomes and to aid clinical professionals and patients in making more informed treatment and management decisions.

Acknowledgments

The authors are very grateful to the forward-thinking physicians and staff of the community nephrology practice, Teredesai, McCann & Associates, PC, in Western Pennsylvania, who generously provided detailed, de-identified data from their 20-year electronic health record for this study. We particularly thank Pradip Teredesai, MD, FACP; Qizhi Xie, MD, PhD; Nirav Patel, MD; and staff members Linda Smith and Audra Barletta, who gave us important clinical and technical information about the data and the key characteristics of CKD, AKI, and their treatments. This study was designated as Exempt by the Institutional Review Board at Carnegie Mellon University.

Author Affiliations: The H. John Heinz III College, Carnegie Mellon University (YZ, RP), Pittsburgh, PA.

Source of Funding: This study is part of a doctoral thesis at Carnegie Mellon University and has no funding source.

Author Disclosures: Dr Padman and Ms Zhang report no relationship or financial interest with any entity that would pose a conflict of interest with the subject matter of this article.

Authorship Information: Concept and design (YZ, RP); acquisition of data (YZ, RP); analysis and interpretation of data (YZ, RP); drafting of the manuscript (YZ); critical revision of the manuscript for important intellectual content (YZ, RP); statistical analysis (YZ); administrative, technical, or logistic support (RP); and supervision (RP).

Address correspondence to: Yiye Zhang, MS, The H. John Heinz III College, Carnegie Mellon University, 4800 Forbes Ave, Pittsburgh, PA 15213. E-mail: yiyez@andrew.cmu.edu.
REFERENCES
1. Chronic diseases and health promotion. World Health Organization website. http://www.who.int/chp/en/. Published 2015. Accessed November 6, 2015.

2. Abra G, Patel M, Moore D, et al. Trend-bearing Chronic Kidney Disease Care Model. Stanford University website. http://cerc.stanford.edu/fellowships/docs/CERC4modelsummary2.11.2013_3PMpdf.pdf. Published 2013. Accessed November 6, 2015.

3. Zhang Y, Padman R, Wasserman L, Patel N, Teredesai P, Xie Q. On clinical pathway discovery from electronic health record data. IEEE Intelligent Systems. 2015;30(1):70-75.

4. Saria S. A $3 trillion challenge to computational scientists: transforming healthcare delivery. IEEE Intelligent Systems. 2014;29(4):82-87.

5. Bishop CM. Pattern Recognition and Machine Learning. New York, NY: Springer-Verlag; 2006.

6. Rabiner L, Juang B-H. Fundamentals of Speech Recognition. Upper Saddle River, NJ: Prentice Hall; 1993.

7. Stavens D, Thrun S. A self-supervised terrain roughness estimator for off-road autonomous driving. Presented in: proceedings of Conference on Uncertainty in AI (UAI); July 13-16 2006; Cambridge, MA. https://dslpitt.org/uai/papers/06/p469-stavens.pdf. Accessed November 6, 2015.

8. Linden G, Smith B, York J. Amazon.com recommendations: item-to-item collaborative filtering. IEEE Internet Computing. 2003;7(1):76-80.

9. Kusiak A. Innovation: a data-driven appraoch. Internatl J Production Econom. 2009;122(1):440-448.

10. Miles I. Innovation in services. In: Fagerberg J, Mowery DC, Nelson RR, eds. The Oxford Handbook of Innovation. New York, NY: Oxford University Press; 2005.

11. Miles I. Service Innovation. In: Maglio PP, Kieliszewski CA, Spohrer JC, eds. Handbook of Service Science. New York, NY: Springer; 2010:511-533.

12. Hall BH, Lotti F, Mairesse J. Innovation and productivity in SMEs: empirical evidence for Italy. Small Bus Econ. 2009;33(1):13-33.

13. Tether B, Howells J. Changing understanding of innovation in services. Innvoation Services. 2007;9:21-60.

14. Goldzweig CL, Towfigh A, Maglione M, Shekelle PG. Costs and benefits of health information technology: new trends from the literature. Health Aff (Millwood). 2009;28(2):w282-w293.

15. Shekelle PG, Morton SC, Keeler EB. Costs and benefits of health information technology. Evid Rep Technol Assess (Full Rep). 2006(132):1-71.

16. Kayyali B, Knott D, Kuiken SV. The big-data revolution in US health care: accelerating value and innovation. McKinsey & Company website. http://www.mckinsey.com/insights/health_systems_and_services/the_big-data_revolution_in_us_health_care. Published April 2013. Accessed November 6, 2015.

17. Moxey A, Robertson J, Newby D, Hains I, Williamson M, Pearson SA. Computerized clinical decision support for prescribing: provision does not guarantee uptake. J Am Med Inform Assoc. 2010;17(1):25-33.

18. Collins FS, Varmus H. A new initiative on precision medicine. N Engl J Med. 2015;372(9):793-795.

19. HITECH Act enforcement interim final rule. HHS website. http://www.hhs.gov/ocr/privacy/hipaa/administrative/enforcementrule/hitechenforcementifr.html. Accessed November 6, 2015.

20. Lee DS, Stitt A, Austin PC, et al. Prediction of heart failure mortality in emergent care: a cohort study. Ann Intern Med. 2012;156(11):767-775.

