Author: Shoer, Saar; Karady, Tal; Keshet, Ayya; Shilo, Smadar; Rossman, Hagai; Gavrieli, Amir; Meir, Tomer; Lavon, Amit; Kolobkov, Dmitry; Kalka, Iris; Godneva, Anastasia; Cohen, Ori; Kariv, Adam; Hoch, Ori; Zer-Aviv, Mushon; Castel, Noam; Sudre, Carole; Zohar, Anat Ekka; Irony, Angela; Spector, Tim; Geiger, Benjamin; Hizi, Dorit; Shalev, Varda; Balicer, Ran; Segal, Eran
Title: A prediction model to prioritize individuals for SARS-CoV-2 test built from national symptom surveys Cord-id: dnmote9j Document date: 2020_10_10
ID: dnmote9j
Snippet: Background The gold standard for COVID-19 diagnosis is detection of viral RNA through PCR. Due to global limitations in testing capacity, effective prioritization of individuals for testing is essential. Methods We devised a model estimating the probability of an individual to test positive for COVID-19 based on answers to 9 simple questions that have been associated with COVID-19 infection. Our model was devised from a subsample of a national symptom survey that was answered over 2 million time
Document: Background The gold standard for COVID-19 diagnosis is detection of viral RNA through PCR. Due to global limitations in testing capacity, effective prioritization of individuals for testing is essential. Methods We devised a model estimating the probability of an individual to test positive for COVID-19 based on answers to 9 simple questions that have been associated with COVID-19 infection. Our model was devised from a subsample of a national symptom survey that was answered over 2 million times in Israel in its first 2 months and a targeted survey distributed to all residents of several cities in Israel. Overall, 43,752 adults were included, from which 498 self-reported as being COVID-19 positive. Findings Our model was validated on a held-out set of individuals from Israel where it achieved an auROC of 0.737 (CI: 0.712-0.759), auPR of 0.144 (CI: 0.119-0.177) and demonstrated its applicability outside of Israel in an independently-collected symptom survey dataset from the U.S., U.K. and Sweden. Our analyses revealed interactions between several symptoms and age, suggesting variation in the clinical manifestation of the disease in different age groups. Conclusions our tool can be used online and without exposure to suspected patients, thus suggesting worldwide utility in combating COVID-19 by better directing the limited testing resources through prioritization of individuals for testing, thereby increasing the rate at which positive individuals can be identified. Moreover, individuals at high risk for a positive test result can be isolated prior to testing.
Search related documents:
Co phrase search for related documents- actively contact and machine learning model: 1
- actual number and additional cost: 1
- actual number and additional validation: 1
- actual number and logistic regression: 1, 2
- actual number and low prevalence: 1, 2
- actual number and machine learning: 1, 2, 3, 4, 5, 6, 7, 8, 9
- actual number and machine learning model: 1, 2
- additional cost and logistic regression: 1, 2, 3
- additional cost and low prevalence: 1
- additional cost and machine learning: 1, 2, 3
- additional feature and logistic regression: 1
- additional feature and machine learning: 1
- additional symptom and logistic regression: 1
- additional symptom and machine learning: 1
- additional validation and logistic regression: 1, 2
- additional validation and low prevalence: 1
- additional validation and machine learning: 1, 2, 3, 4, 5, 6, 7, 8, 9
- additive explanation and logistic regression: 1, 2, 3
- additive explanation and logistic regression model: 1
Co phrase search for related documents, hyperlinks ordered by date