Applications for Future Internet. International Summit, AFI 2016, Puebla, Mexico, May 25-28, 2016, Revised Selected Papers

Research Article

A Conversational Agent for Use in the Identification of Rare Diseases

Download65 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-49622-1_15,
        author={Ana Lambert and Cesar Monta\`{o}ez and Monica Martinez and Marcelo Funes-Gallanzi},
        title={A Conversational Agent for Use in the Identification of Rare Diseases},
        proceedings={Applications for Future Internet. International Summit, AFI 2016, Puebla, Mexico, May 25-28, 2016, Revised Selected Papers},
        proceedings_a={AFI360},
        year={2017},
        month={1},
        keywords={General cognition engines Artificial cognition systems Diagnosis Rare diseases},
        doi={10.1007/978-3-319-49622-1_15}
    }
    
  • Ana Lambert
    Cesar Montañez
    Monica Martinez
    Marcelo Funes-Gallanzi
    Year: 2017
    A Conversational Agent for Use in the Identification of Rare Diseases
    AFI360
    Springer
    DOI: 10.1007/978-3-319-49622-1_15
Ana Lambert1,*, Cesar Montañez2,*, Monica Martinez2,*, Marcelo Funes-Gallanzi3,*
  • 1: Universidad Iberoamericana
  • 2: Natura Xalli
  • 3: AVNTK, S.C.
*Contact email: ana.caballero@leon.uia.mx, cesar.torres@naturaxalli.com, monica.bueno@naturaxalli.com, mfg@avntk.com

Abstract

This paper presents work in progress on implementing a conversational agent, Dr. Rachael, in the form of a virtual caregiver, for use in helping to identify rare diseases. The rationale for the system is grounded in the fact that rare disorders by their very nature are difficult to diagnose unless the caregiver or doctor is familiar with a wide range of these conditions. The conversational agent uses unstructured free-flowing natural language together with a large database of rare disorders, and is easily updatable by human caregivers without any technical expertise. Matching of users’ comments with database entries is performed using a general cognition engine; which is able to understand natural language regardless of specific wording or grammar. In this paper we give a comprehensive background to and an overview of the system, with a focus on aspects pertaining to natural language processing and user interaction. The system is currently only implemented for English.