A Semantic Extraction and Sentimental Assessment of Risk Factors (SESARF): An NLP Approach for Precision Medicine: A Medical Decision Support Tool for Early Diagnosis from Clinical Notes

Clinical notes contain information that is crucial for the diagnosis process. However, it is usually not properly manually analyzed due to the tremendous efforts and time it takes. Hence, an automated approach is eagerly needed to maximize clinical knowledge management and reduce cost. In this paper, we propose a framework SESARF: a Semantic Extractor to identify hidden risk factors in clinical notes and a Sentimental Analyzer to assess the severity levels associated with the identified Risk Factors. This tool can be customized to any disease using Linked Open Data (LOD) by selecting a specific disease and collecting its risk factors list from medical ontologies. The extracted knowledge can serve two purposes: 1) a feature vector is prepared, for any classifier in machine learning, containing risk factors and their weights based on our semantic enrichment and sentimental analyzer and 2) a proper comparison of the extracted information with wearable body sensors that can alert any major changes in a patient's health status to personalize treatment.