Leveraging artificial intelligence-mediated communication for cancer prevention and control and drug addiction: A systematic review

Abstract

Objective

To conduct a systematic review on Artificial Intelligence-Mediated Communication (AIMC) behavioral interventions in cancer prevention/control and substance use.

Methods

Eight databases were searched from 2017 to 2022 using the Population Intervention Control Outcome Study (PICOS) framework. We synthesized findings of AIMC-based interventions for adult populations in cancer prevention/control or substance use, applying SIGN Methodology Checklist 2 for quality assessments and reviewing retention and engagement.

Results

Initial screening identified 187 studies; seven met inclusion criteria, involving 2768 participants. Females comprised 67.6% (n = 1870). Mean participant age was 42.73 years (SD = 7.00). Five studies demonstrated significant improvements in substance use recovery, physical activity, genetic testing, or dietary habits.

Conclusions

AIMC shows promise in enhancing health behaviors, but further exploration is needed on privacy risks, biases, safety concerns, chatbot features, and serving underserved populations.

Implications

There is a critical need to foster comprehensive fully powered studies and collaborations between technology developers, healthcare providers, and researchers. Policymakers can facilitate the responsible integration of AIMC technologies into healthcare systems, ensuring equitable access and maximizing their impact on public health outcomes.

Lay Summary

Researchers conducted a thorough review of how Artificial Intelligence-Mediated Communication (AIMC) can influence behavior in cancer prevention/control and substance use. They analyzed seven studies involving nearly 2800 adults, mostly women, focusing on outcomes like substance use recovery and lifestyle changes. Six studies reported randomized controlled trials, focusing on interventions for substance use and other health behaviors. Several studies showed promising results, such as improved physical activity and dietary habits. Studies varied in design: one was a single-arm trial, while others had multiple arms or stratified randomization. Most trials used validated outcome measures and reported high retention rates. Despite promising results in behavior change, sustainability beyond treatment was rarely reported. Studies highlighted demographic diversity and employed intent-to-treat or per-protocol analyses. Challenges included blinding issues and potential biases. Overall, the trials emphasized the need for comprehensive, rigorous research in AI-mediated health interventions. The review highlighted the need for more research on privacy concerns, biases, and the effectiveness of AIMC tools, especially for underserved populations. The findings suggest that AIMC could play a significant role in improving public health, but more robust studies and collaborations are necessary to maximize its impact and ensure fair access in healthcare systems.