Gastroenterology
June 1, 2022Sweat Sensor Skin-like Microfluidic Device
July 1, 2022Article of the Month – June 2022
Assessment of Facial Morphologic Features in Patients with Congenital Adrenal Hyperplasia Using Deep Learning...
Assessment of Facial Morphologic Features in Patients with Congenital Adrenal Hyperplasia Using Deep Learning
Wael AbdAlmageed, PhD; Hengameh Mirzaalian, PhD; Xiao Guo, MS; Linda M. Randolph, MD; Veeraya K. Tanawattanacharoen, BSc; Mitchell E. Geffner, MD; Heather M. Ross, BSc; Mimi S. Kim, MD, MSc
Importance
Congenital adrenal hyperplasia (CAH) is the most common primary adrenal insufficiency in children, involving excess androgens secondary to disrupted steroidogenesis as early as the seventh gestational week of life. Although structural brain abnormalities are seen in CAH, little is known about facial morphology.
Objectives
To investigate differences in facial morphologic features beteen patients with CAH and control individuals with the use of machine learning.
Design, Setting, and Participants
This cross-sectional study was performed at a pediatric tertiary center in Southern California, from November 2017 to December 2019. Patients younger than 30 years with a biochemical diagnosis of classical CAH due to 21-hydroxylase deficiency and otherwise healthy controls were recruited from the clinic, and face images were acquired. Additional controls were selected from public face image data sets.
Outcomes and Measures...
The main outcome was the prediction of CAH, as performed by machine learning (linear discriminant analysis, random forests, deep neural networks). Handcrafted features and learned representations were studied for CAH score prediction, and deformation analysis of facial landmarks and regionwide analyses were performed. A 6-fold cross-validation strategy was used to avoid overfitting and bias.
Results
The study included 102 patients with CAH (62 [60.8%] female; mean [SD] age, 11.6 [7.1] years) and 59 controls (30 [50.8%] female; mean [SD] age, 9.0 [5.2] years) from the clinic and 85 controls (48 [60%] female; age, <29 years) from face databases. With the use of deep neural networks, a mean (SD) AUC of 92% (3%) was found for accurately predicting CAH over sixfold. With the use of classical machine learning and handcrafted facial features, mean (SD) AUCs of 86% (5%) in linear discriminant analysis and 83% (3%) in random forests were obtained for predicting CAH over sixfold. There was a deviation of facial features between groups using deformation fields generated from facial landmark templates. Regionwide analysis and class activation maps (deep learning of regions) revealed that the nose and upper face were most contributory (mean [SD] AUC: 69% [17%] and 71% [13%], respectively).
Conclusions
The findings suggest that facial morphologic features in patients with CAH are distinct and that deep learning can discover subtle facial features to predict CAH. A longitudinal study of facial morphology as a phenotypic biomarker may help expand understanding of adverse lifespan outcomes for patients with CAH.
Relevance to Healthcare Field
Congenital Adrenal Hyperplasia is the most common primary adrenal insufficiency in children. In this study, facial morphologic features in patients with CAH were reliably distinguished from healthy controls using facial landmark templates, demonstrating a tendency for deformation to the center of the face. Facial features could be studied as a phenotypic biomarker from birth or before birth to expand understanding of the clinical phenotype and adverse clinical outcomes in this population and understand the etiology of affected facial morphologic features in patients with CAH.