1
|
Reiter AMV, Pantel JT, Danyel M, Horn D, Ott CE, Mensah MA. Validation of 3 Computer-Aided Facial Phenotyping Tools (DeepGestalt, GestaltMatcher, and D-Score): Comparative Diagnostic Accuracy Study. J Med Internet Res 2024; 26:e42904. [PMID: 38477981 DOI: 10.2196/42904] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2022] [Revised: 04/19/2023] [Accepted: 11/17/2023] [Indexed: 03/14/2024] Open
Abstract
BACKGROUND While characteristic facial features provide important clues for finding the correct diagnosis in genetic syndromes, valid assessment can be challenging. The next-generation phenotyping algorithm DeepGestalt analyzes patient images and provides syndrome suggestions. GestaltMatcher matches patient images with similar facial features. The new D-Score provides a score for the degree of facial dysmorphism. OBJECTIVE We aimed to test state-of-the-art facial phenotyping tools by benchmarking GestaltMatcher and D-Score and comparing them to DeepGestalt. METHODS Using a retrospective sample of 4796 images of patients with 486 different genetic syndromes (London Medical Database, GestaltMatcher Database, and literature images) and 323 inconspicuous control images, we determined the clinical use of D-Score, GestaltMatcher, and DeepGestalt, evaluating sensitivity; specificity; accuracy; the number of supported diagnoses; and potential biases such as age, sex, and ethnicity. RESULTS DeepGestalt suggested 340 distinct syndromes and GestaltMatcher suggested 1128 syndromes. The top-30 sensitivity was higher for DeepGestalt (88%, SD 18%) than for GestaltMatcher (76%, SD 26%). DeepGestalt generally assigned lower scores but provided higher scores for patient images than for inconspicuous control images, thus allowing the 2 cohorts to be separated with an area under the receiver operating characteristic curve (AUROC) of 0.73. GestaltMatcher could not separate the 2 classes (AUROC 0.55). Trained for this purpose, D-Score achieved the highest discriminatory power (AUROC 0.86). D-Score's levels increased with the age of the depicted individuals. Male individuals yielded higher D-scores than female individuals. Ethnicity did not appear to influence D-scores. CONCLUSIONS If used with caution, algorithms such as D-score could help clinicians with constrained resources or limited experience in syndromology to decide whether a patient needs further genetic evaluation. Algorithms such as DeepGestalt could support diagnosing rather common genetic syndromes with facial abnormalities, whereas algorithms such as GestaltMatcher could suggest rare diagnoses that are unknown to the clinician in patients with a characteristic, dysmorphic face.
Collapse
Affiliation(s)
- Alisa Maria Vittoria Reiter
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Jean Tori Pantel
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
- Institute for Digitalization and General Medicine, University Hospital Aachen, Aachen, Germany
- Center for Rare Diseases Aachen ZSEA, University Hospital Aachen, Aachen, Germany
| | - Magdalena Danyel
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
- BIH Biomedical Innovation Academy, Clinician Scientist Program, Berlin Institute of Health at Charité-Universitätsmedizin Berlin, Berlin, Germany
- Berlin Center for Rare Diseases, Charité - Universitätsmedizin Berlin corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Denise Horn
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Claus-Eric Ott
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Martin Atta Mensah
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
- BIH Biomedical Innovation Academy, Digital Clinician Scientist Program, Berlin Institute of Health at Charité-Universitätsmedizin Berlin, Berlin, Germany
| |
Collapse
|
2
|
AbdAlmageed W, Mirzaalian H, Guo X, Randolph LM, Tanawattanacharoen VK, Geffner ME, Ross HM, Kim MS. Assessment of Facial Morphologic Features in Patients With Congenital Adrenal Hyperplasia Using Deep Learning. JAMA Netw Open 2020; 3:e2022199. [PMID: 33206189 PMCID: PMC7675110 DOI: 10.1001/jamanetworkopen.2020.22199] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/10/2023] Open
Abstract
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. OBJECTIVE To investigate differences in facial morphologic features between patients with CAH and control individuals with 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. MAIN OUTCOMES AND MEASURES The main outcome was 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 regionwise 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 use of deep neural networks, a mean (SD) AUC of 92% (3%) was found for accurately predicting CAH over 6 folds. With 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 6 folds. There was a deviation of facial features between groups using deformation fields generated from facial landmark templates. Regionwise 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 AND RELEVANCE The findings suggest that facial morphologic features in patients with CAH is distinct and that deep learning can discover subtle facial features to predict CAH. Longitudinal study of facial morphology as a phenotypic biomarker may help expand understanding of adverse lifespan outcomes for patients with CAH.
