Abstract
The explosive growth of data has led to a situation where the human brain is overloaded with more information than it can process. It is particularly dire in healthcare where critical information may be buried in the mountains of data in the Electronic Medical Record systems (EMR systems) and healthcare workers struggle to make sense of this information to provide the best care for their patients. Cognitive computing, exemplified by Watson, offers the promise of transforming EMR systems from mere data storage to intelligent systems that help physicians in providing improved patient care. When seeing a patient, a physician needs to quickly grasp the summary of the patient’s medical history from the EMR to prepare for the visit and to put the patient’s complaints in context. During the visit, there may be a need to supplement, confirm, and investigate the information that the patient provides with information from the EMR. These information needs can be fulfilled by a cognitive system using advanced analytics on the patient record data. Some of the ways this can happen are a problem-oriented summary of a patient record, precisely answering natural language questions about the patient record content, automatically identifying urgent abnormalities, and by providing precise causes for such abnormalities. In this cognitive computing view, an EMR is an active entity that leverages the vast knowledge of the medical sciences, drug information, and medical ontologies in the context of the patient medical records to meet the information needs of the healthcare provider.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Computer stored and managed patient data is referred to by multiple names, such as, EHR and EMR, often with little or no difference between the terms. To avoid possible confusion, we consistently use the term EMR to refer to a patient medical record and EMRs as its plural. Furthermore, we use the term EMR system(s) to refer to the software and hardware system that stores and provides access to the contents of EMRs.
References
American Medical Association. Improving care: priorities to improve electronic health record usability. 2014. [Online]. https://download.ama-assn.org/resources/doc/ps2/x-pub/ehr-priorities.pdf. Accessed 9 Oct 2014.
Bowens FM, Frye PA, Jones WA, 2010. Health Information Technology: Integration of Clinical Workflow into Meaningful Use of Electronic Health Records, Perspectives in Health Information Management / AHIMA, American Health Information Management Association, 7(Fall), 1d.
Buchanan GB, Shortliffe HE. Rule based expert systems: the MYCIN experiments of the Stanford Heuristic Programming Project. Boston: Addison-Wesley Longman Publishing Co; 1984.
Campbell JR. Strategies for Problem List Implementation in a Complex Clinical Enterprise. Lake Buena Vista, FL, American Medical Informatics Association (AMIA). 1998.
Devarakonda M, Tsou C-H. Automated problem list generation from electronic medical records in IBM Watson. Austin: AAAI (Innovatibe Applications of AI Track); 2015.
Devarakonda M, Zhang D, Ching-Huei T, Bornea M. Problem-oriented patient record summary: an early report on a Watson application. Natal: IEEE Healthcom; 2014.
Ferrucci D, et al. Building Watson: an overview of the DeepQA project. AI Mag. 2010;31(3):59–79.
Ferrucci D, et al. Watson: beyond jeopardy!. Artificial Intelligence. 2013;199(200):93–105.
Freund Y, Mason L. The Alternating Decision Tree Algorithm. San Francisco, Proc. of the 16th Int’l Conf on Machine Learning. 1999.
Gibbs WJ. Examining users on news provider web sites: a review of methodology. J Usability Stud. 2008;3(3):129–48.
Holmes C. The Problem List beyond Meaningful Use, Part I. Journal of American Health Information Management Association, 2011a;81(2), 30–3.
Holmes C. The Problem List beyond Meaningful Use, Part 2. Journal of American Health Information Management Association, 2011b; 81(3), 32–5.
Institute of Medicine. Crossing the quality chasm: a New Health System for the 21st century. Washington, DC: The National Academics Press; 2001.
Isabel Healthcare. Isabel symptom checker. 2014. [Online]. http://symptomchecker.isabelhealthcare.com/. Accessed 22 Dec 2014.
Kelly JE, Hamm S. Smart machines: IBM’s Watson and the era of cognitive computing. 2013. s.l.:Columbia Business School Publishing, New York, NY.
Lally A, et al. WatsonPaths: scenario-based question answering and inference over unstructured information. Yorktown Heights: IBM Research; 2014 (Report No. RC25489).
Liang J, Devarakonda M, Mehta N. Cognitive needs of physicians: a study based on interviews at two major hospitals s.l. 2015. IBM Research Report (Manuscript in Preparation).
Meystre SM, Haug PJ. Randomized controlled trial of an automated problem. International Journal of Medical Informatics, 2008;77,602–12.
Shartzer LJ. Health IT and workflow in small physicians’ practices. Quest Answer Brief. 2005. http://www.nihcm.org/pdf/AHRQ-QandA.pdf [Accessed: 7/21/15]
US National Library of Medicine, 2009. UMLS Reference Manual. [Online] Available at: http://www.ncbi.nlm.nih.gov/books/NBK9675/ [Accessed 15 04 2014]
Weed LL. Medical records that guide and teach. New Engl J Med, 1968;278(11):593–600.
Wenzina R, Kaiser K. Using TimeML to support the modeling of computerized clinical guidelines. In: Lovis C, et al., editors. e-Health – for continuity of care. s.l.:2014 European Federation for Medical Informatics and IOS Press. Washington, DC.
Wikipedia – Workflow. Workflow. 2014. [Online]. http://en.wikipedia.org/wiki/Workflow. Accessed 24 Dec 2014.
Wikipedia. Jeopardy!. 2014. [Online]. http://en.wikipedia.org/wiki/Jeopardy !. Accessed 14 Dec 2014.
Acknowledgements
We thank the physicians and IT staff at Cleveland Clinic who guided definition of the requirements for the functionality discussed here and provided de-identified EMRs under an IRB protocol for the studies. Watson EMRA is a next higher level function built on the medical-domain adapted Jeopardy! Watson. All three, the Jeopardy! Watson, Medical Watson, and Watson EMRA, are the results of an extraordinary team of research, engineering, and support staff at IBM. We gratefully acknowledge their work and contributions which are discussed here.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Devarakonda, M.V., Mehta, N. (2016). Cognitive Computing for Electronic Medical Records. In: Weaver, C., Ball, M., Kim, G., Kiel, J. (eds) Healthcare Information Management Systems. Health Informatics. Springer, Cham. https://doi.org/10.1007/978-3-319-20765-0_32
Download citation
DOI: https://doi.org/10.1007/978-3-319-20765-0_32
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20764-3
Online ISBN: 978-3-319-20765-0
eBook Packages: MedicineMedicine (R0)