ABSTRACT. The objective of this paper is to systematically review how generative artificial intelligence can enhance treatment accuracy and efficiency, patient communication and outcomes, clinical decision support, computer-aided detection and diagnosis processes, and medical imaging analysis. The findings and analyses highlight that ChatGPT and machine-learning-based expertise and judgment in personalized care can provide adequate treatment recommendations in conformity with the patient clinical presentation, disease severity, and co-diagnoses. Throughout March 2023, a quantitative literature review of the Web of Science, Scopus, and ProQuest databases was performed, with search terms including “generative artificial intelligence-driven healthcare systems” + “medical imaging analysis,” “clinical decision support,” and “patient engagement and monitoring.” As research published in 2023 was inspected, only 176 articles satisfied the eligibility criteria. By taking out controversial or ambiguous findings (insufficient/irrelevant data), outcomes unsubstantiated by replication, too general material, or studies with nearly identical titles, I selected 33 mainly empirical sources. Data visualization tools: Dimensions (bibliometric mapping) and VOSviewer (layout algorithms). Reporting quality assessment tool: PRISMA. Methodological quality assessment tools include: AMSTAR, Dedoose, Distiller SR, and SRDR.

Keywords: ChatGPT; generative artificial intelligence; healthcare system; medical imaging analysis; clinical decision support; patient engagement and monitoring

How to cite: Hayward, R. (2023). “Generative Artificial Intelligence-driven Healthcare Systems in Medical Imaging Analysis, in Clinical Decision Support, and in Patient Engagement and Monitoring,” Contemporary Readings in Law and Social Justice 15(1): 63–80. doi: 10.22381/CRLSJ15120234.

Received 26 March 2023 • Received in revised form 24 July 2023
Accepted 27 July 2023 • Available online 30 July 2023