Infectious diseases such as COVID-19 are known to spread rapidly from person to person. In the absence of an effective vaccine or drug treatment, infection control relies on the rapid identification and isolation of persons with infection, a process called contact tracing. Contact tracing processes used today are manual, time-consuming, error-prone, and do not scale. Proposals to scale contact tracing through the use of smartphones pose risks to individuals’ privacy and confidentiality.

Poirot is a privacy-preserving system that users smartphones to detect exposure to potentially infectious individuals and provide recommendations for infection control. There are many proposals for performing privacy-preserving automated contact tracing today. While all of these proposals are a necessary first step, Poirot strives to look beyond these solutions to be a more effective exposure detection tool.

Proactive Alerts

Due to delays in testing and potential asymptomatic transmission of COVID-19, it may be too late to alert only those who come in contact with confirmed cases. If a known carrier comes in close contact with another individual who then comes in close contact with you, you could be at risk even if the status of the second person is still unconfirmed. Poirot can identify this situation and proactively recommend you to take precautions.

Personalized Assessment

Contact proximity alone is not enough to determine your exposure risk. For example, did you wear any personal protective equipment (PPE)? Poirot will ask you to provide additional information on an encounter that potentially put you at high risk, and use it to reassess the risk in a personalized way.                                                                                                                                                                                                               

Data from Trusted Sources

We cannot assume everybody would use our app from day one. For Poirot to work, we allow it to incorporate data from trusted sources, such as confirmed cases and positive testing results, and update your risk assessment automatically based on your recent contacts.                                                                                                                                                                                                                                                                 

Our team consists of a group of researchers at Duke University from the Computer Science Department and the  Department of Family Medicine and Community Health and Duke Global Health Institute. It is also advised by an expert panel spanning global health and computer science.

Privacy in statistical databases

Applied cryptography, Blockchains

Digital health intervention development and evaluation

Data-intensive systems and scalable data analytics