ABSTRACT
This paper addresses the task of analyzing healthcare data for medical decision making. We describe a method for ranking medications based on historical data of the outcomes recorded as part of a system of Electronic Medical Records (EMR). Medication ranking can be used to recommend medications for a given group of diagnoses. The ranking process captures the effects of medication and subsequent diagnoses. We used longitudinal electronic medical records of five test patients for the purpose of this study. More than 5000 medical visit documents are analyzed and the medication and diagnosis information are extracted to create a vector space model. The resulting matrix ranked 167 medications and 187 problems. This is designed to enable the decision making capabilities within EMRs. Similar approaches can be used to provide decision support towards preventive medication.
- Berry, M. W. "Computational Information Retrieval," Proceedings in Applied Mathematics 106, 2000. Google ScholarDigital Library
- Berry, Dumais, O'Brien. "Using Linear Algebra for Intelligent Information Retrieval", SIAM Review (37)4: 573--595, 1995. Google ScholarDigital Library
- Evans D. C., Nichol, W. P., Perlin, J. B. "Effect of the implementation of an enterprise-wide Electronic Health Record on productivity in the Veterans Health Administration". Health Econ Policy Law 1 (Pt 2): 163--9.Google ScholarCross Ref
- Handler T. et al., "EHR Definition, Attributes and Essential Requirements", Healthcare Information and Management Systems Society. 2003.Google Scholar
- Kolda, T. J., and Bader, B. W. "Tensor Decompositions and Applications," SIAM Review, 51(3): 455--50, 2009. Google ScholarDigital Library
- Larson, R. Davis, M.. SIMS 202: Information Organization and Retrieval. UC Berkeley SIMS, Lecture 18: Vector Representation, 2002.Google Scholar
- Lavelli, Sebastiani, Zanoli. Distributional Term Representations: An experimental Comparison. CIKM 2004, November 8-13, Washington, DC, USA. Google ScholarDigital Library
- Papineni, K.. Why Inverse Document Frequency?. IBM T.J. Watson Research Center Yorktown Heights, New York, Usa, 2001.Google Scholar
- Salton, G. Wong, A. and Yang, C. S. "A Vector Space Model for Automatic Indexing," Communications of the ACM, vol. 18, nr. 11, pages 613--620, 1975 Google ScholarDigital Library
- Wagner, M. M. et al "The Role of Clinical Event Monitors in Public Health Surveillance," JAMIA 2002.Google Scholar
Index Terms
- Medical decision making using vector space model
Recommendations
Computer decision support systems in general practice
The majority of healthcare contacts in the United Kingdom occur in primary care. The development of structured knowledge-based systems is being encouraged to assist doctors in diagnosis (Shortliffe et al., Medical Informatics, Addison-Wesley, Workingham,...
Improving medical decision trees by combining relevant health-care criteria
Through the years, decision trees have been widely used both to represent and to conduct decision processes. They can be automatically induced from databases using supervised learning algorithms which usually aim at minimizing the size of the tree. When ...
Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis
CHI '24: Proceedings of the CHI Conference on Human Factors in Computing SystemsToday’s AI systems for medical decision support often succeed on benchmark datasets in research papers but fail in real-world deployment. This work focuses on the decision making of sepsis, an acute life-threatening systematic infection that requires an ...
Comments