• Corpus ID: 233296396

Risk score learning for COVID-19 contact tracing apps

@inproceedings{Murphy2021RiskSL,
  title={Risk score learning for COVID-19 contact tracing apps},
  author={Kevin Murphy and Abhishek Kumar and Stelios Serghiou},
  booktitle={MLHC},
  year={2021}
}
Digital contact tracing apps for COVID, such as the one developed by Google and Apple, need to estimate the risk that a user was infected during a particular exposure, in order to decide whether to notify the user to take precautions, such as entering into quarantine, or requesting a test. Such risk score models contain numerous parameters that must be set by the public health authority. In this paper, we show how to automatically learn these parameters from data. Our method needs access to… 

Figures from this paper

COVID-19 Risk Minimization Decision Making Strategy Using Data-Driven Model
TLDR
The DPTTs and Data-Driven Epidemic Intelligence Strategies (DDEIS) are compared and a novel solution to overcome them are proposed for epidemic resurgence risk minimization, guaranteeing public health safety and quick return of cities to normalcy.

References

SHOWING 1-10 OF 29 REFERENCES
Quantifying SARS-CoV-2 infection risk within the Apple/Google exposure notification framework to inform quarantine recommendations
TLDR
This work model uncertainty in the shape of an exhaled virus-containing plume, inhalation parameters, and distance as a function of Bluetooth attenuation and calibrate an exponential dose-response curve on the basis of the infection probabilities of household contacts to reduce SARS-CoV-2 transmission.
Modeling the combined effect of digital exposure notification and non-pharmaceutical interventions on the COVID-19 epidemic in Washington state
TLDR
In a model in which 15% of the population participated, it is found that digital exposure notification systems could reduce infections and deaths by approximately 8% and 6%, effectively complementing traditional contact tracing.
The epidemiological impact of the NHS COVID-19 App.
TLDR
The impact of the NHS COVID-19 app for England and Wales, from its launch on 24 September 2020 through to the end of December 2020, is investigated to provide evidence for continued development and deployment of such apps in populations that are awaiting full protection from vaccines.
Digital proximity tracing app notifications lead to faster quarantine in non-household contacts: results from the Zurich SARS-CoV-2 Cohort Study
TLDR
These findings constitute the first evidence that DPT may reach exposed contacts faster than MCT, leading to earlier quarantine and potential interruption of SARS-CoV-2 transmission chains.
Performance of Digital Contact Tracing Tools for COVID-19 Response in Singapore: Cross-Sectional Study
TLDR
Although the tag-based RTLS performed well for contact tracing in a clinical setting, its implementation in the community would be more challenging than TraceTogether, which had a much lower sensitivity.
CRISP: A Probabilistic Model for Individual-Level COVID-19 Infection Risk Estimation Based on Contact Data
TLDR
This is the first model with efficient inference for COVID-19 infection spread based on individual-level contact data, and can be parametrized by the reproduction factor $R_0$ and exhibits population-level infectiousness and recovery time series similar to those of the classical SEIR model.
Inherent privacy limitations of decentralized contact tracing apps
TLDR
In this brief communication, a few of these inherent privacy limitations of any decentralized automatic contact tracing system are discussed.
Early Evidence of Effectiveness of Digital Contact Tracing for SARS-CoV-2 in Switzerland
TLDR
It is demonstrated proof-of-principle that digital contact tracing reaches exposed contacts, who then test positive for SARS-CoV-2, indicating thatdigital contact tracing is an effective complementary tool for controlling the spread of Sars-Cov-2.
Quantifying SARS-CoV-2 transmission suggests epidemic control with digital contact tracing
TLDR
A mathematical model for infectiousness was developed to estimate the basic reproductive number R0 and to quantify the contribution of different transmission routes and the requirements for successful contact tracing, and the combination of two key parameters needed to reduce R0 to less than 1 was determined.
A population-based controlled experiment assessing the epidemiological impact of digital contact tracing
TLDR
A 4-week population-based controlled experiment that took place in La Gomera between June and July 2020, where the epidemiological impact of the Spanish DCT app Radar Covid was assessed, provides experimental evidence of the potential usefulness of DCT during an epidemic outbreak in a real population.
...
...