Comparison of clinical geneticist and computer visual attention in assessing genetic conditions.

Artificial intelligence (AI) for facial diagnostics is increasingly used in the genetics clinic to evaluate patients with potential genetic conditions. Current approaches focus on one type of AI called Deep Learning (DL). While DL- based facial diagnostic platforms have a high accuracy rate for many conditions, less is understood about how this technology assesses and classifies (categorizes) images, and how this compares to humans. To compare human and computer attention, we performed eye-tracking analyses of geneticist clinicians (n = 22) and non-clinicians (n = 22) who viewed images of people with 10 different genetic conditions, as well as images of unaffected individuals. We calculated the Intersection-over-Union (IoU) and Kullback-Leibler divergence (KL) to compare the visual attentions of the two participant groups, and then the clinician group against the saliency maps of our deep learning classifier. We found that human visual attention differs greatly from DL model's saliency results. Averaging over all the test images, IoU and KL metric for the successful (accurate) clinician visual attentions versus the saliency maps were 0.15 and 11.15, respectively. Individuals also tend to have a specific pattern of image inspection, and clinicians demonstrate different visual attention patterns than non-clinicians (IoU and KL of clinicians versus non-clinicians were 0.47 and 2.73, respectively). This study shows that humans (at different levels of expertise) and a computer vision model examine images differently. Understanding these differences can improve the design and use of AI tools, and lead to more meaningful interactions between clinicians and AI technologies.

Approximating facial expression effects on diagnostic accuracy via generative AI in medical genetics.

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 "happy" 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.

Application of facial analysis Technology in Clinical Genetics: Considerations for diverse populations.

Facial analysis technology in rare diseases has the potential to shorten the diagnostic odyssey by providing physicians with a valuable diagnostic tool. Given that most clinical genetic resources focus on populations of European descent, we compare craniofacial features in genetic syndromes across different populations and review how machine learning algorithms perform on diagnosing genetic syndromes in geographically and ethnically diverse populations. We also discuss the value of populations from ancestrally diverse backgrounds in the training set of machine learning algorithms. Finally, this review demonstrates that across diverse population groups, machine learning models have outstanding accuracy as supported by the area under the curve values greater than 0.9. Artificial intelligence is only in its infancy in the diagnosis of rare disease in diverse populations and will become more accurate as larger and more diverse training sets, including a wider spectrum of ages, particularly infants, are studied.

Perspectives on the future of dysmorphology.

The field of clinical genetics and genomics continues to evolve. In the past few decades, milestones like the initial sequencing of the human genome, dramatic changes in sequencing technologies, and the introduction of artificial intelligence, have upended the field and offered fascinating new insights. Though difficult to predict the precise paths the field will follow, rapid change may continue to be inevitable. Within genetics, the practice of dysmorphology, as defined by pioneering geneticist David W. Smith in the 1960s as "the study of, or general subject of abnormal development of tissue form" has also been affected by technological advances as well as more general trends in biomedicine. To address possibilities, potential, and perils regarding the future of dysmorphology, a group of clinical geneticists, representing different career stages, areas of focus, and geographic regions, have contributed to this piece by providing insights about how the practice of dysmorphology will develop over the next several decades.

Scoping review and classification of deep learning in medical genetics.

Deep learning (DL) is applied in many biomedical areas. We performed a scoping review on DL in medical genetics. We first assessed 14,002 articles, of which 133 involved DL in medical genetics. DL in medical genetics increased rapidly during the studied period. In medical genetics, DL has largely been applied to small data sets of affected individuals (mean = 95, median = 29) with genetic conditions (71 different genetic conditions were studied; 24 articles studied multiple conditions). A variety of data types have been used in medical genetics, including radiologic (20%), ophthalmologic (14%), microscopy (8%), and text-based data (4%); the most common data type was patient facial photographs (46%). DL authors and research subjects overrepresent certain geographic areas (United States, Asia, and Europe). Convolutional neural networks (89%) were the most common method. Results were compared with human performance in 31% of studies. In total, 51% of articles provided data access; 16% released source code. To further explore DL in genomics, we conducted an additional analysis, the results of which highlight future opportunities for DL in medical genetics. Finally, we expect DL applications to increase in the future. To aid data curation, we evaluated a DL, random forest, and rule-based classifier at categorizing article abstracts.

Cross-cultural representations of conjoined twins.

Conjoined twinning is a rare birth defect estimated to occur in about 1 in 50,000 to 100,000 births. The mechanism of conjoined twinning is not proven. Different forms of conjoined twinning are observed with the thoracopagus form being the most common. The rate of conjoined twinning is similar across all major populations. A dramatic malformation of this type would be an extraordinary occurrence leading people to reflect on the spiritual or supernatural nature of such an event. Therefore, it is not surprising that artifacts that seem to depict different forms of conjoined twins are seen across diverse cultures. In this article, we present a survey of these cultural artifacts including anatomic classification based on external anatomy and an exploration of the cultural and spiritual contexts associated with the artifacts. A key finding is that the most common form of conjoined twinning in the artifacts is parapagus (both dicephalus and diprosopus) in contrast to thoracopagus, the most common form in epidemiologic studies. Potential reasons for this difference are discussed. Evidence is presented to support the speculation that these objects represent artistic impressions of actual conjoined twinning events.

Comorbidity of congenital heart defects and holoprosencephaly is likely genetically driven and gene-specific.

Comorbidity of holoprosencephaly (HPE) and congenital heart disease (CHD) in individuals with genetic variants in known HPE-related genes has been recurrently observed. Morphogenesis of the brain and heart from very early stages are regulated by several biological pathways, some of them involved in both heart and brain development as evidenced by genetic studies on model organisms. For instance, downregulation of Hedgehog or Nodal signaling pathways, both known as major triggers of HPE, has been shown to play a role in the pathogenesis of CHD, including structural defects and left-right asymmetry defects. In this study, individuals with various types of HPE were investigated clinically and by genomic sequencing. Cardiac phenotypes were assessed in 434 individuals with HPE who underwent targeted sequencing. CHDs were identified in 8% (n = 33) of individuals, including 10 (30%) cases of complex heart disease. Only four individuals (4/33) had damaging variants in the known HPE genes STAG2, SIX3, and SHH. Interestingly, no CHD was identified in the 37 individuals of our cohort with pathogenic variants in ZIC2. These findings suggest that CHD occurs more frequently in HPE-affected individuals with or without identifiable genetic variants, and this co-occurrence may be genetically driven and gene-specific.

MECP2 duplication syndrome in a patient from Cameroon.

MECP2 duplication syndrome (MDS; OMIM 300260) is an X-linked neurodevelopmental disorder caused by nonrecurrent duplications of the Xq28 region involving the gene methyl-CpG-binding protein 2 (MECP2; OMIM 300005). The core phenotype of affected individuals includes infantile hypotonia, severe intellectual disability, very poor-to-absent speech, progressive spasticity, seizures, and recurrent infections. The condition is 100% penetrant in males, with observed variability in phenotypic expression within and between families. Features of MDS in individuals of African descent are not well known. Here, we describe a male patient from Cameroon, with MDS caused by an inherited 610 kb microduplication of Xq28 encompassing the genes MECP2, IRAK1, L1CAM, and SLC6A8. This report supplements the public data on MDS and contributes by highlighting the phenotype of this condition in affected individuals of African descent.

Rubinstein-Taybi syndrome in diverse populations.

Rubinstein-Taybi syndrome (RSTS) is an autosomal dominant disorder, caused by loss-of-function variants in CREBBP or EP300. Affected individuals present with distinctive craniofacial features, broad thumbs and/or halluces, and intellectual disability. RSTS phenotype has been well characterized in individuals of European descent but not in other populations. In this study, individuals from diverse populations with RSTS were assessed by clinical examination and facial analysis technology. Clinical data of 38 individuals from 14 different countries were analyzed. The median age was 7 years (age range: 7 months to 47 years), and 63% were females. The most common phenotypic features in all population groups included broad thumbs and/or halluces in 97%, convex nasal ridge in 94%, and arched eyebrows in 92%. Face images of 87 individuals with RSTS (age range: 2 months to 47 years) were collected for evaluation using facial analysis technology. We compared images from 82 individuals with RSTS against 82 age- and sex-matched controls and obtained an area under the receiver operating characteristic curve (AUC) of 0.99 (p < .001), demonstrating excellent discrimination efficacy. The discrimination was, however, poor in the African group (AUC: 0.79; p = .145). Individuals with EP300 variants were more effectively discriminated (AUC: 0.95) compared with those with CREBBP variants (AUC: 0.93). This study shows that clinical examination combined with facial analysis technology may enable earlier and improved diagnosis of RSTS in diverse populations.

Turner syndrome in diverse populations.

