Contact Tracing Strategy with Decision Support System using Machine Learning and Artificial Intelligence Concepts
Contact tracing has become an essential public health strategy during the ongoing COVID-19 pandemic. When an individual tests positive for the SARS-CoV-2 virus, contact tracers work to identify and notify that person’s close contacts to contain further spread (CDC, 2022). However, contact tracing at scale presents numerous challenges. Manual contact tracing is labor-intensive and time-consuming, while relying solely on infected individuals’ recall of their interactions risks missing exposures.
To address these challenges, researchers and technology companies have explored leveraging machine learning (ML) and artificial intelligence (AI) to enhance digital contact tracing efforts. ML and AI show promise for automating and expediting parts of the contact tracing process. For example, ML algorithms can analyze location data to infer likely contacts based on proximity over time (Ferretti et al., 2020). AI-powered chatbots and virtual agents may assist human contact tracers in handling high case volumes (Anthropic, 2021). Decision support systems incorporating ML risk prediction could also help prioritize follow-up with higher-risk contacts.
While raising privacy and ethics concerns that require mitigation, digital tools augmented with ML and AI may help contact tracing scale to pandemic levels of transmission while minimizing delays between exposure and notification. Used transparently and for public health purposes alone, these technologies could support health departments’ contact tracing missions. Overall, an optimized contact tracing strategy may integrate automated digital contact matching with human follow-up, utilizing ML and AI where they can streamline the process while protecting individuals’ privacy and civil liberties.
In summary, ML and AI show promise for enhancing digital contact tracing efforts during public health emergencies like the COVID-19 pandemic. Automated contact matching and risk prediction through decision support systems could help scale contact tracing to meet high case volumes while minimizing delays. When developed and applied ethically, these emerging technologies may strengthen health departments’ response capacity. Looking ahead, continued research and piloting will be important to refine how ML and AI can best augment, rather than replace, human-led public health strategies like contact tracing.
Ferretti, L., Wymant, C., Kendall, M., Zhao, L., Nurtay, A., Abeler-Dörner, L., Parker, M., Bonsall, D., & Fraser, C. (2020). Quantifying SARS-CoV-2 transmission suggests epidemic control with digital contact tracing. Science, 368(6491), eabb6936. https://doi.org/10.1126/science.abb6936
Anthropic. (2021, March 18). How AI can help scale COVID-19 contact tracing. Anthropic. https://www.anthropic.com/blog/how-ai-can-help-scale-covid-19-contact-tracing
Centers for Disease Control and Prevention. (2022, February 11). Contact tracing for COVID-19. Centers for Disease Control and Prevention. https://www.cdc.gov/coronavirus/2019-ncov/daily-life-coping/contact-tracing.html
Public Health Advocacy: Improving Access to Healthcare and Addressing Social Determinants of Health
Public Health Advocacy: Improving Access to Healthcare and Addressing Social Determinants of Health 1. Introduction Public health advocacy is an integral part of public health practice. The American Public Health Association (APHA) defines advocacy as “the act of recommending, supporting, and arguing for a certain cause or policy.” In the context of public health, advocacy […]
