GestaltMatcher Database - A Global Reference for Facial Phenotypic Variability in Rare Human Diseases

The most important factor that complicates the work of dysmorphologists is the significant phenotypic variability of the human face. Next-Generation Phenotyping (NGP) tools that assist clinicians with recognizing characteristic syndromic patterns are particularly challenged when confronted with patients from populations different from their training data. To that end, we systematically analyzed the impact of genetic ancestry on facial dysmorphism. For that purpose, we established the GestaltMatcher Database (GMDB) as a reference dataset for medical images of patients with rare genetic disorders from around the world. We collected 10,980 frontal facial images - more than a quarter previously unpublished - from 8,346 patients, representing 581 rare disorders. Although the predominant ancestry is still European (67%), data from underrepresented populations have been increased considerably via global collaborations (19% Asian and 7% African). This includes previously unpublished reports for more than 40% of the African patients. The NGP analysis on this diverse dataset revealed characteristic performance differences depending on the composition of training and test sets corresponding to genetic relatedness. For clinical use of NGP, incorporating non-European patients resulted in a profound enhancement of GestaltMatcher performance. The top-5 accuracy rate increased by +11.29%. Importantly, this improvement in delineating the correct disorder from a facial portrait was achieved without decreasing the performance on European patients. By design, GMDB complies with the FAIR principles by rendering the curated medical data findable, accessible, interoperable, and reusable. This means GMDB can also serve as data for training and benchmarking. In summary, our study on facial dysmorphism on a global sample revealed a considerable cross ancestral phenotypic variability confounding NGP that should be counteracted by international efforts for increasing data diversity. GMDB will serve as a vital reference database for clinicians and a transparent training set for advancing NGP technology.

References

Averdunk L, Huetzen M, Moreno-Andres D, Kalb R, McKee S, Hsieh T . Biallelic variants in CRIPT cause a Rothmund-Thomson-like syndrome with increased cellular senescence. Genet Med. 2023; 25(7):100836. DOI: 10.1016/j.gim.2023.100836. View

Hadj-Rabia S, Schneider H, Navarro E, Klein O, Kirby N, Huttner K . Automatic recognition of the XLHED phenotype from facial images. Am J Med Genet A. 2017; 173(9):2408-2414. DOI: 10.1002/ajmg.a.38343. View

Mons B, van Haagen H, Chichester C, Hoen P, den Dunnen J, van Ommen G . The value of data. Nat Genet. 2011; 43(4):281-3. DOI: 10.1038/ng0411-281. View

Mishima H, Suzuki H, Doi M, Miyazaki M, Watanabe S, Matsumoto T . Evaluation of Face2Gene using facial images of patients with congenital dysmorphic syndromes recruited in Japan. J Hum Genet. 2019; 64(8):789-794. DOI: 10.1038/s10038-019-0619-z. View

Lyon G, Vedaie M, Beisheim T, Park A, Marchi E, Gottlieb L . Expanding the phenotypic spectrum of NAA10-related neurodevelopmental syndrome and NAA15-related neurodevelopmental syndrome. Eur J Hum Genet. 2023; 31(7):824-833. PMC: 10325952. DOI: 10.1038/s41431-023-01368-y. View

Aerden M, Denomme-Pichon A, Bonneau D, Bruel A, Delanne J, Gerard B . The neurodevelopmental and facial phenotype in individuals with a TRIP12 variant. Eur J Hum Genet. 2023; 31(4):461-468. PMC: 10133310. DOI: 10.1038/s41431-023-01307-x. View

Martinez-Abadias N, Gonzalez-Jose R, Gonzalez-Martin A, Van der Molen S, Talavera A, Hernandez P . Phenotypic evolution of human craniofacial morphology after admixture: a geometric morphometrics approach. Am J Phys Anthropol. 2005; 129(3):387-98. DOI: 10.1002/ajpa.20291. View

Robinson P, Kohler S, Bauer S, Seelow D, Horn D, Mundlos S . The Human Phenotype Ontology: a tool for annotating and analyzing human hereditary disease. Am J Hum Genet. 2008; 83(5):610-5. PMC: 2668030. DOI: 10.1016/j.ajhg.2008.09.017. View

Winter R, Baraitser M . The London Dysmorphology Database. J Med Genet. 1987; 24(8):509-10. PMC: 1050214. DOI: 10.1136/jmg.24.8.509. View

10.

Hennocq Q, Willems M, Amiel J, Arpin S, Attie-Bitach T, Bongibault T . Next generation phenotyping for diagnosis and phenotype-genotype correlations in Kabuki syndrome. Sci Rep. 2024; 14(1):2330. PMC: 10822856. DOI: 10.1038/s41598-024-52691-3. View

11.

Porras A, Summar M, Linguraru M . Objective differential diagnosis of Noonan and Williams-Beuren syndromes in diverse populations using quantitative facial phenotyping. Mol Genet Genomic Med. 2021; 9(5):e1636. PMC: 8172204. DOI: 10.1002/mgg3.1636. View

12.

Vorravanpreecha N, Lertboonnum T, Rodjanadit R, Sriplienchan P, Rojnueangnit K . Studying Down syndrome recognition probabilities in Thai children with de-identified computer-aided facial analysis. Am J Med Genet A. 2018; 176(9):1935-1940. DOI: 10.1002/ajmg.a.40483. View

13.

Hsieh T, Bar-Haim A, Moosa S, Ehmke N, Gripp K, Pantel J . GestaltMatcher facilitates rare disease matching using facial phenotype descriptors. Nat Genet. 2022; 54(3):349-357. PMC: 9272356. DOI: 10.1038/s41588-021-01010-x. View

14.

Gurovich Y, Hanani Y, Bar O, Nadav G, Fleischer N, Gelbman D . Identifying facial phenotypes of genetic disorders using deep learning. Nat Med. 2019; 25(1):60-64. DOI: 10.1038/s41591-018-0279-0. View

15.

Narayanan D, Ranganath P, Aggarwal S, Dalal A, Phadke S, Mandal K . Computer-aided Facial Analysis in Diagnosing Dysmorphic Syndromes in Indian Children. Indian Pediatr. 2019; 56(12):1017-1019. View

16.

Liu J, Barrett J, Leonardi E, Lee L, Roychoudhury S, Chen Y . Natural History and Real-World Data in Rare Diseases: Applications, Limitations, and Future Perspectives. J Clin Pharmacol. 2022; 62 Suppl 2:S38-S55. PMC: 10107901. DOI: 10.1002/jcph.2134. View

17.

Kruszka P, Tekendo-Ngongang C, Muenke M . Diversity and dysmorphology. Curr Opin Pediatr. 2019; 31(6):702-707. DOI: 10.1097/MOP.0000000000000816. View

18.

Muenke M, Adeyemo A, Kruszka P . An electronic atlas of human malformation syndromes in diverse populations. Genet Med. 2016; 18(11):1085-1087. DOI: 10.1038/gim.2016.3. View

19.

Rigter P, de Konink C, Dunn M, Proietti Onori M, Humberson J, Thomas M . Role of CAMK2D in neurodevelopment and associated conditions. Am J Hum Genet. 2024; 111(2):364-382. PMC: 10870144. DOI: 10.1016/j.ajhg.2023.12.016. View

20.

Elmas M, Gogus B . Success of Face Analysis Technology in Rare Genetic Diseases Diagnosed by Whole-Exome Sequencing: A Single-Center Experience. Mol Syndromol. 2020; 11(1):4-14. PMC: 7109386. DOI: 10.1159/000505800. View