Machine Learning: Multi-site Evidence-Based Best Practice Discovery
This study establishes interoperability among electronic medical records from 737 healthcare sites and performs machine learning for best practice discovery. A mapping algorithm is designed to disambiguate free text entries and to provide a unique and unified way to link content to structured medical concepts despite the extreme variations that can occur during clinical diagnosis documentation. Redundancy is reduced through concept mapping. A SNOMED-CT graph database is created to allow for rapid data access and queries. These integrated data can be accessed through a secured web-based portal. A classification model (DAMIP) is then designed to uncover discriminatory characteristics that can predict the quality of treatment outcome. We demonstrate system usability by analyzing Type II diabetic patients. DAMIP establishes a classification rule on a training set which results in greater than 80% blind predictive accuracy on an independent set of patients. By including features obtained from structured concept mapping, the predictive accuracy is improved to over 88%. The results facilitate evidence-based treatment and optimization of site performance through best practice dissemination and knowledge transfer.
KeywordsClassification Rule Depth Level Discriminatory Feature Unify Medical Language System Graph Database
This paper receives the 2016 NSF Health Organization Transformation award (second place). The work is partially supported by a grant from the National Science Foundation IIP-1361532. Findings and conclusions in this paper are those of the authors and do not necessarily reflect the views of the National Science Foundation.
- 4.Donnelly, K.: SNOMED-CT: the advanced terminology and coding system for eHealth. Stud. Health Technol. Inform. 121, 279 (2006)Google Scholar
- 8.Hernandez, P., et al.: Automated mapping of pharmacy orders from two electronic health record systems to RxNorm within the STRIDE clinical data warehouse. American Medical Informatics Association (2009)Google Scholar
- 9.Carlo, L., Chase, H.S., Weng, C.: Aligning structured and unstructured medical problems using umls. American Medical Informatics Association (2010)Google Scholar
- 10.Patel, C.O., Cimino, J.J.: Using semantic and structural properties of the unified medical language system to discover potential terminological relationships. J. Am. Med. Inform. Assoc. 16(3), 346–353%@ 1067–5027 (2009)Google Scholar
- 11.Gallagher, R.J., Lee, E.K.: Mixed integer programming optimization models for brachytherapy treatment planning. In: Proceedings of the AMIA Annual Fall Symposium. American Medical Informatics Association (1997)Google Scholar
- 14.Estacio, R.O., et al.: Effect of blood pressure control on diabetic microvascular complications in patients with hypertension and type 2 diabetes. Diab. Care 23, B54 (2000)Google Scholar
- 15.Aronson, A.R.: Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program. In: Proceedings of the AMIA Symposium. American Medical Informatics Association (2001)Google Scholar
- 16.Aronson, A.R.: Metamap: Mapping Text to the UMLS Metathesaurus. NLM, NIH, DHHS, Bethesda, pp. 1–26 (2006)Google Scholar
- 18.National Center for Health Statistics (U.S.). ICD-9-CM: The International Classification of Diseases, 9th Revision, Clinical Modification. 1978: Commission on Professional and Hospital ActivitiesGoogle Scholar
- 19.Caiado, J., Crato, N., Peña, D.: Comparison of times series with unequal length in the frequency domain. Commun. Stat. Simul. Comput.® 38(3), 527–540 (2009)Google Scholar
- 21.Lee, E.K., et al.: A clinical decision tool for predicting patient care characteristics: patients returning within 72 hours in the emergency department. In: AMIA Annual Symposium Proceedings. American Medical Informatics Association (2012)Google Scholar