Back

Developing a Specialized Dravet Syndrome Ontology for Rare Disease Informatics and AI Applications

Golnari, P.; Prantzalos, K.; Upadhyaya, D. P.; Buchhalter, J.; Sahoo, S. S.

2026-07-04 neurology
10.64898/2026.07.01.26357055 medRxiv
Show abstract

Dravet syndrome (DS) is a severe developmental and epileptic encephalopathy whose clinical and research representation requires integration of heterogeneous knowledge spanning seizures, development, behavior, SUDEP/autonomic risk, genetics, comorbidities, electrophysiology, pharmacology, and drug responsiveness. We report the development of a DS-focused ontology created by expert-guided specialization of a previously published epilepsy ontology. Scope expansion was defined through a scientific advisory board, structured review meetings, and iterative ontology curation in OWL. The resulting resource reorganized DS content across nine major domains and expanded the publicly released ontology from the pre-extension baseline to the current BioPortal version. Beyond structural growth, the ontology was assessed through expert-guided curation and downstream task-based reuse, including two published ontology-enabled LLM studies and an ongoing ontology-derived DS knowledge graph and AI assistant platform. These results suggest that disease-focused ontology specialization can provide durable infrastructure for DS data harmonization, knowledge representation, and AI-enabled translational informatics.

Matching journals

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

1
Epilepsia
○ 56 papers in training set
Top 0.1%
22.5%
Similar papers in this journal
2
Database
◐ 61 papers in training set
Top 0.1%
9.7%
Similar papers in this journal
3
Epilepsia Open
○ 17 papers in training set
Top 0.1%
6.3%
Similar papers in this journal
4
Communications Medicine
○ 113 papers in training set
Top 0.2%
5.5%
Similar papers in this journal
5
Scientific Data
○ 209 papers in training set
Top 0.4%
5.5%
Similar papers in this journal
6
PLOS ONE
● 5266 papers in training set
Top 29%
4.9%
50% of probability mass above
7
BMC Medical Informatics and Decision Making
○ 43 papers in training set
Top 0.5%
4.1%
8
Epilepsy Research
○ 14 papers in training set
Top 0.1%
3.2%
9
Journal of the American Medical Informatics Association
◐ 71 papers in training set
Top 1.0%
3.2%
10
Orphanet Journal of Rare Diseases
○ 21 papers in training set
Top 0.2%
2.4%
11
Annals of Clinical and Translational Neurology
○ 34 papers in training set
Top 0.4%
2.1%
12
Brain Communications
◐ 166 papers in training set
Top 2%
1.9%
13
Epilepsy & Behavior
○ 12 papers in training set
Top 0.1%
1.7%
14
Scientific Reports
○ 3612 papers in training set
Top 56%
1.5%
15
PLOS Digital Health
● 106 papers in training set
Top 3%
1.4%
16
Clinical Neurophysiology
○ 56 papers in training set
Top 0.6%
1.1%
17
Frontiers in Neurology
○ 102 papers in training set
Top 2%
1.1%
18
Annals of Neurology
○ 64 papers in training set
Top 1%
1.0%
19
BMJ Health & Care Informatics
● 15 papers in training set
Top 0.9%
1.0%
20
PLOS Computational Biology
● 1863 papers in training set
Top 19%
0.8%
21
Nature Computational Science
○ 55 papers in training set
Top 2%
0.8%
22
Nature Medicine
○ 125 papers in training set
Top 3%
0.8%
23
European Journal of Neurology
○ 22 papers in training set
Top 0.7%
0.8%
24
Med
○ 39 papers in training set
Top 0.7%
0.8%
25
npj Parkinson's Disease
○ 105 papers in training set
Top 1%
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.