Back

Covid-19 clinical data analysis using Ball Mapper

Dlotko, P.; Rudkin, S.

2020-04-15 intensive care and critical care medicine
10.1101/2020.04.10.20061374 medRxiv
Show abstract

In this note we provide a result of analysis of blood test data from patients with SARS-Cov-2 using Ball Mapper Algorithm. We observe that patients with the virus and in particularly patients who end up in Intensive Care Unit have quite narrow values of those parameters. Please note that this is a preliminary work and it need to be validated on much larger dataset which we are trying to acquire at the moment.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

1
PLOS ONE
● 5266 papers in training set
Top 8%
19.5%
Similar papers in this journal
2
Cureus
○ 68 papers in training set
Top 0.1%
10.2%
Similar papers in this journal
3
Scientific Reports
○ 3612 papers in training set
Top 6%
8.3%
Similar papers in this journal
4
F1000Research
○ 88 papers in training set
Top 0.2%
4.5%
Similar papers in this journal
5
Frontiers in Medicine
○ 120 papers in training set
Top 0.6%
4.3%
Similar papers in this journal
6
Heliyon
○ 152 papers in training set
Top 1.0%
3.6%
50% of probability mass above
7
BMC Medical Informatics and Decision Making
○ 43 papers in training set
Top 0.7%
2.9%
8
Applied Sciences
○ 25 papers in training set
Top 0.1%
2.9%
9
Informatics in Medicine Unlocked
○ 22 papers in training set
Top 0.3%
2.6%
10
Bioinformatics
◐ 1204 papers in training set
Top 6%
2.6%
11
Frontiers in Public Health
○ 148 papers in training set
Top 2%
2.6%
12
Frontiers in Molecular Biosciences
○ 102 papers in training set
Top 0.4%
2.2%
13
PLOS Computational Biology
● 1863 papers in training set
Top 12%
2.2%
14
BMC Bioinformatics
○ 457 papers in training set
Top 4%
1.5%
15
PeerJ
◐ 308 papers in training set
Top 6%
1.4%
16
IEEE/ACM Transactions on Computational Biology and Bioinformatics
● 38 papers in training set
Top 0.7%
1.2%
17
JMIRx Med
◐ 32 papers in training set
Top 1%
1.2%
18
Expert Systems with Applications
○ 11 papers in training set
Top 0.2%
1.2%
19
BioMed Research International
○ 28 papers in training set
Top 1%
1.2%
20
International Journal of Medical Informatics
○ 26 papers in training set
Top 0.9%
1.2%
21
Wellcome Open Research
○ 67 papers in training set
Top 0.8%
1.1%
22
Computer Methods and Programs in Biomedicine
○ 28 papers in training set
Top 0.7%
1.1%
23
Genomics
○ 64 papers in training set
Top 1%
1.1%
24
Annals of Translational Medicine
○ 18 papers in training set
Top 0.4%
1.1%
25
Frontiers in Neurology
○ 102 papers in training set
Top 2%
1.1%
26
Biomolecules
○ 100 papers in training set
Top 2%
0.9%
27
Viruses
○ 332 papers in training set
Top 4%
0.9%
28
Frontiers in Physiology
○ 106 papers in training set
Top 3%
0.6%
29
Mathematical Biosciences and Engineering
● 23 papers in training set
Top 1%
0.5%
30
Biomedical Signal Processing and Control
○ 22 papers in training set
Top 0.8%
0.5%

"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.