Identification of high-risk COVID-19 patients using machine learning

The current COVID-19 public health crisis, caused by SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2), has produced a devastating toll both in terms of human life loss and economic disruption. In this paper we present a machine-learning algorithm capable of identifying whether a given patient (actually infected or suspected to be infected) is more likely to survive than to die, or vice-versa. We train this algorithm with historical data, including medical history, demographic data, as well as COVID-19-related information. This is extracted from a database of confirmed and suspected COVID-19 infections in Mexico, constituting the official COVID-19 data compiled and made publicly available by the Mexican Federal Government. We demonstrate that the proposed method can detect high-risk patients with high accuracy, in each of four identified clinical stages, thus improving hospital capacity planning and timely treatment. Furthermore, we show that our method can be extended to provide optimal estimators for hypothesis-testing techniques commonly-used in biological and medical statistics. We believe that our work could be of use in the context of the current pandemic in assisting medical professionals with real-time assessments so as to determine health care priorities.

Modelling intensive care unit capacity under different epidemiological scenarios of the COVID-19 pandemic in three Western European countries

Background The coronavirus disease 2019 (COVID-19) pandemic has placed enormous strain on intensive care units (ICUs) in Europe. Ensuring access to care, irrespective of COVID-19 status, in winter 2020–2021 is essential. Methods An integrated model of hospital capacity planning and epidemiological projections of COVID-19 patients is used to estimate the demand for and resultant spare capacity of ICU beds, staff and ventilators under different epidemic scenarios in France, Germany and Italy across the 2020–2021 winter period. The effect of implementing lockdowns triggered by different numbers of COVID-19 patients in ICUs under varying levels of effectiveness is examined, using a ‘dual-demand’ (COVID-19 and non-COVID-19) patient model. Results Without sufficient mitigation, we estimate that COVID-19 ICU patient numbers will exceed those seen in the first peak, resulting in substantial capacity deficits, with beds being consistently found to be the most constrained resource. Reactive lockdowns could lead to large improvements in ICU capacity during the winter season, with pressure being most effectively alleviated when lockdown is triggered early and sustained under a higher level of suppression. The success of such interventions also depends on baseline bed numbers and average non-COVID-19 patient occupancy. Conclusion Reductions in capacity deficits under different scenarios must be weighed against the feasibility and drawbacks of further lockdowns. Careful, continuous decision-making by national policymakers will be required across the winter period 2020–2021.

Identification of high-risk COVID-19 patients using machine learning

The current COVID-19 public health crisis, caused by SARSCoV-2 (severe acute respiratory syndrome coronavirus 2), has produced a devastating toll both in terms of human life loss and economic disruption. In this paper we present a machine-learning algorithm capable of identifying whether a given patient (actually infected or suspected to be infected) is more likely to survive than to die, or vice-versa. We train this algorithm with historical data, including medical history, demographic data, as well as COVID-19-related information. This is extracted from a database of confirmed and suspected COVID-19 infections in Mexico, constituting the official COVID-19 data compiled and made publicly available by the Mexican Federal Government. We demonstrate that the proposed method can detect high-risk patients with high accuracy, in each of four identified treatment stages, thus improving hospital capacity planning and timely treatment. Furthermore, we show that our method can be extended to provide optimal estimators for hypothesis-testing techniques commonly-used in biological and medical statistics. We believe that our work could be of use in the context of the current pandemic in assisting medical professionals with real-time assessments so as to determine health care priorities.

CPAS: the UK’s national machine learning-based hospital capacity planning system for COVID-19

The coronavirus disease 2019 (COVID-19) global pandemic poses the threat of overwhelming healthcare systems with unprecedented demands for intensive care resources. Managing these demands cannot be effectively conducted without a nationwide collective effort that relies on data to forecast hospital demands on the national, regional, hospital and individual levels. To this end, we developed the COVID-19 Capacity Planning and Analysis System (CPAS)—a machine learning-based system for hospital resource planning that we have successfully deployed at individual hospitals and across regions in the UK in coordination with NHS Digital. In this paper, we discuss the main challenges of deploying a machine learning-based decision support system at national scale, and explain how CPAS addresses these challenges by (1) defining the appropriate learning problem, (2) combining bottom-up and top-down analytical approaches, (3) using state-of-the-art machine learning algorithms, (4) integrating heterogeneous data sources, and (5) presenting the result with an interactive and transparent interface. CPAS is one of the first machine learning-based systems to be deployed in hospitals on a national scale to address the COVID-19 pandemic—we conclude the paper with a summary of the lessons learned from this experience.