JMIR Publications

ABSTRACT

Background:

Chatbots are applications that can conduct natural language conversations with users. In the medical field, chatbots have been developed and used to serve different purposes. They provide patients with timely information that can be critical in some scenarios, such as access to mental health resources. Since the development of the first chatbot, ELIZA in the late 1960s, much efforts followed to produce chatbots for various health purposes developed in different ways.

Objective:

This study aims to review previous studies exploring different technical aspects used for developing text-based chatbots for healthcare.

Methods:

We searched for relevant articles in eight literature databases (IEEE, ACM, Springer, ScienceDirect, Embase, MEDLINE, PsycINFO and Google Scholar). We also performed forward and backward reference checking of the selected articles. Study selection was performed by one reviewer and 50% of the selected studies were randomly checked by a second reviewer. A narrative approach was used for result synthesis. Chatbots were classified based on the different technical aspects of their development. The main chatbot components were identified in addition to the different techniques for implementing each module.

Results:

The number of retrieved publications in our original search was 2481, out of which we identified 45 studies that matched our inclusion and exclusion criteria. The most common language of communication between users and chatbots was English (n=23). Four main modules were identified, the text understanding module, the dialog management module, the database layer and the text generation module. The most common technique for developing the text understanding and dialogue management are pattern matching methods (n=18 and n=25 respectively). The most common text generation is fixed output (n=36). Very few studies relied on generating original output. Most studies kept a medical knowledge base to be used by the chatbot for different purposes throughout the conversations. A few studies kept conversation scripts and collected user data and previous conversations.

Conclusions:

Many chatbots have been developed for medical use, with an increasing rate. There is an apparent shift in adopting machine learning based approaches for developing chatbot systems in recent years. Further research can be conducted to link clinical outcomes to different chatbot development techniques and technical characteristics.