Automated syndrome diagnosis by three-dimensional facial imaging.

PURPOSE: Deep phenotyping is an emerging trend in precision medicine for genetic disease. The shape of the face is affected in 30-40% of known genetic syndromes. Here, we determine whether syndromes can be diagnosed from 3D images of human faces. METHODS: We analyzed variation in three-dimensional (3D) facial images of 7057 subjects: 3327 with 396 different syndromes, 727 of their relatives, and 3003 unrelated, unaffected subjects. We developed and tested machine learning and parametric approaches to automated syndrome diagnosis using 3D facial images. RESULTS: Unrelated, unaffected subjects were correctly classified with 96% accuracy. Considering both syndromic and unrelated, unaffected subjects together, balanced accuracy was 73% and mean sensitivity 49%. Excluding unrelated, unaffected subjects substantially improved both balanced accuracy (78.1%) and sensitivity (56.9%) of syndrome diagnosis. The best predictors of classification accuracy were phenotypic severity and facial distinctiveness of syndromes. Surprisingly, unaffected relatives of syndromic subjects were frequently classified as syndromic, often to the syndrome of their affected relative. CONCLUSION: Deep phenotyping by quantitative 3D facial imaging has considerable potential to facilitate syndrome diagnosis. Furthermore, 3D facial imaging of "unaffected" relatives may identify unrecognized cases or may reveal novel examples of semidominant inheritance.

Integrating primary care and behavioral health with four special populations: Children with special needs, people with serious mental illness, refugees, and deaf people.

Special patient populations can present unique opportunities and challenges to integrating primary care and behavioral health services. This article focuses on four special populations: children with special needs, persons with severe and persistent mental illness, refugees, and deaf people who communicate via sign language. The current state of primary care and behavioral health collaboration regarding each of these four populations is examined via Doherty, McDaniel, and Baird's (1996) five-level collaboration model. The section on children with special needs offers contrasting case studies that highlight the consequences of effective versus ineffective service integration. The challenges and potential benefits of service integration for the severely mentally ill are examined via description of PRICARe (Promoting Resources for Integrated Care and Recovery), a model program in Colorado. The discussion regarding a refugee population focuses on service integration needs and emerging collaborative models as well as ways in which refugee mental health research can be improved. The section on deaf individuals examines how sign language users are typically marginalized in health care settings and offers suggestions for improving the health care experiences and outcomes of deaf persons. A well-integrated model program for deaf persons in Austria is described. All four of these special populations will benefit from further integration of primary care and mental health services.