A software tool, which analyses two-dimensional photos of faces, is helping to identify certain types of alcohol-related neurodevelopmental disorders (ARNDs).

Foetal alcohol spectrum disorders (FASDs) is a range of conditions caused by a mother’s consumption of alcohol during pregnancy and include foetal alcohol syndrome (FAS), partial foetal alcohol syndrome (pFAS) as well as alcohol-related neurodevelopmental disorders. When a mother drinks alcohol, it passes to her baby through the placenta. Because the baby can’t process alcohol as well as the mother can, it can disrupt their development in the womb, damage cells in their brain, spinal cord and other parts of their body. It can also result in distinctive facial features, such as small eyes, a thin upper lip, and a smooth area between the nose and upper lip. The well-defined diagnostic criteria for FAS and pFAS means that these conditions can normally be diagnosed without knowing whether or not the mother consumed alcohol during her pregnancy. ARNDs, however, have proven more difficult to spot; diagnosing them relies on knowing whether or not the foetus has been exposed to alcohol.
Like FAS and pFAS, ARND does cause some facial abnormalities, but they are much more subtle and difficult to recognise. The early signs of cognitive and behavioural abnormalities may not become apparent until the children are much older. This late diagnosis means that individuals are less likely to receive the extra support they need, which can result in further problems down the line, such as trouble at school, alcohol abuse and mental illness.

A novel approach to ARND diagnosis using a computer-based facial analysis tool has been published in the journal Pediatrics [1]. The study focuses on a system that can carry out facial recognition using photos taken with a standard camera. Participants from the Fetal Alcohol Syndrome Epidemiology Research database were aged 5–9, and from South Africa, the USA, and Italy and included 36 people with FAS, 31 with pFAS and 22 with ARND. The study also included a control group of 50 children without FASD. The computer-aided method was found to be just as accurate as a trained human clinician at diagnosing FASDs in general. However, the computer performed significantly better when it came to the more difficult-to-diagnose ARNDs.

Further trials will be needed, but these initial findings are encouraging. According to the authors of the study, “We found there was an increased diagnostic accuracy for ARND via our computer-aided method. Earlier recognition of these patients will lead to earlier intervention with improved patient outcomes.”

The UK Chief Medical Officers recommend that if you’re pregnant or planning to become pregnant, the safest approach is not to drink alcohol at all to keep risks to your baby to a minimum. AlphaBiolabs offers a range of alcohol tests and alcohol-detection devices. For information, please call 0333 600 1300 or email info@alphabiolabs.com.

1. M. Valentine, D.C.J. Bihm, L. Wolf, et al. Computer-aided recognition of facial attributes for fetal alcohol spectrum disorders. Pediatrics 2017;140(6): 10.1542/peds.2016-2028