MedChatBot: An UMLS based Chatbot for Medical Students

Abstract

The use of natural dialog has great significance in the design of interactive tutoring systems. The nature of student queries can be confined to a small set of templates based on the task domain. This paper describes the development of a chatbot for medical students, that is based on the open source AIML based Chatterbean. We deploy the widely available Unified Medical Language System (UMLS) as the domain knowledge source for generating responses to queries. The AIML based chatbot is customized to convert natural language queries into relevant SQL queries. The SQL queries are run against the knowledge base and results returned to the user in natural dialog. Student survey was carried out to identify various queries posed by students. The chatbot was designed to address common template queries. Knowledge inference techniques were applied to generate responses for queries for which knowledge was not explicitly encoded. Query responses were rated by three experts on a 1-5 point likert scale, who agreed among themselves with Pearson Correlation Coefficient of 0.54 and p < 0.05. The overall average rating assigned by experts was 3.4.

KBot: A Knowledge Graph Based ChatBot for Natural Language Understanding Over Linked Data

“…They are based on the knowledge bases from those domains to provide consistent support for the user. Educational chatbot help students answer specific education-related queries such as Med-Chatbot [6] for medical students, based on the open-source AIML. In this chatbot, authors deploy a widely available Unified Medical Language System (UMLS) as the domain knowledge source for generating responses and translating natural language queries into relevant SQL queries.…”

“…In this paper, we propose a chatbot (KBot) that addresses some of the above challenges, and that can compete in terms of performances with existing linked data chatbots. Besides, we process one of the largest research databases in social science (i.e., the myPersonality corpus 6 ), which was collected from over 6 million volunteers on Facebook (FB). The data was anonymized and sampled to share with registered scholars around the world.…”

Perpectivas de las tecnologías de Chatbot y su aplicación a las entrevistas de evaluación del lenguaje

“…Entre ellos podemos destacar los trabajos de Delgado Guerrero et al (2017) que presentan el diseño y desarrollo de un chatbot para ser usado por los estudiantes de la carrera de Ingeniería en Sistemas Computacionales de la Facultad de Ciencias Matemáticas y Físicas de la Universidad de Guayaquil, Ecuador; el trabajo de Ranoliya et al (2017), que presentan un sistema que está siendo desarrollado en el ámbito de la educación universitaria y al que se le puede pedir información sobre la admisión, la vida de la universidad, aspectos académicos, servicios, etc. y, en el ámbito de la medicina educativa, queremos resaltar el chatbot desarrollado por Kazi et al (2012) para estudiantes de Medicina. Este chatbot se incorpora a un sistema de tutoría e integra contenidos de UMLS 4 , un recurso médico que integra el vocabulario de las ciencias biomédicas con más de dos millones de entradas.…”

Automated Medical Chatbot

“…Chowdhry and Zeesha Memon focuses on a design for an AIML based Medical Chatbot. This Chatbot design is implemented using a JAVA based AIML interpreter called Chatter bean [3]. To use the proposed design, the user has to type a message that should contain the illness name and it detects the illness names using AIML patterns.…”

“…To use the proposed design, the user has to type a message that should contain the illness name and it detects the illness names using AIML patterns. Once the illness is detected, the Chatbot provides the user about the necessary information about the problem [3].…”