Utility of Face2Gene’s DeepGestalt and D-Score applications in paediatric neurodevelopmental disorders in South Africa

Face2Gene is a clinical tool that leverages facial features to aid genetic diagnosis. The DeepGestalt application suggests potential diagnoses based on facial similarity, while the D-Score evaluates likelihood of an individual having dysmorphic features suggestive of a possible genetic diagnosis. Given performance variability across populations and limited data from South Africa, this study assessed clinical utility in South African children with neurodevelopmental disorders (NDDs). Facial photographs from 301 children were analysed. The cohort comprised three groups: 36 children with NDDs with confirmed molecular diagnoses, 176 with NDDs without molecular diagnoses and 89 unaffected children. Diagnostic (recognition) accuracy was measured by whether the confirmed diagnosis appeared in the top-1 or top-10 ranked algorithm-generated suggestions (DeepGestalt). D-Scores were extracted to calculate group differences. Among children with confirmed molecular diagnoses, accuracy was 19% (95% CI: 9-35%) (top-1) and 34% (95% CI: 20-52%) (top-10), improving to 33% (95% CI: 16-56%) and 61% (95% CI: 39-80%) when limited to conditions included in the DeepGestalt training set. One-way ANOVA revealed differences between participants with and without significant dysmorphic features, as assessed by clinicians. The D-Score demonstrated moderate sensitivity (78%, [95% CI: 0.64, 0.88]) and low specificity (42%, [95% CI: 0.38, 0.50]), but high negative predictive value (91%, [95% CI: 0.84, 0.95]), suggesting it may be more useful for ruling out dysmorphism; however, the low specificity indicates a high rate of false positives, even among clinically non-dysmorphic children. These findings suggest that under-representation of African populations may limit clinical performance and equity of AI-based facial phenotyping tools.

Authors

Institutions

Publication Details

Journal
European Journal of Human Genetics
Published
2026-08-27
DOI
https://doi.org/10.1038/s41431-026-02216-5
Primary Topic
Genomics and Rare Diseases
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Utility of Face2Gene’s DeepGestalt and D-Score applications in paediatric neurodevelopmental disorders in South Africa

Ann Karanu, Michal R. Zieff, Charles R. Newton, Pauline Samia et al.
European Journal of Human Genetics
Genomics and Rare Diseases
article

Utility of Face2Gene’s DeepGestalt and D-Score applications in paediatric neurodevelopmental disorders in South Africa

Ann Karanu, Michal R. Zieff, Charles R. Newton, Pauline Samia, Zandrè Bruwer, Claire Fourie, Emma Eastman, Karen Fieggen, Brigitte Melly, Faghri February, Susan Wamithi, Shahida Moosa, Gina Itzikowitz, Alice Galvin, Eunice Chepkemoi, Celia van der Merwe, Emily O’Heir, Dorothy Chepkirui, Anne O’Donnell‐Luria, Megan Page, Constance Rehema, Moses Mosobo, Shaheen Sayed, Nicole McIver, Rachel Odhiambo, Johnstone Makale, Ikeoluwa Osei-Owusu, Moses Mangi, Racheal Mapenzi, Fatima Khan, Samuel Mwasambu, Raphaela Itzikowitz, Javan Nyale, Amina Abubakar, Dorcas Kamuya, Kirsten A. Donald, Rizqa Sulaiman-Bardien, Christina Austin Tse, Alex Macharia, Tabith Shali, Phatiswa Lopoleng Ranyana, Aleya Zulfikar Remtullah, Anne O’Donnell-Luria, Nonceba Ngubo, Rene Lepore, Lizette Rooi, Kegan Chase, Elise B. Robinson, Deepika Goolab, Thandi Xintolo, Jess Ringshaw, Carmen Swanepoel, Hendrike Mc Donald
article en

Abstract

Face2Gene is a clinical tool that leverages facial features to aid genetic diagnosis. The DeepGestalt application suggests potential diagnoses based on facial similarity, while the D-Score evaluates likelihood of an individual having dysmorphic features suggestive of a possible genetic diagnosis. Given performance variability across populations and limited data from South Africa, this study assessed clinical utility in South African children with neurodevelopmental disorders (NDDs). Facial photographs from 301 children were analysed. The cohort comprised three groups: 36 children with NDDs with confirmed molecular diagnoses, 176 with NDDs without molecular diagnoses and 89 unaffected children. Diagnostic (recognition) accuracy was measured by whether the confirmed diagnosis appeared in the top-1 or top-10 ranked algorithm-generated suggestions (DeepGestalt). D-Scores were extracted to calculate group differences. Among children with confirmed molecular diagnoses, accuracy was 19% (95% CI: 9-35%) (top-1) and 34% (95% CI: 20-52%) (top-10), improving to 33% (95% CI: 16-56%) and 61% (95% CI: 39-80%) when limited to conditions included in the DeepGestalt training set. One-way ANOVA revealed differences between participants with and without significant dysmorphic features, as assessed by clinicians. The D-Score demonstrated moderate sensitivity (78%, [95% CI: 0.64, 0.88]) and low specificity (42%, [95% CI: 0.38, 0.50]), but high negative predictive value (91%, [95% CI: 0.84, 0.95]), suggesting it may be more useful for ruling out dysmorphism; however, the low specificity indicates a high rate of false positives, even among clinically non-dysmorphic children. These findings suggest that under-representation of African populations may limit clinical performance and equity of AI-based facial phenotyping tools.

European Journal of Human Genetics
Broad Institute (US), National Health Laboratory Service (ZA), Boston Children's Hospital (US), Harvard University (US), University of Cape Town (ZA), Stellenbosch University (ZA), Groote Schuur Hospital (ZA), Tygerberg Hospital (ZA), Kenya Medical Research Institute (KE), University of Oxford (GB), Massachusetts General Hospital (US), Aga Khan University Nairobi (KE), Red Cross War Memorial Children's Hospital (ZA), University of Manitoba (CA)
Stanley Center for Psychiatric Research, Broad Institute, National Institute of Mental Health, National Human Genome Research Institute
Openalex Percentile: Top 11%
Genomics and Rare Diseases
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.