iHANDs: Intelligent Health Advising and Decision-Support Agent

This paper describes an intelligent health and decision support agent (iHANDs) built with various artificial intelligence mechanisms. Upon receiving the user´s symptom descriptions, iHands conducts both web search and local medical knowledge database search, utilizing the user´s electronic health records (EHR) to direct the search process. An information-fusion algorithm is developed based on Dempster-Shafer theory to merge the information from various sources with different reliabilities and generate the strength of support for each possible cause. A dynamic reference network is created and updated to record all information obtained during the interleaved search and reasoning process. Ihands performs a bi-directional search: from symptoms to possible causes and also from possible causes to most likely symptoms and risk factors. Bayesian inference mechanism is used to identify the confidence level for each possible cause given the user´s symptoms and EHR. When needed, an iterative broaden search will be conducted to increase the confidence level to exceed a pre-set threshold or to further distinguish a few possible causes with very close confidence levels. The preliminary experiment results show the promise of iHands in assisting individuals in their healthcare decision-making process.