21. Zhang Y, Padman R, Levin JE. Paving the COWpath: data-driven design of pediatric order sets. J Am Med Inform Assoc. 2014;21(e2):e304-e311.

22. Saria S, Rajani AK, Gould J, Koller D, Penn AA. Integration of early physiological responses predicts later illness severity in preterm infants. Sci Transl Med. 2010;2(48):48ra65.

23. Chen JH, Podchiyska T, Altman RB. OrderRex: clinical order decision support and outcome predictions by data-mining electronic medical records [published online July 21, 2015]. J Am Med Inform Assoc. 2015. pii:ocv091.

24. Halpern Y, Choi Y, Horng S, Sontag D. Using Anchors to Estimate Clinical State without Labeled Data. Paper presented at: AMIA Annual Symposium Proceedings; November 2014; Washington, DC.

25. Neill DB, Cooper GF. A multivariate Bayesian scan statistic for early event detection and characterization. Mach Learn. 2010;79(3):261-282.

26. Coresh J, Selvin E, Stevens LA, et al. Prevalence of chronic kidney disease in the United States. JAMA. 2007;298(17):2038-2047.

27. United States renal data system: 2013 atlas of CKD & ESRD. United States Renal Data System website. http://www.usrds.org/atlas.aspx. Published 2013. Accessed November 6, 2015.

28. National Kidney Foundation. KDOQI clinical practice guideline for diabetes and CKD: 2012 update. Am J Kidney Dis. 2012;60(5):850-886.

29. Rotter T, Kinsman L, James E, et al. Clinical pathways: effects on professional practice, patient outcomes, length of stay and hospital costs. Cochrane Database System Rev. 2010(3):CD006632.

30. Lin F, Chou S, Pan S, Chen Y. Mining time dependency patterns in clinical pathways. Int J Med Inform. 2001;62(1):11-25.

31. Huang CW, Syed-Abdul S, Jian WS, et al. A novel tool for visualizing chronic kidney disease associated polymorbidity: a 13-year cohort study in Taiwan. J Am Med Inform Assoc. 2015;22(2):290-298.

32. Zhang Y, Padman R, Wasserman L. On learning and visualizing practice-based clinical pathways for chronic kidney disease. Presented at: American Medical Informatics Association 2014 Annual Symposium; November 2014; Washington, DC.

33. Lakshmanan GT, Rozsnyai S, Wang F. Investigating clinical care pathways correlated with outcomes. In: Business Process Management. Berlin, Heidelberg, Germany; Springer; 2013: 323-338.

34. Huang Z, Lu X, Duan H. On mining clinical pathway patterns from medical behaviors. Artif Intell Med. 2012;56(1):35-50.

35. van der Aalst WMP, van Dongen BF, Herbst J, Maruster L, Schimm G, Weijters AJMM. Workflow mining: a survey of issues and approaches. Data Knowl Eng. 2003;47(2):237-267.

36. Egho E, Jay N, Raïssi C, Nuemi G, Quantin C, Napoli A. An approach for mining care trajectories for chronic diseases. In: Artificial Intelligence in Medicine. Berlin, Heidelberg, Germany; Springer; 2013: 258-267.

37. Yang W, Su Q. Process mining for clinical pathway: literature review and future directions. Paper presented at: 11th International Conference on Service Systems and Service Management; June 2014; Bejing, China.

38. Huang Z, Dong W, Ji L, Gan C, Lu X, Duan H. Discovery of clinical pathway patterns from event logs using probabilistic topic models.
J Biomed Inform. 2014;47:39-57.

39. Zhang Y, Padman R. Patel N. Paving the COWPath: learning and visualizing clinical pathways from electronic health record data [published online September 28, 2015]. J Biomed Inform. 2015. pii: S1532-0464(15)00202-6.

40. Elzinga CH. Sequence analysis: metric representations of categorical time series. Socio-logical Methods and Research. 2006.

41. Rousseeuw PJ. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Computational and Applied Mathematics. 1987;20:53-65.

42. Eddy SR. What is a hidden Markov model? Nat Biotechnol. 2004;22(10):1315-1316.


43. Rabiner LR, Juang BH. An introduction to hidden Markov models. IEEE ASSP Magazine. 1986;3(1):4-16.

44. Karlin S. A First Course in Stochastic Processes. San Diego, CA: Academic Press; 2014.

45. Geisser S. Predictive Inference (Monographs on Statistics & Applied Probability [book 55]). New York, NY: Chapman and Hall/CRC; 1993.

46. Chertow GM, Burdick E, Honour M, Bonventre JV, Bates DW. Acute kidney injury, mortality, length of stay, and costs in hospitalized patients. J Am Soc Nephrol. 2005;16(11):3365-3370.

47. James BC, Savitz LA. How Intermountain trimmed health care costs through robust quality improvement efforts. Health Aff (Millwood). 2011;30(6):1185-1191.

48. Shortell SM, Wu FM, Lewis VA, Colla CH, Fisher ES. A taxonomy of accountable care organizations for policy and practice. Health Serv Res. 2014;49(6):1883-1899.

49. Elmasri R, Navathe SB. Fundamentals of Database Systems. 6th edition. New York, NY: Pearson; 2010. 
PDF
 
Copyright AJMC 2006-2019 Clinical Care Targeted Communications Group, LLC. All Rights Reserved.
x
Welcome the the new and improved AJMC.com, the premier managed market network. Tell us about yourself so that we can serve you better.
Sign Up