Designing a medical information diagnosis platform with IoT integration

Hejian Liu; Xin Guan; Rong Bai; Tianqiao Qin; Yanrui Chen; Tao Liu

doi:10.1016/j.heliyon.2024.e25390

Designing a medical information diagnosis platform with IoT integration

Heliyon. 2024 Feb 1;10(3):e25390. doi: 10.1016/j.heliyon.2024.e25390. eCollection 2024 Feb 15.

Authors

Hejian Liu¹, Xin Guan², Rong Bai³, Tianqiao Qin⁴, Yanrui Chen⁵, Tao Liu⁶

Affiliations

¹ School of Education, Teachers College, Guangzhou University, Guangzhou, 510006, China.
² Guangzhou Xinhua University, Dongguan, 523133, China.
³ Social Sciences Division, University of Chicago, Chicago, Chicago, 60637, United States.
⁴ School of Management, Guangzhou University, Guangzhou, 510006, China.
⁵ School of Public Administration, Guangzhou University, Guangzhou, 510006, China.
⁶ School of Journalism and Communication, Guangzhou University, Guangzhou, 510006, China.

Abstract

In order to enhance the operational efficiency of the healthcare industry, this paper investigates a medical information diagnostic platform through the application of swarm and evolutionary algorithms. This paper begins with an analysis of the current development status of medical information diagnostic platforms based on Chat Generative Pre-trained Transformer (ChatGPT) and Internet of Things (IoT) technology. Subsequently, a comprehensive exploration of the advantages and disadvantages of swarm and evolutionary algorithms within the medical information diagnostic platform is presented. Further, the optimization of the swarm algorithm is achieved through reverse learning and Gaussian functions. The rationality and effectiveness of the proposed optimization algorithm are validated through horizontal comparative experiments. Experimental results demonstrate that the optimized model achieves favorable performance at the levels of minimum, average, and maximum algorithm fitness values. Additionally, preprocessing data in a 10 * 10 server configuration enhances the algorithm's fitness values. The minimum fitness value obtained by the optimized algorithm is 3.56, representing a 3 % improvement compared to the minimum value without sorting. In comparative experiments on algorithm stability, the optimized algorithm exhibits the best stability, with further enhancement observed when using sorting algorithms. Therefore, this paper not only provides a new perspective for the field of medical information diagnostics but also offers effective technical support for practical applications in medical information processing.

Keywords: Bee colony and evolutionary algorithms; Gaussian functions; Internet of things technology; Medical information diagnosis platform; Reverse learning.