IMS: An improved medical retrieval model via medical-context aware query expansion and comprehensive ranking

Medical information retrieval demands terminology understanding which indicates the needs for domain specific knowledge. This paper presents a medical retrieval model called IntelligentMedicalSearch system (IMS). The contribution of the paper is four-fold: (i) medical-aware query expansion technique; (ii) MeSH-manipulated indexer which entails medical terminologies and their synonym (iii) extended Boolean matching to measure similarity between query and documents; (iv) comprehensive ranking method which prioritizes matched expanded query size besides sole total occurrence score. Result shown that (i) enrichment of query expansion using synonym term can improve mean average precision (MAP) value as opposed to standard query expansion; (iii) our comprehensive ranking method achieved high recall and according to MAP score we are in the top four run system amongst submitted run systems in ImageCLEF2010 medical task.