Artificial intelligence-based risk assessment tools for sexual, reproductive and mental health: a systematic review.

Abstract

Background: Artificial intelligence (AI), which emulates human intelligence through knowledge-based heuristics, has transformative impacts across various industries. In the global healthcare sector, there is a pressing need for advanced risk assessment tools due to the shortage of healthcare workers to manage the health needs of the growing population effectively. AI-based tools such as triage systems, symptom checkers, and risk prediction models are poised to democratize healthcare. This systematic review aims to comprehensively assess the current landscape of AI tools in healthcare and identify areas for future research, focusing particularly on sexual reproductive and mental health.

Methods: Adhering to PRISMA guidelines, this review utilized data from seven databases: Science Direct, PubMed, SAGE, ACM Digital Library, Springer, IEEE Xplore, and Wiley. The selection process involved a rigorous screening of titles, abstracts, and full-text examinations of peer-reviewed articles published in English from 2018 to 2023. To ensure the quality of the studies, two independent reviewers applied the PROBAST and QUADAS-2 tools to evaluate the risk of bias in prognostic and diagnostic studies, respectively. Data extraction was also independently conducted.

Results: Out of 1743 peer-reviewed articles screened, 63 articles (3.61%) met the inclusion criteria and were included in this study. These articles predominantly utilized clinical vignettes, demographic data, and medical data from online sources. Of the studies analyzed, 61.9% focused on sexual and reproductive health, while 38.1% addressed mental health assessment tools. The analysis revealed an increasing trend in research output over the review period and a notable disparity between developed and developing countries. The review highlighted that AI-based systems could outperform traditional clinical methods when implemented correctly.

Conclusions: The findings indicate that integrating AI-based models into existing clinical systems can lead to substantial improvements in healthcare delivery and outcomes. However, future research should prioritize obtaining larger and more diverse datasets, including those from underrepresented populations, to reduce biases and disparities. Additionally, for AI-based healthcare interventions to be widely adopted, transparency and ethical considerations must be addressed, ensuring these technologies are used responsibly and effectively in practical scenarios.