Constructing literature abstracts by computer: techniques and prospects
Information Processing and Management: an International Journal - Special issue on natural language processing and information retrieval
Emerging paradigms of cognition in medical decision-making
Journal of Biomedical Informatics
Cognitive and usability engineering methods for the evaluation of clinical information systems
Journal of Biomedical Informatics
Intelligent access to text: integrating information extraction technology into text browsers
HLT '01 Proceedings of the first international conference on Human language technology research
Journal of Biomedical Informatics
Real users, real data, real problems: the MiTAP system for monitoring bio events
HLT '02 Proceedings of the second international conference on Human Language Technology Research
Customization in a unified framework for summarizing medical literature
Artificial Intelligence in Medicine
Summarization from medical documents: a survey
Artificial Intelligence in Medicine
The automatic creation of literature abstracts
IBM Journal of Research and Development
Analyzing patient records to establish if and when a patient suffered from a medical condition
BioNLP '12 Proceedings of the 2012 Workshop on Biomedical Natural Language Processing
Hi-index | 0.00 |
Background: To provide high-quality and safe care, clinicians must be able to optimally collect, distill, and interpret patient information. Despite advances in text summarization, only limited research exists on clinical summarization, the complex and heterogeneous process of gathering, organizing and presenting patient data in various forms. Objective: To develop a conceptual model for describing and understanding clinical summarization in both computer-independent and computer-supported clinical tasks. Design: Based on extensive literature review and clinical input, we developed a conceptual model of clinical summarization to lay the foundation for future research on clinician workflow and automated summarization using electronic health records (EHRs). Results: Our model identifies five distinct stages of clinical summarization: (1) Aggregation, (2) Organization, (3) Reduction and/or Transformation, (4) Interpretation and (5) Synthesis (AORTIS). The AORTIS model describes the creation of complex, task-specific clinical summaries and provides a framework for clinical workflow analysis and directed research on test results review, clinical documentation and medical decision-making. We describe a hypothetical case study to illustrate the application of this model in the primary care setting. Conclusion: Both practicing physicians and clinical informaticians need a structured method of developing, studying and evaluating clinical summaries in support of a wide range of clinical tasks. Our proposed model of clinical summarization provides a potential pathway to advance knowledge in this area and highlights directions for further research.