Collapse
Affiliation(s)
- Wael AbdAlmageed
- Information Sciences Institute, University of Southern California, Los Angeles
- Department of Electrical and Computer Engineering, University of Southern California, Los Angeles
| | - Hengameh Mirzaalian
- Information Sciences Institute, University of Southern California, Los Angeles
| | - Xiao Guo
- Information Sciences Institute, University of Southern California, Los Angeles
| | - Linda M. Randolph
- Division of Medical Genetics, Children’s Hospital Los Angeles, Los Angeles, California
- Keck School of Medicine of the University of Southern California, Los Angeles
| | | | - Mitchell E. Geffner
- Keck School of Medicine of the University of Southern California, Los Angeles
- Center for Endocrinology, Diabetes, and Metabolism, Children’s Hospital Los Angeles, Los Angeles, California
- The Saban Research Institute at Children’s Hospital Los Angeles, Los Angeles, California
| | - Heather M. Ross
- Center for Endocrinology, Diabetes, and Metabolism, Children’s Hospital Los Angeles, Los Angeles, California
| | - Mimi S. Kim
- Keck School of Medicine of the University of Southern California, Los Angeles
- Center for Endocrinology, Diabetes, and Metabolism, Children’s Hospital Los Angeles, Los Angeles, California
- The Saban Research Institute at Children’s Hospital Los Angeles, Los Angeles, California
| |
Collapse
|
3
|
Pantel JT, Hajjir N, Danyel M, Elsner J, Abad-Perez AT, Hansen P, Mundlos S, Spielmann M, Horn D, Ott CE, Mensah MA. Efficiency of Computer-Aided Facial Phenotyping (DeepGestalt) in Individuals With and Without a Genetic Syndrome: Diagnostic Accuracy Study. J Med Internet Res 2020; 22:e19263. [PMID: 33090109 PMCID: PMC7644377 DOI: 10.2196/19263] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2020] [Revised: 06/26/2020] [Accepted: 07/26/2020] [Indexed: 12/11/2022] Open
Abstract
Background Collectively, an estimated 5% of the population have a genetic disease. Many of them feature characteristics that can be detected by facial phenotyping. Face2Gene CLINIC is an online app for facial phenotyping of patients with genetic syndromes. DeepGestalt, the neural network driving Face2Gene, automatically prioritizes syndrome suggestions based on ordinary patient photographs, potentially improving the diagnostic process. Hitherto, studies on DeepGestalt’s quality highlighted its sensitivity in syndromic patients. However, determining the accuracy of a diagnostic methodology also requires testing of negative controls. Objective The aim of this study was to evaluate DeepGestalt's accuracy with photos of individuals with and without a genetic syndrome. Moreover, we aimed to propose a machine learning–based framework for the automated differentiation of DeepGestalt’s output on such images. Methods Frontal facial images of individuals with a diagnosis of a genetic syndrome (established clinically or molecularly) from a convenience sample were reanalyzed. Each photo was matched by age, sex, and ethnicity to a picture featuring an individual without a genetic syndrome. Absence of a facial gestalt suggestive of a genetic syndrome was determined by physicians working in medical genetics. Photos were selected from online reports or were taken by us for the purpose of this study. Facial phenotype was analyzed by DeepGestalt version 19.1.7, accessed via Face2Gene CLINIC. Furthermore, we designed linear support vector machines (SVMs) using Python 3.7 to automatically differentiate between the 2 classes of photographs based on DeepGestalt's result lists. Results We included photos of 323 patients diagnosed with 17 different genetic syndromes and matched those with an equal number of facial images without a genetic syndrome, analyzing a total of 646 pictures. We confirm DeepGestalt’s high sensitivity (top 10 sensitivity: 295/323, 91%). DeepGestalt’s syndrome suggestions in individuals without a craniofacially dysmorphic syndrome followed a nonrandom distribution. A total of 17 syndromes appeared in the top 30 suggestions of more than 50% of nondysmorphic images. DeepGestalt’s top scores differed between the syndromic and control images (area under the receiver operating characteristic [AUROC] curve 0.72, 95% CI 0.68-0.76; P<.001). A linear SVM running on DeepGestalt’s result vectors showed stronger differences (AUROC 0.89, 95% CI 0.87-0.92; P<.001). Conclusions DeepGestalt fairly separates images of individuals with and without a genetic syndrome. This separation can be significantly improved by SVMs running on top of DeepGestalt, thus supporting the diagnostic process of patients with a genetic syndrome. Our findings facilitate the critical interpretation of DeepGestalt’s results and may help enhance it and similar computer-aided facial phenotyping tools.
