Up to 40% of genetic and rare disorders (RD) present facial dysmorphologies. Visual assessment of facial gestalt is commonly used for clinical diagnosis, health management and treatment monitoring. Quantitative approaches to facial phenotypes are more objective and provide first diagnoses of RD with relatively high accuracy, but are mainly based on populations of European descent, disregarding the influence of population ancestry. Here we assessed the facial phenotypes associated to four genetic disorders in a Latino-American population from Colombia. We recorded the coordinates of 18 facial landmarks in 2D images from 79 controls 51 pediatric individuals diagnosed with Down (DS), Morquio (MS), Noonan (NS) and Neurofibromatosis type 1 (NF1) syndromes. We quantified facial differences using Euclidean Distance Matrix Analysis (EDMA) and assessed the diagnostic accuracy of Face2gene, an automatic deep learning algorithm with widespread use in the clinical practice. Quantitative comparisons indicated that individuals diagnosed with DS and MS were associated with the most severe phenotypes, with 58.2% and 65.4% of facial traits significantly different as compared to controls. The percentage decreased to 47.7% in NS and to 11.4% in NF1. Each syndrome presented a characteristic pattern of facial dysmorphology, supporting the potential of facial biomarkers for disorder diagnosis. However, our results detected population-specific traits in the Colombian population as compared to the facial gestalt described in literature for DS, NS and NF1. When clinical diagnosis based on genetic testing was used to verify the diagnosis based on 2D facial pictures, our results showed that Face2Gene accuracy was very high in DS, moderate in NS and NF1, and very low in MS, with low gestalt similarity scores in highly admixed individuals. Our study underscores the added value of precise quantitative comparison of facial dysmorphologies in genetic and rare disorders and the need to incorporate populations with diverse contributions of Amerindian, African and European ancestry components to further improve automatic diagnostic methods.

The authors have declared no competing interest.

This study was funded by Proyecto COL0012168-1097 Interfacultades-ICESI, and 2017SGR1630 Research group (AGAUR).

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Human Research Ethics Committee of the Icesi University gave ethical approval for this work through Approval Act No. 309

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.

Yes

All data produced in the present study are available upon reasonable request to the authors