Back

Beta regression with spatio-temporal effects as a tool for hospital impact analysis of initial phase epidemics: the case of COVID-19 in Spain

Jannes, G.; Barreal, J.

2020-06-29 health economics
10.1101/2020.06.27.20141614 medRxiv
Show abstract

COVID-19 has put an extraordinary strain on medical staff around the world, but also on hospital facilities and the global capacity of national healthcare systems. In this paper, Beta regression is introduced as a tool to analyze the rate of hospitalization and the proportion of Intensive Care Unit admissions over both hospitalized and diagnosed patients, with the aim of explaining as well as predicting, and thus allowing to better anticipate, the impact on hospital resources during an early-phase epidemic. This is applied to the initial phase COVID-19 pandemic in Spain and its different regions from 20-Feb to 08-Apr of 2020. Spatial and temporal factors are included in the Beta distribution through a precision factor. The model reveals the importance of the lagged data of hospital occupation, as well as the rate of recovered patients. Excellent agreement is found for next-day predictions, while even for multiple-day predictions (up to 12 days), robust results are obtained in most cases in spite of the limited reliability and consistency of the data.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

1
IEEE Access
● 35 papers in training set
Top 0.1%
23.4%
Similar papers in this journal
2
PLOS ONE
● 5266 papers in training set
Top 8%
19.4%
Similar papers in this journal
3
Frontiers in Public Health
○ 148 papers in training set
Top 0.1%
15.8%
Similar papers in this journal
50% of probability mass above
4
Scientific Reports
○ 3612 papers in training set
Top 9%
7.1%
Similar papers in this journal
5
The European Physical Journal Plus
○ 13 papers in training set
Top 0.1%
2.5%
Similar papers in this journal
6
Journal of Medical Internet Research
◐ 87 papers in training set
Top 1%
2.2%
7
One Health
○ 29 papers in training set
Top 0.2%
1.8%
8
Value in Health
○ 11 papers in training set
Top 0.2%
1.5%
9
Sensors
○ 43 papers in training set
Top 0.7%
1.5%
10
Mathematics
○ 11 papers in training set
Top 0.1%
1.2%
11
PLOS Computational Biology
● 1863 papers in training set
Top 16%
1.2%
12
Epidemics
○ 116 papers in training set
Top 1%
1.2%
13
BMC Medical Research Methodology
○ 47 papers in training set
Top 0.9%
1.2%
14
Health Policy
○ 11 papers in training set
Top 0.4%
1.1%
15
Epidemiology and Infection
◐ 89 papers in training set
Top 2%
1.1%
16
COVID
○ 14 papers in training set
Top 0.3%
1.0%
17
Microorganisms
○ 106 papers in training set
Top 3%
1.0%
18
BMC Health Services Research
○ 51 papers in training set
Top 2%
1.0%
19
Medical Decision Making
○ 12 papers in training set
Top 0.3%
0.9%
20
BMJ Open
● 601 papers in training set
Top 12%
0.9%
21
Bulletin of Mathematical Biology
○ 92 papers in training set
Top 1%
0.6%
22
International Journal of Environmental Research and Public Health
○ 128 papers in training set
Top 5%
0.6%
23
Frontiers in Artificial Intelligence
○ 20 papers in training set
Top 0.8%
0.6%
24
Computers in Biology and Medicine
○ 128 papers in training set
Top 5%
0.6%
25
Healthcare
○ 17 papers in training set
Top 1%
0.5%
26
Archives of Clinical and Biomedical Research
○ 28 papers in training set
Top 2%
0.5%
27
BMC Medical Informatics and Decision Making
○ 43 papers in training set
Top 2%
0.5%
28
European Journal of Public Health
◐ 21 papers in training set
Top 0.7%
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.