The COVID-19 adaptive risk predictor (SCARP), an algorithmic tool

The COVID-19 adaptive risk predictor (SCARP), an algorithmic tool, can estimate the risk of progression to serious disease or death in adult patients (18 years and older) hospitalised with COVID-19 on a 1-day and 7-day basis. Given the current crisis, this calculator can prove to be an indispensable tool for Indian clinicians in the front line of the pandemic.

Severe COVID-19 Adaptive Risk Predictor (SCARP) calculator: How to use

To begin using SCARP, one needs to insert the patient’s details in the SCARP calculator. The clinical predictors’ inputs would be entered consecutively (additional boxes will appear as you enter information). The sequential inputs are calculated adaptively depending on the data entered, allowing the calculator to be customised for each patient. The 1-day and 7-day risk predictions will be issued, as well as visual representations of summary decision trees at each level, accessible through the prediction logic tabs.

The severe COVID-19 adaptive risk prediction (SCARP) calculator was created by a team of investigators at Johns Hopkins University School of Medicine. It accurately identifies the risk of progression to severe illness or death in hospitalised patients with COVID-19. The calculator’s conception and success were detailed in a recent Annals of Internal Medicine paper.

The investigators developed the SCARP calculator using data from 3163 COVID-19 patients hospitalised in the JH-CROWN: COVID-19 Precision Medicine Analytics Platform Registry. The list collects data from hospitals affiliated with Johns Hopkins Medicine. The register collected data on demographic profiles, the cause of entry, comorbidity, time-varying vitals, laboratory measurements, and clinical seriousness. The researchers used the random forest for longevity, longitudinal, and multivariate analysis of data (RF-SLAM) to predict 1- and 7-day chances of progression to severe COVID-19 infection or death for every day within the first 14 days of hospitalisation.

Summary decision trees show that the summary tree for 1-day risk prediction captures up to 89 per cent of the variation in 1-day RF-SLAM risk predictions. Additionally, the review tree for the 7-day risk prediction captured up to 90% of the variation in the 7-day RF-SLAM risk predictions for severe COVID-19 or mortality. SCARP calculator is online and easy to use.

Parameters to be mentioned in SCARP


Respiratory rate (highest in past 6 hours)

Days since hospital admission

Supplemental oxygen delivery (L/min) (O2 requirement when most hypoxic in past 6 hours)

Oxygen saturation (lowest value in the past 6 hours)

The risk calculator gives the risk of severe illness or death predicted on day 1 and day 7

Drawback of SCARP

According to the research investigators, a drawback of the SCARP tool production approach was the use of evidence from a particular health system, which could result in problems of generalisability.

Potential clinical use in India

India is threatened by a second outbreak of the virus that is more lethal and destructive. India’s coronavirus case count tops 12 million, making it the third-largest in the world after the United States and Brazil. It has recorded over 1,60,000 deaths as a result of the outbreak. On 30 March, the infection doubling rate – or the time required for the number of coronavirus cases to double – was less than 170 days, down from a peak of 590 days on 28 February. India is witnessing record coronavirus cases and deaths, despite an unprecedented lack of medical oxygen and hospital beds, as a vicious second wave of COVID-19 overwhelms the country’s underfunded, vulnerable healthcare system.

SCARP has the potential to serve as a quantitative method to assist Indian clinicians in treating patients hospitalised with COVID-19, especially those with complicated and seemingly uncertain clinical courses. Besides this, the instrument may be used to assist hospital operations in determining the most efficient way to allocate services to satisfy the ever-changing need for intensive care.

Reference: Wongvibulsin S, Garibaldi BT, Antar AAR, et al. Development of severe COVID-19 adaptive risk predictor (SCARP), a calculator to predict severe disease or death in hospitalized patients with COVID-19. Ann Intern Med. Published online March 2, 2021. doi:10.7326/M20-6754


Disclaimer- The views and opinions expressed in this article are those of the author’s and do not necessarily reflect the official policy or position of M3 India.

The author, Dr Monish S Raut is a Consultant in Cardiothoracic Vascular Anaesthesiology. His area of expertise is perioperative management and echocardiography with numerous publications in various national and international indexed journals.

Related Articles

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: