{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:03:29Z","timestamp":1773795809137,"version":"3.50.1"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T00:00:00Z","timestamp":1719532800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100030692","name":"Intramural Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100030692","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Summary<\/jats:p>\n               <jats:p>Artificial intelligence (AI) is increasingly used in genomics research and practice, and generative AI has garnered significant recent attention. In clinical applications of generative AI, aspects of the underlying datasets can impact results, and confounders should be studied and mitigated. One example involves the facial expressions of people with genetic conditions. Stereotypically, Williams (WS) and Angelman (AS) syndromes are associated with a \u201chappy\u201d demeanor, including a smiling expression. Clinical geneticists may be more likely to identify these conditions in images of smiling individuals. To study the impact of facial expression, we analyzed publicly available facial images of approximately 3500 individuals with genetic conditions. Using a deep learning (DL) image classifier, we found that WS and AS images with non-smiling expressions had significantly lower prediction probabilities for the correct syndrome labels than those with smiling expressions. This was not seen for 22q11.2 deletion and Noonan syndromes, which are not associated with a smiling expression. To further explore the effect of facial expressions, we computationally altered the facial expressions for these images. We trained HyperStyle, a GAN-inversion technique compatible with StyleGAN2, to determine the vector representations of our images. Then, following the concept of InterfaceGAN, we edited these vectors to recreate the original images in a phenotypically accurate way but with a different facial expression. Through online surveys and an eye-tracking experiment, we examined how altered facial expressions affect the performance of human experts. We overall found that facial expression is associated with diagnostic accuracy variably in different genetic conditions.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btae239","type":"journal-article","created":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T09:23:08Z","timestamp":1719566588000},"page":"i110-i118","source":"Crossref","is-referenced-by-count":12,"title":["Approximating facial expression effects on diagnostic accuracy <i>via<\/i> generative AI in medical genetics"],"prefix":"10.1093","volume":"40","author":[{"given":"Tanviben","family":"Patel","sequence":"first","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"Amna A","family":"Othman","sequence":"additional","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"\u00d6mer","family":"S\u00fcmer","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Augsburg University , Augsburg, Bavaria 86159, Germany"}]},{"given":"Fabio","family":"Hellman","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Augsburg University , Augsburg, Bavaria 86159, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3194-8625","authenticated-orcid":false,"given":"Peter","family":"Krawitz","sequence":"additional","affiliation":[{"name":"Institute for Genomic Statistics and Bioinformatics, University of Bonn , Bonn, North Rhine-Westphalia 53113, Germany"}]},{"given":"Elisabeth","family":"Andr\u00e9","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Augsburg University , Augsburg, Bavaria 86159, Germany"}]},{"given":"Molly E","family":"Ripper","sequence":"additional","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"Chris","family":"Fortney","sequence":"additional","affiliation":[{"name":"Social and Behavioral Research Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7768-5744","authenticated-orcid":false,"given":"Susan","family":"Persky","sequence":"additional","affiliation":[{"name":"Social and Behavioral Research Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"Ping","family":"Hu","sequence":"additional","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"Cedrik","family":"Tekendo-Ngongang","sequence":"additional","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"Suzanna Ledgister","family":"Hanchard","sequence":"additional","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"Kendall A","family":"Flaharty","sequence":"additional","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"Rebekah L","family":"Waikel","sequence":"additional","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"Dat","family":"Duong","sequence":"additional","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]},{"given":"Benjamin D","family":"Solomon","sequence":"additional","affiliation":[{"name":"Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute , Bethesda, MA 20892, United States"}]}],"member":"286","published-online":{"date-parts":[[2024,6,28]]},"reference":[{"key":"2024062809003879600_btae239-B1","first-page":"4432","author":"Abdal","year":"2019"},{"key":"2024062809003879600_btae239-B2","first-page":"18511","author":"Alaluf","year":"2022"},{"key":"2024062809003879600_btae239-B3","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1007\/s00787-018-1174-4","article-title":"Emotional face recognition in male adolescents with autism spectrum disorder or disruptive behavior disorder: an eye-tracking study","volume":"27","author":"Bours","year":"2018","journal-title":"Eur Child Adolesc Psychiatry"},{"key":"2024062809003879600_btae239-B4","first-page":"2406","author":"Cao","year":"2018"},{"key":"2024062809003879600_btae239-B5","first-page":"67","author":"Cao","year":"2018"},{"key":"2024062809003879600_btae239-B6","doi-asserted-by":"crossref","first-page":"e0266442","DOI":"10.1371\/journal.pone.0266442","article-title":"Callifacs: the common marmoset facial action coding system","volume":"17","author":"Correia-Caeiro","year":"2022","journal-title":"PLoS One"},{"key":"2024062809003879600_btae239-B7","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1038\/s42256-021-00338-7","article-title":"AI for radiographic covid-19 detection selects shortcuts over signal","volume":"3","author":"DeGrave","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2024062809003879600_btae239-B8","doi-asserted-by":"crossref","first-page":"864092","DOI":"10.3389\/fgene.2022.864092","article-title":"Neural networks for classification and image generation of aging in genetic syndromes","volume":"13","author":"Duong","year":"2022","journal-title":"Front Genet"},{"key":"2024062809003879600_btae239-B9","author":"Duong","year":"2023"},{"key":"2024062809003879600_btae239-B10","doi-asserted-by":"crossref","first-page":"100053","DOI":"10.1016\/j.xhgg.2021.100053","article-title":"Neural network classifiers for images of genetic conditions with cutaneous manifestations","volume":"3","author":"Duong","year":"2022","journal-title":"Hum Genet Genom Adv"},{"key":"2024062809003879600_btae239-B11","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1007\/BF01115465","article-title":"Environmental psychology & nonverbal behavior","volume":"1","author":"Ekman","year":"1976","journal-title":"J Nonverbal Behav"},{"key":"2024062809003879600_btae239-B12","first-page":"87","author":"Guo","year":"2016"},{"key":"2024062809003879600_btae239-B13","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1016\/j.gim.2022.04.025","article-title":"Scoping review and classification of deep learning in medical genetics","volume":"24","author":"Hanchard","year":"2022","journal-title":"Genet Med"},{"key":"2024062809003879600_btae239-B14","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1038\/s41588-021-01010-x","article-title":"Gestaltmatcher facilitates rare disease matching using facial phenotype descriptors","volume":"54","author":"Hsieh","year":"2022","journal-title":"Nat Genet"},{"key":"2024062809003879600_btae239-B15","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.gim.2021.08.015","article-title":"Cost-effectiveness of genome sequencing for diagnosing patients with undiagnosed rare genetic diseases","volume":"24","author":"Incerti","year":"2022","journal-title":"Genet Med"},{"key":"2024062809003879600_btae239-B16","volume-title":"Smith\u2019s Recognizable Patterns of Human Malformation \u2013 E-book","author":"Jones","year":"2021"},{"key":"2024062809003879600_btae239-B17","first-page":"4401","author":"Karras","year":"2019"},{"key":"2024062809003879600_btae239-B18","author":"Krawitz","year":"2021"},{"key":"2024062809003879600_btae239-B19","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1002\/ajmg.a.38362","article-title":"Noonan syndrome in diverse populations","volume":"173","author":"Kruszka","year":"2017","journal-title":"Am J Med Genet A"},{"key":"2024062809003879600_btae239-B20","doi-asserted-by":"crossref","first-page":"e32059","DOI":"10.1002\/ajmg.c.32059","article-title":"Application of facial analysis technology in clinical genetics: considerations for diverse populations","volume":"193","author":"Kruszka","year":"2023","journal-title":"Am J Med Genet C Semin Med Genet"},{"key":"2024062809003879600_btae239-B21","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1109\/TAFFC.2020.2973158","article-title":"A deeper look at facial expression dataset bias","volume":"13","author":"Li","year":"2022","journal-title":"IEEE Trans Affective Comput"},{"key":"2024062809003879600_btae239-B22","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1111\/j.1469-7610.2007.01736.x","article-title":"Genomic imprinting and the expression of affect in Angelman syndrome: what\u2019s in the smile?","volume":"48","author":"Oliver","year":"2007","journal-title":"J Child Psychol Psychiatry"},{"key":"2024062809003879600_btae239-B23","first-page":"2988","author":"Pe\u00f1a","year":"2021"},{"key":"2024062809003879600_btae239-B24","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/B978-0-12-815739-8.00006-7","volume-title":"Machine Learning","author":"Pisner","year":"2020"},{"key":"2024062809003879600_btae239-B25","doi-asserted-by":"crossref","first-page":"e635","DOI":"10.1016\/S2589-7500(21)00137-0","article-title":"Development and evaluation of a machine learning-based point-of-care screening tool for genetic syndromes in children: a multinational retrospective study","volume":"3","author":"Porras","year":"2021","journal-title":"Lancet Digit Health"},{"key":"2024062809003879600_btae239-B26","first-page":"8821","author":"Ramesh","year":"2021"},{"key":"2024062809003879600_btae239-B27","doi-asserted-by":"crossref","first-page":"462","DOI":"10.3389\/fgene.2018.00462","article-title":"Facial genetics: a brief overview","volume":"9","author":"Richmond","year":"2018","journal-title":"Front Genet"},{"key":"2024062809003879600_btae239-B28","first-page":"10684","author":"Rombach","year":"2022"},{"key":"2024062809003879600_btae239-B29","volume-title":"What the Face Reveals: Basic and Applied Studies of Spontaneous Expression using the Facial Action Coding System (FACS)","author":"Rosenberg","year":"2020"},{"key":"2024062809003879600_btae239-B30","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1186\/s13023-020-01424-6","article-title":"The use of machine learning in rare diseases: a scoping review","volume":"15","author":"Schaefer","year":"2020","journal-title":"Orphanet J Rare Dis"},{"key":"2024062809003879600_btae239-B31","doi-asserted-by":"crossref","first-page":"2004","DOI":"10.1109\/TPAMI.2020.3034267","article-title":"Interfacegan: interpreting the disentangled face representation learned by GANS","volume":"44","author":"Shen","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2024062809003879600_btae239-B32","doi-asserted-by":"crossref","first-page":"e0223905","DOI":"10.1371\/journal.pone.0223905","article-title":"Assessing the convergent validity between the automated emotion recognition software noldus FaceReader 7 and facial action coding system scoring","volume":"14","author":"Skiendziel","year":"2019","journal-title":"PLoS One"},{"key":"2024062809003879600_btae239-B33","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1002\/ajmg.a.63060","article-title":"Perspectives on the future of dysmorphology","volume":"191","author":"Solomon","year":"2023","journal-title":"Am J Med Genet A"},{"key":"2024062809003879600_btae239-B34","doi-asserted-by":"crossref","first-page":"9851","DOI":"10.1073\/pnas.1302575110","article-title":"Clinical genomic database","volume":"110","author":"Solomon","year":"2013","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2024062809003879600_btae239-B35","first-page":"712","author":"S\u00fcmer","year":"2023"},{"key":"2024062809003879600_btae239-B36","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0896-6273(01)00476-7","article-title":"New frontiers in Alzheimer\u2019s disease genetics","volume":"32","author":"Tanzi","year":"2001","journal-title":"Neuron"},{"key":"2024062809003879600_btae239-B37","doi-asserted-by":"crossref","first-page":"2939","DOI":"10.1002\/ajmg.a.61888","article-title":"Rubinstein\u2013Taybi syndrome in diverse populations","volume":"182","author":"Tekendo-Ngongang","year":"2020","journal-title":"Am J Med Genet A"},{"key":"2024062809003879600_btae239-B38","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/34.908962","article-title":"Recognizing action units for facial expression analysis","volume":"23","author":"Tian","year":"2001","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2024062809003879600_btae239-B39","author":"Von Oswald","year":"2019"},{"key":"2024062809003879600_btae239-B40","author":"Waikel","year":"2023"},{"key":"2024062809003879600_btae239-B41","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/s43681-021-00108-6","article-title":"Bias, awareness, and ignorance in deep-learning-based face recognition","volume":"2","author":"Wehrli","year":"2022","journal-title":"AI Ethics"},{"key":"2024062809003879600_btae239-B42","author":"Wright","year":"2019"},{"key":"2024062809003879600_btae239-B43","first-page":"7559","article-title":"Differentiable augmentation for data-efficient GAN training","volume":"33","author":"Zhao","year":"2020","journal-title":"Adv Neural Inform Process Syst"},{"key":"2024062809003879600_btae239-B44","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.neucom.2020.03.036","article-title":"Action unit analysis enhanced facial expression recognition by deep neural network evolution","volume":"425","author":"Zhi","year":"2021","journal-title":"Neurocomputing"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/Supplement_1\/i110\/58354849\/btae239.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/Supplement_1\/i110\/58354849\/btae239.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T09:23:29Z","timestamp":1719566609000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/40\/Supplement_1\/i110\/7700869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,28]]},"references-count":44,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2024,6,28]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae239","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,6,28]]}}}