Collapse
Affiliation(s)
- Jean Tori Pantel
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.,Institute for Genomic Statistics and Bioinformatics, University Hospital Bonn, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - Nurulhuda Hajjir
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.,Klinik für Pädiatrie mit Schwerpunkt Gastroenterologie, Nephrologie und Stoffwechselmedizin, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany
| | - Magdalena Danyel
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.,Berlin Center for Rare Diseases, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany
| | - Jonas Elsner
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany
| | - Angela Teresa Abad-Perez
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany
| | - Peter Hansen
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.,The Jackson Laboratory for Genomic Medicine, Farmington, CT, United States
| | - Stefan Mundlos
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.,RG Development & Disease, Max Planck Institute for Molecular Genetics, Berlin, Germany
| | - Malte Spielmann
- RG Development & Disease, Max Planck Institute for Molecular Genetics, Berlin, Germany.,Institute of Human Genetics, University of Lübeck, Lübeck, Germany
| | - Denise Horn
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany
| | - Claus-Eric Ott
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany
| | - Martin Atta Mensah
- Institute of Medical Genetics and Human Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Berlin, Germany.,Berlin Institute of Health, Berlin, Germany
| |
Collapse
|
4
|
Fontana P, Passaretti FF, Maioli M, Cantalupo G, Scarano F, Lonardo F. Clinical and molecular spectrum of Wiedemann-Steiner syndrome, an emerging member of the chromatinopathy family. World J Med Genet 2020; 9:1-11. [DOI: 10.5496/wjmg.v9.i1.1] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/14/2020] [Revised: 04/19/2020] [Accepted: 05/14/2020] [Indexed: 02/06/2023] Open
Abstract
Wiedemann-Steiner syndrome (OMIM #605130) is a rare congenital malformation syndrome characterized by hypertrichosis cubiti associated with short stature; consistent facial features, including long eyelashes, thick or arched eyebrows with a lateral flare, wide nasal bridge, and downslanting and vertically narrow palpebral fissures; mild to moderate intellectual disability; behavioral difficulties; and hypertrichosis on the back. It is caused by heterozygous pathogenic variants in KMT2A. This gene has an established role in histone methylation, which explains the overlap of Wiedemann-Steiner syndrome with other chromatinopathies, a heterogeneous group of syndromic conditions that share a common trigger: The disruption of one of the genes involved in chromatin modification, leading to dysfunction of the epigenetic machinery.
Collapse
Affiliation(s)
- Paolo Fontana
- Medical Genetics Unit, San Pio Hospital, Benevento 82100, Italy
| | | | - Marianna Maioli
- Medical Genetics Unit, San Pio Hospital, Benevento 82100, Italy
| | | | | | | |
Collapse
|
5
|
Abstract
Dysmorphology is the practice of defining the morphologic phenotype of syndromic disorders. Genomic sequencing has advanced our understanding of human variation and molecular dysmorphology has evolved in response to the science of relating embryologic developmental implications of abnormal gene signaling pathways to the resultant phenotypic presentation. Machine learning has enabled the application of deep convoluted neural networks to recognize the comparative likeness of these phenotypes relative to the causal genotype or disrupted gene pathway.
Collapse
Affiliation(s)
- Donald Basel
- Department of Pediatrics, Division of Genetics, Medical College of Wisconsin, 9000 West Wisconsin Avenue, MS #716, Milwaukee, WI 53226, USA.
| |
Collapse
|