Back

Swarm-GestaltMatcher: distributed Gestalt learning to enhance facial phenotyping for rare genetic syndromes

2026-01-05 health informatics Title + abstract only
View on medRxiv
Show abstract

Deep learning-based facial phenotyping represents a major paradigm shift in the diagnosis of rare and ultra-rare genetic disorders. By capturing disease-specific craniofacial "gestalts" that are often subtle, overlapping, but overlooked in routine clinical practice, these technologies surpass the traditional limits of dysmorphology assessment. Despite this, data scarcity and stringent privacy policies constraint centralized model training and its clinical translation. Swarm learning, a decentral...

Predicted journal destinations

1
Scientific Reports
701 training papers
Top 13% 11.7%
2
Nature Communications
483 training papers
Top 7% 11.7%
3
Journal of the American Medical Informatics Association
53 training papers
Top 2% 10.9%
4
Journal of Biomedical Informatics
37 training papers
Top 0.8% 7.7%
5
npj Digital Medicine
85 training papers
Top 2% 7.7%
6
PLOS Digital Health
88 training papers
Top 3% 6.4%
7
JAMIA Open
35 training papers
Top 2% 6.4%
8
Genetics in Medicine
57 training papers
Top 2% 5.9%
9
BMC Medical Informatics and Decision Making
36 training papers
Top 4% 3.8%
10
Bioinformatics
24 training papers
Top 0.5% 1.9%
11
Computers in Biology and Medicine
39 training papers
Top 4% 1.9%
12
PLOS Computational Biology
141 training papers
Top 8% 1.5%
13
Journal of Medical Internet Research
81 training papers
Top 11% 1.5%
14
International Journal of Medical Informatics
25 training papers
Top 5% 1.3%
15
PLOS ONE
1737 training papers
Top 96% 1.3%
16
JMIR Medical Informatics
16 training papers
Top 4% 1.3%
17
Communications Medicine
63 training papers
Top 3% 1.2%
18
Nature Medicine
88 training papers
Top 10% 1.1%
19
Nature Genetics
72 training papers
Top 9% 1.0%
20
Patterns
15 training papers
Top 2% 0.9%
21
The American Journal of Human Genetics
77 training papers
Top 7% 0.9%
22
Human Genetics and Genomics Advances
39 training papers
Top 7% 0.7%
23
Genome Medicine
56 training papers
Top 8% 0.7%
24
Frontiers in Digital Health
18 training papers
Top 4% 0.7%
25
BMC Medical Research Methodology
41 training papers
Top 9% 0.7%