Back

FHIR Profiliferation: A Data Science Approach

Kramer, M. A.

2022-03-12 health informatics
10.1101/2022.03.09.22272163 medRxiv
Show abstract

Profiling is a mechanism for shaping Fast Healthcare Interoperability Resources (FHIR) for particular use cases. "Profiliferation" (profile + proliferation) is a coinage referring to the explosive growth in the number of FHIR profiles over the past few years. By reviewing a broad sample of almost 3000 FHIR profiles from 125 implementation guides, it was determined that just two items, Observation and Extension, accounted for half the profiles. FHIRs 80/20 rule was determined to be closer to 65/35, revealing that FHIR is more dependent on profiling than initially intended. Use of the Observation resource was inconsistent, hinting that the resource is either poorly designed, or that users lack proper guidance. Better management of reusable items and certain changes in FHIR and profiling practices could improve the consistency of FHIR artifacts and reduce unnecessary and potentially incompatible profiles.

Matching journals

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

1
JAMIA Open
◐ 42 papers in training set
Top 0.1%
12.7%
Similar papers in this journal
2
Journal of the American Medical Informatics Association
◐ 71 papers in training set
Top 0.3%
12.3%
Similar papers in this journal
3
Journal of Biomedical Informatics
○ 47 papers in training set
Top 0.1%
10.5%
Similar papers in this journal
4
BMC Medical Informatics and Decision Making
○ 43 papers in training set
Top 0.2%
7.8%
Similar papers in this journal
5
JMIR Medical Informatics
◐ 18 papers in training set
Top 0.1%
6.6%
Similar papers in this journal
6
PLOS Digital Health
● 106 papers in training set
Top 1%
6.2%
50% of probability mass above
7
BMJ Health & Care Informatics
● 15 papers in training set
Top 0.2%
5.4%
8
PLOS ONE
● 5266 papers in training set
Top 30%
4.8%
9
DIGITAL HEALTH
○ 17 papers in training set
Top 0.1%
4.8%
10
Journal of Medical Internet Research
◐ 87 papers in training set
Top 0.6%
4.3%
11
International Journal of Medical Informatics
○ 26 papers in training set
Top 0.4%
2.6%
12
Frontiers in Digital Health
○ 24 papers in training set
Top 0.5%
2.1%
13
Computers in Biology and Medicine
○ 128 papers in training set
Top 3%
1.7%
14
Scientific Reports
○ 3612 papers in training set
Top 55%
1.7%
15
GigaScience
◐ 212 papers in training set
Top 3%
1.4%
16
Bioinformatics
◐ 1204 papers in training set
Top 8%
1.1%
17
JMIR Formative Research
◐ 33 papers in training set
Top 1%
1.1%
18
Frontiers in Public Health
○ 148 papers in training set
Top 6%
0.9%
19
PLOS Computational Biology
● 1863 papers in training set
Top 20%
0.8%
20
Computer Methods and Programs in Biomedicine
○ 28 papers in training set
Top 1%
0.6%
21
JMIR Public Health and Surveillance
◐ 45 papers in training set
Top 2%
0.6%
22
Frontiers in Artificial Intelligence
○ 20 papers in training set
Top 0.9%
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.