From: Performance and clinical utility of a new supervised machine-learning pipeline in detecting rare ciliopathy patients based on deep phenotyping from electronic health records and semantic similarity
Ciliopathy cases
Controls
# Training set
20
4844
# Test set
10
2387
# Total
30
7231
Sex ratio (M/F)
1.5
1
Age* (median (IQR))
14.8 (12–19.2)
11.5 (4.6–25.8)
% Syndromic forms
40%
NA
#HPO (median (IQR))
18 (10.3–35.8)
10 (6–18)