AI facial analysis system improves diagnosis of rare diseases

An international team of researchers led by scientists at the University Hospital Bonn and the Charité - Universitätsmedizin Berlin have developed a computer-aided artificial intelligence (AI) platform for image analysis of patient faces to improve diagnosis of rare diseases. Findings were published in Genome Medicine.

In this study, the researchers focused on the broad spectrum of facial appearances of patients with glycosylphosphatidylinositol (GPI). The differences in severity of external appearances often complicate the diagnosis of this disease, so the study evaluated whether an AI facial analysis platform could help.

"This disease belongs to a group that we describe as GPI anchor deficiencies and which includes more than 30 genes," explained physician and physicist Peter Krawitz, MD, from the Institute for Genome Statistics and Bioinformatics of the University Hospital Bonn. "The result is that many patients and their relatives often suffer many years of uncertainty until the correct diagnosis is made."

The system contains DNA sequencing methods, cell surface analysis and computer-aided image recognition to identify cell surface changes indicating GPI deficiencies. Researchers used photographs of 91 patients to test the AI in its ability to recognize cell surface changes characteristic in GPI. Overall, some deficiencies were detected in some of the participants.

"The artificial modeling of gene-typical faces that we achieved with these datasets clearly shows that the computer-aided evaluation of patients' portraits can facilitate and improve the diagnosis of GPI anchor deficiencies, which is significant progress," said lead author Alexej Knaus, MSc, from the Institute for Genome Statistics and Bioinformatics of the University Hospital Bonn.

""
Cara Livernois, News Writer

Cara joined TriMed Media in 2016 and is currently a Senior Writer for Clinical Innovation & Technology. Originating from Detroit, Michigan, she holds a Bachelors in Health Communications from Grand Valley State University.

Trimed Popup
Trimed Popup