Back

Bayesian Networks in Healthcare: the chasm between research enthusiasm and clinical adoption

Kyrimi, E.; McLachlan, S.; Dube, K.; Fenton, N.

2020-06-05 health informatics
10.1101/2020.06.04.20122911 medRxiv
Show abstract

ProblemBayesian Networks (BN) can address real-world decision-making problems, and there is enormous and rapidly increasing interest in their use in healthcare. Yet, despite thousands of BNs in healthcare papers published yearly, evidence of their adoption in practice is extremely limited and there is no consensus on why. MethodA preliminary review was conducted to identify research gaps and justify the conduct of a broader scoping or systematic review of BNs in healthcare ResultsWe highlight that: (1) there have been no significant attempts to systematically review the domain; (2) there are weaknesses in the way BN development processes are presented in the literature; and (3) in contrast to enthusiasm (including from clinicians) there has been negligible adoption of published BNs into clinical practice. ConclusionA systematic review of BNs in healthcare is needed to a) understand the chasm between research enthusiasm and clinical adoption; and b) improve clinical adoption.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
BMC Medical Informatics and Decision Making
○ 43 papers in training set
Top 0.1%
12.3%
Similar papers in this journal
2
Journal of the American Medical Informatics Association
◐ 71 papers in training set
Top 0.3%
11.7%
Similar papers in this journal
3
Frontiers in Artificial Intelligence
○ 20 papers in training set
Top 0.1%
7.8%
Similar papers in this journal
4
BMC Medical Research Methodology
○ 47 papers in training set
Top 0.1%
7.1%
Similar papers in this journal
5
PLOS ONE
● 5266 papers in training set
Top 26%
6.2%
Similar papers in this journal
6
Journal of Medical Internet Research
◐ 87 papers in training set
Top 0.6%
4.2%
7
International Journal of Medical Informatics
○ 26 papers in training set
Top 0.2%
4.0%
50% of probability mass above
8
Computers in Biology and Medicine
○ 128 papers in training set
Top 1%
3.2%
9
npj Digital Medicine
○ 118 papers in training set
Top 2%
3.2%
10
Journal of Biomedical Informatics
○ 47 papers in training set
Top 0.6%
2.7%
11
Medical Decision Making
○ 12 papers in training set
Top 0.1%
2.7%
12
BMJ Health & Care Informatics
● 15 papers in training set
Top 0.5%
2.3%
13
BMJ Open
● 601 papers in training set
Top 8%
2.1%
14
JMIR Medical Informatics
◐ 18 papers in training set
Top 0.3%
2.1%
15
Frontiers in Digital Health
○ 24 papers in training set
Top 0.5%
2.1%
16
JAMIA Open
◐ 42 papers in training set
Top 0.9%
1.9%
17
Systematic Reviews
○ 15 papers in training set
Top 0.2%
1.9%
18
DIGITAL HEALTH
○ 17 papers in training set
Top 0.4%
1.7%
19
PLOS Digital Health
● 106 papers in training set
Top 3%
1.7%
20
Artificial Intelligence in Medicine
○ 17 papers in training set
Top 0.6%
1.1%
21
Scientific Reports
○ 3612 papers in training set
Top 68%
1.0%
22
International Journal of Environmental Research and Public Health
○ 128 papers in training set
Top 5%
0.9%
23
Biology Methods and Protocols
◐ 61 papers in training set
Top 2%
0.9%
24
The Lancet Digital Health
○ 25 papers in training set
Top 0.9%
0.8%
25
BJPsych Open
● 29 papers in training set
Top 0.7%
0.8%
26
Computer Methods and Programs in Biomedicine
○ 28 papers in training set
Top 1%
0.6%
27
PLOS Computational Biology
● 1863 papers in training set
Top 22%
0.6%
28
Journal of Theoretical Biology
○ 162 papers in training set
Top 2%
0.6%
29
JMIR Public Health and Surveillance
◐ 45 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.