Back

Machine Learning the Phenomenology of COVID-19 From Early Infection Dynamics

Magdon-Ismail, M.

2020-03-20 health informatics
10.1101/2020.03.17.20037309 medRxiv
Show abstract

We present a robust data-driven machine learning analysis of the COVID-19 pandemic from its early infection dynamics, specifically infection counts over time. The goal is to extract actionable public health insights. These insights include the infectious force, the rate of a mild infection becoming serious, estimates for asymtomatic infections and predictions of new infections over time. We focus on USA data starting from the first confirmed infection on January 20 2020. Our methods reveal significant asymptomatic (hidden) infection, a lag of about 10 days, and we quantitatively confirm that the infectious force is strong with about a 0.14% transition from mild to serious infection. Our methods are efficient, robust and general, being agnostic to the specific virus and applicable to different populations or cohorts.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Patterns
○ 78 papers in training set
Top 0.1%
19.3%
Similar papers in this journal
2
Nature Communications
○ 5641 papers in training set
Top 13%
13.5%
Similar papers in this journal
3
Scientific Reports
○ 3612 papers in training set
Top 4%
10.2%
Similar papers in this journal
4
Nature Medicine
○ 125 papers in training set
Top 0.2%
6.5%
Similar papers in this journal
5
Nature Machine Intelligence
○ 70 papers in training set
Top 0.9%
2.9%
Similar papers in this journal
50% of probability mass above
6
Biostatistics
◐ 24 papers in training set
Top 0.1%
2.8%
7
PLOS Computational Biology
● 1863 papers in training set
Top 11%
2.5%
8
Science Advances
● 1243 papers in training set
Top 14%
2.5%
9
Communications Medicine
○ 113 papers in training set
Top 1%
2.2%
10
npj Digital Medicine
○ 118 papers in training set
Top 2%
2.2%
11
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 25%
2.0%
12
Journal of The Royal Society Interface
● 235 papers in training set
Top 2%
1.8%
13
Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences
● 15 papers in training set
Top 0.1%
1.8%
14
PNAS Nexus
◐ 159 papers in training set
Top 1%
1.6%
15
PLOS ONE
● 5266 papers in training set
Top 48%
1.6%
16
Journal of Medical Internet Research
◐ 87 papers in training set
Top 2%
1.6%
17
Bioinformatics
◐ 1204 papers in training set
Top 7%
1.2%
18
Communications Biology
○ 993 papers in training set
Top 20%
1.2%
19
iScience
○ 1154 papers in training set
Top 24%
1.2%
20
eLife
● 5828 papers in training set
Top 57%
1.2%
21
Nature
○ 645 papers in training set
Top 10%
0.9%
22
Mathematics
○ 11 papers in training set
Top 0.2%
0.9%
23
JMIR Public Health and Surveillance
◐ 45 papers in training set
Top 1%
0.9%
24
Frontiers in Artificial Intelligence
○ 20 papers in training set
Top 0.6%
0.9%
25
Communications Physics
○ 14 papers in training set
Top 0.1%
0.9%
26
Nature Methods
○ 385 papers in training set
Top 7%
0.6%
27
Physical Review E
● 112 papers in training set
Top 1%
0.6%
28
Nature Physics
○ 45 papers in training set
Top 0.5%
0.6%
29
Neuron
○ 337 papers in training set
Top 5%
0.6%
30
Nature Computational Science
○ 55 papers in training set
Top 2%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.