Display options
Cite
Berger JS, Haskell L, Ting W, et al. Evaluation of machine learning methodology for the prediction of healthcare resource utilization and healthcare costs in patients with critical limb ischemia-is preventive and personalized approach on the horizon?. EPMA J. 2020;11(1):53-64doi: 10.1007/s13167-019-00196-9.
Berger, J. S., Haskell, L., Ting, W., Lurie, F., Chang, S. C., Mueller, L. A., Elder, K., Rich, K., Crivera, C., Schein, J. R., & Alas, V. (2020). Evaluation of machine learning methodology for the prediction of healthcare resource utilization and healthcare costs in patients with critical limb ischemia-is preventive and personalized approach on the horizon?. The EPMA journal, 11(1), 53-64. https://doi.org/10.1007/s13167-019-00196-9
Berger, Jeffrey S, et al. "Evaluation of machine learning methodology for the prediction of healthcare resource utilization and healthcare costs in patients with critical limb ischemia-is preventive and personalized approach on the horizon?." The EPMA journal vol. 11,1 (2020): 53-64. doi: https://doi.org/10.1007/s13167-019-00196-9
Berger JS, Haskell L, Ting W, Lurie F, Chang SC, Mueller LA, Elder K, Rich K, Crivera C, Schein JR, Alas V. Evaluation of machine learning methodology for the prediction of healthcare resource utilization and healthcare costs in patients with critical limb ischemia-is preventive and personalized approach on the horizon?. EPMA J. 2020 Jan 03;11(1):53-64. doi: 10.1007/s13167-019-00196-9. eCollection 2020 Mar. PMID: 32140185; PMCID: PMC7028871.
Copy Download .nbib Format: NLM
Share it on

EPMA J. 2020 Jan 03;11(1):53-64. doi: 10.1007/s13167-019-00196-9. eCollection 2020 Mar.

Evaluation of machine learning methodology for the prediction of healthcare resource utilization and healthcare costs in patients with critical limb ischemia-is preventive and personalized approach on the horizon?.

The EPMA journal

Jeffrey S Berger, Lloyd Haskell, Windsor Ting, Fedor Lurie, Shun-Chiao Chang, Luke A Mueller, Kenneth Elder, Kelly Rich, Concetta Crivera, Jeffrey R Schein, Veronica Alas

Affiliations

  1. 1New York University Langone Medical Center, Center for the Prevention of Cardiovascular Disease, New York, NY 10016 USA.
  2. Janssen Scientific Affairs, LLC, Raritan, NJ 08869 USA.
  3. 3Mt. Sinai Health System, New York, NY 10029 USA.
  4. Jobst Vascular Institute, Toledo, OH 43606 USA.
  5. 5Health Economics and Outcomes Research, GNS Healthcare, 196 Broadway, Cambridge, MA 02139 USA.

PMID: 32140185 PMCID: PMC7028871 DOI: 10.1007/s13167-019-00196-9

Abstract

BACKGROUND: Critical limb ischemia (CLI) is a severe stage of peripheral arterial disease and has a substantial disease and economic burden not only to patients and families, but also to the society and healthcare systems. We aim to develop a personalized prediction model that utilizes baseline patient characteristics prior to CLI diagnosis to predict subsequent 1-year all-cause hospitalizations and total annual healthcare cost, using a novel Bayesian machine learning platform, Reverse Engineering Forward Simulation™ (REFS™), to support a paradigm shift from reactive healthcare to Predictive Preventive and Personalized Medicine (PPPM)-driven healthcare.

METHODS: Patients ≥ 50 years with CLI plus clinical activity for a 6-month pre-index and a 12-month post-index period or death during the post-index period were included in this retrospective cohort of the linked Optum-Humedica databases. REFS™ built an ensemble of 256 predictive models to identify predictors of all-cause hospitalizations and total annual all-cause healthcare costs during the 12-month post-index interval.

RESULTS: The mean age of 3189 eligible patients was 71.9 years. The most common CLI-related comorbidities were hypertension (79.5%), dyslipidemia (61.4%), coronary atherosclerosis and other heart disease (42.3%), and type 2 diabetes (39.2%). Post-index CLI-related healthcare utilization included inpatient services (14.6%) and ≥ 1 outpatient visits (32.1%). Median annual all-cause and CLI-related costs per patient were $30,514 and $2196, respectively. REFS™ identified diagnosis of skin and subcutaneous tissue infections, cellulitis and abscess, use of nonselective beta-blockers, other aftercare, and osteoarthritis as high confidence predictors of all-cause hospitalizations. The leading predictors for total all-cause costs included region of residence and comorbid health conditions including other diseases of kidney and ureters, blindness of vision defects, chronic ulcer of skin, and chronic ulcer of leg or foot.

