Review of artificial intelligence‐based question‐answering systems in healthcare

Abstract

Use of conversational agents, like chatbots, avatars, and robots is increasing worldwide. Yet, their effectiveness in health care is largely unknown. The aim of this advanced review was to assess the use and effectiveness of conversational agents in various fields of health care. A literature search, analysis, and synthesis were conducted in February 2022 in PubMed and CINAHL. The included evidence was analyzed narratively by employing the principles of thematic analysis. We reviewed articles on artificial intelligence-based question-answering systems in health care. Most of the identified articles report its effectiveness; less is known about its use. We outlined study findings and explored directions of future research, to provide evidence-based knowledge about artificial intelligence-based question-answering systems.

Comparison of the Performance of GPT-3.5 and GPT-4 With That of Medical Students on the Written German Medical Licensing Examination: Observational Study

“…Considering the rising prevalence of psychiatric disorders and concomitant challenges in providing care, it seemed likely that nonprofessionals would also turn to the chatbot for mental health issues at the time of GPT-3.5's release [8,49,50]. Hence, it is conceivable that GPT-3.5's training data set includes not only a substantial and reliable portion of psychiatric data, but also its developers might have first fine-tuned ChatGPT specifically in this domain in anticipation of its high demand [51][52][53]. Thus, the developers might have also fine-tuned GPT-4 specifically in internal medicine and surgery, possibly reacting to a high demand in this area from users of its' predecessor.…”

Achieving health equity through conversational AI: A roadmap for design and implementation of inclusive chatbots in healthcare

“…A specific subset of AI in healthcare is patient-facing conversational AI agents and chatbots, which directly interact with patients to perform tasks ranging from symptom self-diagnosis and treatment recommendations to medication management [ 6 ]. These include various modalities such as text-based chatbots [ 7 ], voice assistants [ 8 ], and wearable devices [ 9 ].…”

A pilot randomised controlled trial exploring the feasibility and efficacy of a human-AI sleep coaching model for improving sleep among university students

“…To bridge this gap, question-answering (QA) systems have emerged as a tool to enhance knowledge and understanding on numerous topics by providing short and precise answers to questions posed in natural language. 24 This is achieved through natural language processing (NLP), a branch of artificial intelligence (AI) with rapid developments and vast applications using large language models (LLM) for QA. Question-answering systems possess an abundance of domain knowledge, where biomedical QA systems can be trained on evidence-based medical information to increase the accessibility of expert opinions.…”

“…This mimics direct access to an expert by providing timely and accurate responses to user's queries, allowing them to access evidence-based information in real-time. These QA systems have been applied for use in clinical decision support, 25 , 26 medical examinations, 27 , 28 consumer health questions 29 and to improve numerous health outcomes, 24 , 25 including sleep outcomes in university settings. 30 However, despite the QA system's abundance of knowledge, providing information to patients alone in this form is unlikely to be sufficient to promote behavioural change.…”