ABSTRACT. The present study systematically reviews the existing research on how artificial intelligence-based medical and digital health technologies can be deployed in disease and condition prevention, diagnosis, treatment, and monitoring. My findings indicate that, based on spatial computing techniques and pathology data, generative artificial intelligence algorithms can interpret medical images and handle patient data and symptoms. I contribute to the literature by clarifying that ChatGPT can assist in diagnosing medical conditions and in articulating physiological parameter monitoring and personalized healthcare services. Throughout March 2023, a quantitative literature review of the Web of Science, Scopus, and ProQuest databases was performed, with search terms including “healthcare generative artificial intelligence tools” + “synthetic patient cases,” “medical image interpretation,” and “diagnosis and treatment plans.” As research published in 2023 was inspected, only 171 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 26 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; healthcare generative artificial intelligence tool; synthetic patient cases; medical image interpretation; diagnosis and treatment plan

How to cite: Barker, M. (2023). “Healthcare Generative Artificial Intelligence Tools in Synthetic Patient Cases, in Medical Image Interpretation, and in Diagnosis and Treatment Plans,” Contemporary Readings in Law and Social Justice 15(1): 171–187. doi: 10.22381/CRLSJ151202310.

Received 22 March 2023 • Received in revised form 26 July 2023
Accepted 29 July 2023 • Available online 30 July 2023