Enriching UMLS-Based Phenotyping of Rare Diseases Using Deep-Learning: Evaluation on Jeune Syndrome

Carole Faviez; Marc Vincent; Nicolas Garcelon; Caroline Michot; Genevieve Baujat; Valerie Cormier-Daire; Sophie Saunier; Xiaoyi Chen; Anita Burgun

doi:10.3233/SHTI220604

Enriching UMLS-Based Phenotyping of Rare Diseases Using Deep-Learning: Evaluation on Jeune Syndrome

Stud Health Technol Inform. 2022 May 25:294:844-848. doi: 10.3233/SHTI220604.

Authors

Carole Faviez^{1

2}, Marc Vincent³, Nicolas Garcelon^{1

2

3}, Caroline Michot^{4

5}, Genevieve Baujat^{4

5}, Valerie Cormier-Daire^{4

5}, Sophie Saunier⁶, Xiaoyi Chen^{1

2

3}, Anita Burgun^{1

2

7}

Affiliations

¹ Centre de Recherche des Cordeliers, Sorbonne Université, INSERM, Université de Paris, Paris, France.
² Inria Paris, France.
³ Université de Paris, Imagine Institute, Data Science Platform, INSERM UMR 1163, Paris, France.
⁴ Reference Centre for Constitutional Bone Diseases, laboratory of Osteochondrodysplasia, INSERM UMR 1163, Imagine Institute, Université de Paris, Paris, France.
⁵ Hôpital Necker-Enfants Malades, Service de génétique, AP-HP, Paris, France.
⁶ Laboratory of Renal Hereditary Diseases, INSERM UMR 1163, Imagine Institute, Université de Paris, Paris, France.
⁷ Hôpital Necker-Enfants Malades, Département d'informatique médicale, AP-HP, Paris, France.

PMID: 35612223
DOI: 10.3233/SHTI220604

Abstract

The wide adoption of Electronic Health Records (EHR) in hospitals provides unique opportunities for high throughput phenotyping of patients. The phenotype extraction from narrative reports can be performed by using either dictionary-based or data-driven methods. We developed a hybrid pipeline using deep learning to enrich the UMLS Metathesaurus for automatic detection of phenotypes from EHRs. The pipeline was evaluated on a French database of patients with a rare disease characterized by skeletal abnormalities, Jeune syndrome. The results showed a 2.5-fold improvement regarding the number of detected skeletal abnormalities compared to the baseline extraction using the standard release of UMLS. Our method can help enrich the coverage of the UMLS and improve phenotyping, especially for languages other than English.

Keywords: Named entity recognition; deep phenotyping; electronic health records; rare disease.

MeSH terms

Algorithms
Deep Learning*
Electronic Health Records
Ellis-Van Creveld Syndrome
Humans
Rare Diseases / diagnosis
Unified Medical Language System*

Supplementary concepts

Jeune syndrome