Information content as a health system screening tool for rare diseases

1

Rare diseases affect 3.5–5.9% of the global population, with patients often facing a diagnostic odyssey lasting 5–6 years.
2

The study utilized information content as a screening tool to identify rare disease candidates using SNOMED CT in Singapore's health system.
3

The proposed method achieved approximately 95% sensitivity and identified 71 underdiagnosed rare diseases within a dataset of 1.2 million patients.
4

SNOMED CT provides greater granularity for rare diseases than ICD-10, covering over 40% of rare disease terms compared to ICD-10's 20%.
5

This study is the first to apply information-theoretic metrics to electronic health records for rare disease screening, highlighting its potential.

Npj Digital Medicine

by Tudor Groza, Peter N. Robinson, Weng Khong Lim, Kaavya Narasimhalu, Jenny Hsieh, Khung Keong Yeo, Goh Bee Keow, Terrence Thomas, Tien Yin Wong, Neerja Karnani, Gareth Baynam, Saumya Shekhar Jamuar
November 25, 2025

1