Network supported intelligent cooperative diagnosis for difficult and complicated cases in Traditional Chinese Medicine

The diagnosis of difficult and complicated cases in Traditional Chinese Medicine (TCM) often requires experts to cooperatively work together. The right experts and their ability to jointly make the suitable diagnostic decisions are key for resolving the diagnosis. The methodologies described here have been developed for (1) effectively making an initial diagnosis or narrowing down the possible syndrome and disease range, (2) forming a cooperative team via networks, and (3) making a joint decision among multi-agents. The process is divided into two stages. In the first stage, the doctor in charge uses a multi-level sieve method to narrow down the range of possible diseases and syndromes. Important symptoms and diagnostic difficulties will be identified in the sieving process. In the second stage, a multi-agent diagnosis helping system (MADHS) simulates cooperative experts and makes joint decisions. Calls for invitations are distributed by a Network Supported Invitation System (NSIS) when 1) the sieving method is not able to narrow down the range of possible diseases and syndromes, or 2) using the certainty reasoning method is not able to confirm or deny certain diseases or syndromes. Invited experts may reply by sending their intentions and proposals to join the team. Received proposals from experts a team of experts will be collated by the intelligent NSIS. Diseases and syndromes will be further reliably determined by the MADHS system. It is anticipated that the methodologies used here may be widely implemented in computer aided diagnosis not only for TCM, but also for other diagnostic areas. The described system may be implemented as a cloud service system for many expected users.