Page 50 - GTM-1-2

Global Translational Medicine

REVIEW ARTICLE
State-of-the-art: A taxonomy of artificial

intelligence-assisted robotics for medical
therapies and applications

6
3
2
1
Jinyang Wang , Lei Zhu , Po Yang , Ping Li , Jihong Wang *, Huating Li *, and
1
4,5
Bin Sheng *
7
1 Shanghai University of Sport, Shanghai, China
2 ROAS Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou,
China
3 Department of Computer Science, University of Sheffield, Sheffield, U.K.
4 Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China
5 School of Design, The Hong Kong Polytechnic University, Hong Kong, China
6 Shanghai Jiao Tong University Affiliated Sixth People’s Hospital, Shanghai, China
7 Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China

Abstract

This paper presents a review on the development and major advances in artificial
intelligence-assisted robotics for medical therapeutic tasks by focusing on the
current challenges emerging from the clinical application process and the research
*Corresponding authors:
Jihong Wang efforts mitigating the problems. In this review, we searched Nature, Science, and
(cylwsy@163.com) Cell using specific keywords (i.e., medical artificial intelligent robots), categorized
Huating Li research works over the past three decades based on therapeutic applications, and
(huarting99@sjtu.edu.cn)
Bin Sheng discuss the latest development and bottleneck problems of each subtopic. We first
(shengbin@sjtu.edu.cn) present a chronology of the artificial intelligence-assisted techniques developed for
Citation: Wang J, Zhu L, Yang P, medical therapeutic tasks over the past three decades and classify them according
et al., 2022, State-of-the-art: to the principles of the algorithm and its corresponding type of medical therapeutic
A taxonomy of artificial intelligence- tasks. Artificial intelligence technologies have evolved from classic machine
assisted robotics for medical
therapies and applications. Global learning methods in the early nineties to data-driven deep learning methods. We
Transl Med, 1(2): 176. subsequently derive a taxonomy of artificial intelligence-assisted therapeutic tasks
https://doi.org/10.36922/gtm.v1i2.176 in the past three decades based on the types of therapeutic tasks and the trending
Received: August 19, 2022 topics in relation to the problems. Using certain search criteria with Nature and Cell
Accepted: October 5, 2022 databases, one prosperous trend has been abstracted from highly cited research
Published Online: October 28, 2022 papers and the interpretation of our taxonomy. This unprecedented trend embodies
Copyright: © 2022 Author(s). the revolutionary development of artificial intelligence, a closer integration with
This is an Open Access article therapeutic tasks, and a more comprehensive human-robot interaction, all of which
distributed under the terms of the
Creative Commons Attribution benefit sophisticated telesurgery and microsurgery by providing surgeons with
License, permitting distribution, higher imaging accuracy and human-like tactile sensation. Our survey discusses the
and reproduction in any medium, current challenges and future trends of artificial intelligence-assisted therapeutic
provided the original work is
properly cited. tasks for the convenience of clinical research and applications, hoping that they
would help bridge the gap between entrepreneurial translation and research.
Publisher’s Note: AccScience
Publishing remains neutral with
regard to jurisdictional claims in
published maps and institutional Keywords: Artificial intelligence; Chronic disease management; Laparoscopic robots;
affiliations. Medical robotics; Medical therapies; Wearable medical robots

Volume 1 Issue 2 (2022) 1 https://doi.org/10.36922/gtm.v1i2.176