Back
Top 23%
24.2%
#1
24.2%
Top 18%
9.8%
Top 3%
6.5%
Top 4%
5.5%
Top 14%
2.1%
Top 1%
1.7%
Top 11%
1.7%
Top 18%
1.5%
Top 26%
1.3%
Top 4%
1.0%
Top 43%
1.0%
Top 13%
0.8%
Top 28%
0.5%
Top 10%
0.5%
Top 20%
0.5%
Top 10%
0.5%
Top 6%
0.5%
Top 4%
0.5%
Top 12%
0.5%
Top 71%
0.5%
Top 66%
0.5%
Feature Selection for an Explainability Analysis in Detection of COVID-19 Active Cases from Facebook User-Based Online Surveys
2023-06-05
public and global health
Title + abstract only
View on medRxiv
Show abstract
In this paper, we introduce a machine-learning approach to detecting COVID-19-positive cases from self-reported information. Specifically, the proposed method builds a tree-based binary classification model that includes a recursive feature elimination step. Based on Shapley values, the recursive feature elimination method preserves the most relevant features without compromising the detection performance. In contrast to previous approaches that use a limited set of selected features, the machin...
Predicted journal destinations
1
PLOS ONE
1737 training papers
2
Journal of Medical Internet Research
81 training papers
3
Scientific Reports
701 training papers
4
npj Digital Medicine
85 training papers
5
Frontiers in Public Health
135 training papers
6
BMC Public Health
148 training papers
7
JMIR Public Health and Surveillance
45 training papers
8
PLOS Digital Health
88 training papers
9
International Journal of Environmental Research and Public Health
116 training papers
10
PLOS Global Public Health
287 training papers
11
JMIR Formative Research
31 training papers
12
eLife
262 training papers
13
PLOS Computational Biology
141 training papers
14
Cureus
64 training papers
15
Science of The Total Environment
80 training papers
16
Heliyon
57 training papers
17
Public Health
34 training papers
18
JMIRx Med
29 training papers
19
Journal of Public Health
23 training papers
20
Epidemics
96 training papers
21
BMJ Open
553 training papers
22
Nature Communications
483 training papers