Back

Hybrid rule-based and on-premises LLM pipeline for extracting CMR and CPET metrics from free-text reports in repaired tetralogy of Fallot

2026-01-23 cardiovascular medicine Title + abstract only
View on medRxiv
Show abstract

BackgroundPatients with repaired tetralogy of Fallot (rTOF) require lifelong surveillance with cardiovascular magnetic resonance (CMR) and cardiopulmonary exercise testing (CPET). However, results are frequently stored as unstructured free-text reports, hindering large-scale analysis and research. ObjectivesThis study aimed to develop and evaluate a privacy-preserving hybrid natural language processing pipeline combining regular expressions (regex) and an on-premises large language model (LLM) ...

Predicted journal destinations

1
Scientific Reports
701 training papers
Top 9% 14.4%
2
npj Digital Medicine
85 training papers
Top 2% 8.9%
3
European Heart Journal - Digital Health
15 training papers
Top 0.3% 7.7%
4
Frontiers in Cardiovascular Medicine
33 training papers
Top 3% 6.3%
5
Journal of the American Heart Association
92 training papers
Top 6% 6.3%
6
Circulation
37 training papers
Top 3% 6.3%
7
PLOS ONE
1737 training papers
Top 77% 5.9%
8
The American Journal of Cardiology
15 training papers
Top 2% 4.1%
9
Computers in Biology and Medicine
39 training papers
Top 2% 3.8%
10
Heart Rhythm
16 training papers
Top 3% 2.8%
11
Open Heart
18 training papers
Top 4% 2.8%
12
Circulation: Genomic and Precision Medicine
30 training papers
Top 5% 1.9%
13
BMJ Open
553 training papers
Top 54% 1.5%
14
Journal of Clinical Medicine
77 training papers
Top 12% 1.5%
15
Journal of the American Medical Informatics Association
53 training papers
Top 5% 1.5%
16
PLOS Digital Health
88 training papers
Top 12% 1.5%
17
Nature Medicine
88 training papers
Top 5% 1.5%
18
Frontiers in Physiology
18 training papers
Top 0.8% 1.5%
19
JMIR Medical Informatics
16 training papers
Top 5% 1.3%
20
Hypertension
20 training papers
Top 5% 1.2%
21
EBioMedicine
21 training papers
Top 0.5% 1.2%
22
Nature
58 training papers
Top 5% 1.2%
23
eLife
262 training papers
Top 39% 1.2%
24
Nature Communications
483 training papers
Top 51% 1.1%
25
Atherosclerosis
16 training papers
Top 5% 0.7%
26
Cureus
64 training papers
Top 23% 0.7%