Epidemic Models for Personalised COVID-19 Isolation and Exit Policies Using Clinical Risk Predictions

Background: In mid April 2020, with more than 2.5 billion people in the world following social distancing measures due to COVID-19, governments are considering relaxing lock-down. We combined individual clinical risk predictions with epidemic modelling to examine simulations of isolation and exit policies. Methods: We developed a method to include personalised risk predictions in epidemic models based on data science principles. We extended a standard susceptible-exposed-infected-removed (SEIR) model to account for predictions of severity, defined by the risk of an individual needing intensive care in case of infection. We studied example isolation policies using simulations with the risk-extended epidemic model, using COVID-19 data and estimates in France as of mid April 2020 (4 000 patients in ICU, around 7 250 total ICU beds occupied at the peak of the outbreak, 0.5% percent of patients requiring ICU upon infection). We considered scenarios varying in the discrimination performance of a risk prediction model, in the degree of social distancing, and in the severity rate upon infection. Confidence intervals were obtained using an Approximate Bayesian Computation approach. The framework may be used with other epidemic models, with other risk predictions, and for other epidemic outbreaks. Findings: Based on the data for France as of mid April 2020, simulations indicated that an exit policy considering clinical risk predictions starting on May 11, as planned by the government, could enable to immediately relax restrictions for an extra 10% (6 700 000 people) or more of the lowest-risk population, and consequently relax the restrictions on the remaining population up to two times (or several months) faster, with only a small proportion of the population remaining in isolation for an extended period of time -- while abiding to the current ICU capacity. In contrast, implementing the same exit policy without risk predictions would exceed the ICU capacity by a multiple. Sensitivity analyses showed that when the assumed percentage of severe patients among the population decreased, or the prediction model discrimination improved, or ICU capacity increased, policies based on risk models had a greater impact on the results of epidemic simulations. At the same time, sensitivity analyses also showed that differential isolation policies require that higher risk individuals comply with recommended restrictions. In general, our simulations showed that risk prediction models could always improve policy effectiveness, keeping everything else constant, in line with value of information arguments, even for models with moderate discrimination power. Interpretation: Clinical risk prediction models should be considered to manage outbreaks using a framework as the one developed. They can inform personalised isolation policies, for example by gradually restricting (relaxing) isolation from the highest (lowest) to the lowest (highest) predicted risk individuals, when such policies are considered. This may lead to both safer and faster outcomes than what can be achieved without such prediction models. They enable personalisation of policies, which are known to improve effectiveness in other non-healthcare contexts.