The intersection of artificial intelligence with qualitative or mixed methods for communicable disease research: a scoping review

Comprehensive Summary

Fieldhouse et al. examined how AI and machine learning (ML) are incorporated into qualitative and mixed methods (MM) research on communicable diseases. From 1,342 records, 29 publications met inclusion criteria. Across studies, five main categories of AI/ML techniques and three categories of utility were identified, with most research focusing on large-scale analyses of social media during public health emergencies (e.g., COVID-19). Common approaches included natural language processing, topic modeling, and deep learning. The authors stress the importance of “true integration,” where AI/ML methods are applied iteratively with qualitative approaches and human oversight to ensure contextual sensitivity, mitigate cultural/linguistic bias, and enhance rigor.

Outcomes and Implications

This research shows how AI can enhance the speed and depth of qualitative and mixed-methods (MM) analysis, enabling real-time surveillance, predictive analytics, and more personalized interventions. By combining patient experiences with epidemiological data from sources like social media, health records, and environmental surveillance, public health officials can make faster and more informed decisions. Projects such as the Virus Intelligence and Strategic Threat Assessment (VISTA) illustrate the promise of integrating AI with qualitative insights, suggesting that broader clinical and public health use may be feasible in the near future.