CONCLUSIONS: REFS™ identified baseline predictors of subsequent healthcare resource utilization and costs in CLI patients. Machine learning and model-based, data-driven medicine may complement physicians' evidence-based medical services. These findings also support the PPPM framework that a paradigm shift from post-diagnosis disease care to early management of comorbidities and targeted prevention is warranted to deliver a cost-effective medical services and desirable healthcare economy.

© European Association for Predictive, Preventive and Personalised Medicine (EPMA) 2020.

Keywords: Critical limb ischemia; Healthcare costs; Healthcare resource utilization; Machine learning; Predictive preventive personalized medicine; Vascular disease

Conflict of interest statement

Conflict of interestAuthors Haskell, Crivera, and Schein have direct financial relationships with Janssen Pharmaceuticals. Authors Berger, Ting, and Lurie have indirect financial relationships with Ja

References

  1. Interv Cardiol Clin. 2017 Apr;6(2):251-259 - PubMed
  2. Lancet Neurol. 2017 Nov;16(11):908-916 - PubMed
  3. J Vasc Surg. 2014 Dec;60(6):1677-85 - PubMed
  4. Ann Vasc Surg. 2017 Jan;38:191-205 - PubMed
  5. Vasc Med. 2008 Aug;13(3):209-15 - PubMed
  6. PLoS One. 2016 Feb 05;11(2):e0148195 - PubMed
  7. J Am Coll Cardiol. 2017 Apr 18;69(15):1897-1908 - PubMed
  8. EPMA J. 2014 May 30;5(1):8 - PubMed
  9. J Med Econ. 2017 Nov;20(11):1148-1154 - PubMed
  10. N Engl J Med. 2017 Jun 29;376(26):2507-2509 - PubMed
  11. J Manag Care Pharm. 2005 Nov-Dec;11(9):727-34 - PubMed
  12. Brief Bioinform. 2017 Jan;18(1):105-124 - PubMed
  13. J Vasc Surg. 2010 Jan;51(1):230-41 - PubMed
  14. J Clin Epidemiol. 1994 Nov;47(11):1245-51 - PubMed
  15. J Vasc Surg. 2009 Jul;50(1):54-60 - PubMed
  16. J Am Coll Cardiol. 2016 Nov 1;68(18):2002-2015 - PubMed
  17. Circulation. 2017 Mar 21;135(12):e726-e779 - PubMed
  18. Eur J Cardiovasc Prev Rehabil. 2011 Apr;18(2):254-61 - PubMed
  19. EPMA J. 2012 Nov 01;3(1):14 - PubMed
  20. Vasc Health Risk Manag. 2019 Jul 01;15:187-208 - PubMed
  21. J Diabetes Sci Technol. 2015 Dec 20;10(1):6-18 - PubMed
  22. N Engl J Med. 2016 Sep 29;375(13):1216-9 - PubMed
  23. J Am Coll Cardiol. 2016 Apr 26;67(16):1901-13 - PubMed
  24. Cardiovasc Revasc Med. 2015 Oct-Nov;16(7):421-5 - PubMed
  25. Circulation. 2017 Jul 11;136(2):167-176 - PubMed
  26. J Chronic Dis. 1987;40(5):373-83 - PubMed
  27. JAMA. 2018 Mar 13;319(10):1024-1039 - PubMed
  28. J Vasc Surg. 2015 Dec;62(6):1642-51.e3 - PubMed
  29. J Am Coll Cardiol. 2014 Jun 17;63(23):2525-2530 - PubMed
  30. J Vasc Surg. 2014 Sep;60(3):686-95.e2 - PubMed
  31. J Am Heart Assoc. 2018 Aug 21;7(16):e009724 - PubMed
  32. J Vasc Surg. 2012 Oct;56(4):1015-24.e1 - PubMed
  33. Am Econ Rev. 2015 May;105(5):491-495 - PubMed
  34. Health Serv Res. 2016 Dec;51(6):2358-2374 - PubMed
  35. J Am Coll Cardiol. 2016 Apr 26;67(16):1914-6 - PubMed
  36. J Am Heart Assoc. 2016 Feb 23;5(2): - PubMed
  37. Eur Rev Med Pharmacol Sci. 2016;20(3):502-8 - PubMed
  38. Ann Vasc Surg. 2010 Jul;24(5):577-87 - PubMed
  39. Eur J Vasc Endovasc Surg. 2014 Oct;48(4):447-51 - PubMed
  40. J Vasc Surg. 2018 Feb;67(2):558-567 - PubMed

Publication Types