Researchers are testing computer-aided facial analysis for diagnosis
Digitalization will revolutionize the healthcare system, both in terms of diagnosis and therapy options. Scientists from the Charité in Berlin and the Bonn University Hospital have already successfully tested computer-aided facial analysis as a diagnostic tool.
"In rare diseases, the computer-assisted image evaluation of patient portraits can make diagnosis easier and significantly improve it," reports the Rheinische Friedrich-Wilhelms-Universität Bonn of the study results. Using the clinical picture of GPI anchor disorders (including GPI anchor synthesis disorders), the scientists were able to show that the computer-assisted evaluation of portrait photos offers a good starting point for diagnosis. The researchers have published their results in the journal "Genome Medicine".
Improvements in the diagnostic options examined
The international team of researchers led by Dr. Alexej Knaus and Prof. Krawitz from the Institute for Genomic Statistics and Bioinformatics at the University Hospital Bonn and Prof. Dr. Denise Horn from the Institute for Medical Genetics and Human Genetics at the Charité has examined in the current study to what extent computer-aided facial analysis can help to improve the diagnosis of GPI anchor disorders. It was also examined whether modern, particularly fast DNA sequencing methods and surface analysis of cells can improve the diagnostic options.
What Are GPI Anchor Disorders?
An example from the group of GPI anchor disorders is the so-called Mabry syndrome. This rare disease leads to mental retardation and is triggered by the change in a single gene, the scientists report. The syndrome belongs to “a group that we describe as GPI anchor disorders and which includes over 30 genes,” explains Prof. Peter Krawitz from the Institute for Genomic Statistics and Bioinformatics at the University Hospital Bonn.
Signal transmission and cell transport disrupted
The “anchors” made of glycosylphosphatidylinositol (GPI) hold special proteins on the outside of the cell and if this does not work properly due to a gene mutation, the signal transmission and transport within the cell and between the cells are disrupted, the researchers report. This also has an impact on the outward appearance of those affected. However, the spectrum of the external appearance of the GPI anchor disorders is wide, which makes it difficult to identify those affected.
Effects on appearance
"The effects of a mutation in a specific gene can manifest itself from very mild to very strong"; the researchers report. This also applies to the abnormalities on the face. For example, in the Mabry syndrome "a narrow, sometimes tent-shaped upper lip, a wide nasal root and a large eye relief with long eyelid gaps" are known as classic features. However, these can be stronger or weaker, which often complicates the diagnosis of the rare disease.
DNA sequencing, cell surface analysis, computer-assisted image analysis
Since the eponymous increase in alkaline phosphatase in the blood cannot be demonstrated in every patient with Mabry syndrome, "patients and their relatives often go through a long odyssey until the correct diagnosis is made," says Krawitz. New DNA sequencing methods, surface analysis of cells and computer-assisted image analysis could significantly improve the diagnostic options here in the future.
Typical facial features can be seen
In their current studies, the researchers used the faces of a total of 91 patients. The analysis of the cell surfaces in the test subjects, which was also carried out, showed that some of the participants had the changes typical of GPI anchor disorders. The researchers also found gene mutations that are typical of this rare group of diseases when analyzing the genome. The researchers then used "artificial intelligence methods to simulate models of the disease from data on the genetic material, the surface properties of the cells and typical facial features."
Diagnostic options significantly improved
The artificial modeling of the gene-typical faces based on the available data sets, according to the first author Dr. Knaus showed very clearly that "the computer-aided evaluation of patient portraits can facilitate and improve the diagnosis of GPI anchor disorders." According to the scientists, the study result is "a great step forward" and they hope with the help of combined data from the laboratory and the computer to understand better the molecular processes of such diseases.
Can facial analysis also be used for other diseases?
For example, an elevated level of alkaline phosphatase in the blood with conspicuous results in image analysis is a reliable indication of the classification of a new mutation in GPI anchor disorders, the experts explain. In their opinion, the new combination of cell and genetic analysis and computer-aided image evaluation is forward-looking. “It is foreseeable that these methods can also be applied to other diseases. This would be a big leap forward in terms of diagnosis, ”says Prof. Krawitz. (fp)