Turner syndrome (TS) is a common multiple congenital anomaly syndrome resulting from complete or partial absence of the second X chromosome. In this study, we explore the phenotype of TS in diverse populations using clinical examination and facial analysis technology. Clinical data from 78 individuals and images from 108 individuals with TS from 19 different countries were analyzed. Individuals were grouped into categories of African descent (African), Asian, Latin American, Caucasian (European descent), and Middle Eastern. The most common phenotype features across all population groups were short stature (86%), cubitus valgus (76%), and low posterior hairline 70%. Two facial analysis technology experiments were conducted: TS versus general population and TS versus Noonan syndrome. Across all ethnicities, facial analysis was accurate in diagnosing TS from frontal facial images as measured by the area under the curve (AUC). An AUC of 0.903 (p < .001) was found for TS versus general population controls and 0.925 (p < .001) for TS versus individuals with Noonan syndrome. In summary, we present consistent clinical findings from global populations with TS and additionally demonstrate that facial analysis technology can accurately distinguish TS from the general population and Noonan syndrome.

Novel heterozygous variants in KMT2D associated with holoprosencephaly.

Lysine methyltransferase 2D (KMT2D; OMIM 602113) encodes a histone methyltransferase involved in transcriptional regulation of the beta-globin and estrogen receptor as part of a large protein complex known as activating signal cointegrator-2-containing complex (ASCOM). Heterozygous germline mutations in the KMT2D gene are known to cause Kabuki syndrome (OMIM 147920), a developmental multisystem disorder. Neither holoprosencephaly nor other defects in human forebrain development have been previously associated with Kabuki syndrome. Here we report two patients diagnosed with alobar holoprosencephaly in their antenatal period with de novo monoallelic KMT2D variants identified by trio-based exome sequencing. The first patient was found to have a stop-gain variant c.12565G>T (p.Gly4189*), while the second patient had a missense variant c.5A>G (p.Asp2Gly). Phenotyping of each patient did not reveal any age-related feature of Kabuki syndrome. These two cases represent the first report on association between KMT2D and holoprosencephaly.

Cornelia de Lange syndrome in diverse populations.

Cornelia de Lange syndrome (CdLS) is a dominant multisystemic malformation syndrome due to mutations in five genes-NIPBL, SMC1A, HDAC8, SMC3, and RAD21. The characteristic facial dysmorphisms include microcephaly, arched eyebrows, synophrys, short nose with depressed bridge and anteverted nares, long philtrum, thin lips, micrognathia, and hypertrichosis. Most affected individuals have intellectual disability, growth deficiency, and upper limb anomalies. This study looked at individuals from diverse populations with both clinical and molecularly confirmed diagnoses of CdLS by facial analysis technology. Clinical data and images from 246 individuals with CdLS were obtained from 15 countries. This cohort included 49% female patients and ages ranged from infancy to 37 years. Individuals were grouped into ancestry categories of African descent, Asian, Latin American, Middle Eastern, and Caucasian. Across these populations, 14 features showed a statistically significant difference. The most common facial features found in all ancestry groups included synophrys, short nose with anteverted nares, and a long philtrum with thin vermillion of the upper lip. Using facial analysis technology we compared 246 individuals with CdLS to 246 gender/age matched controls and found that sensitivity was equal or greater than 95% for all groups. Specificity was equal or greater than 91%. In conclusion, we present consistent clinical findings from global populations with CdLS while demonstrating how facial analysis technology can be a tool to support accurate diagnoses in the clinical setting. This work, along with prior studies in this arena, will assist in earlier detection, recognition, and treatment of CdLS worldwide.

Diversity and dysmorphology.

PURPOSE OF REVIEW: Dysmorphic features result from errors in morphogenesis frequently associated with genetic syndromes. Recognizing patterns of dysmorphic features is a critical step in the diagnosis and management of human congenital anomalies and genetic syndromes. This review presents recent developments in genetic syndromes and their related dysmorphology in diverse populations. RECENT FINDINGS: Clinical findings in patients with genetic syndromes differ in their heterogeneity across different population groups. Some genetic syndromes have variable features in different ethnicities, in part due to specific background exam characteristics such as flat facial profiles or nasal differences; however, other genetic syndromes are similar across different ethnicities. Facial analysis technology is accurate in diagnosing genetic syndromes in populations around the world and is a powerful adjunct to conventional clinical examination. This accuracy also reinforces the concept that genetic syndromes can and should be diagnosed in any ethnicity. SUMMARY: The increasing amount of data from studies on genetic syndromes in diverse populations is significantly improving our knowledge and approach to dysmorphic patients from various ethnic backgrounds. Optimal management of genetic syndromes requires early diagnosis, including in developing countries.

Williams-Beuren syndrome in diverse populations.

Williams-Beuren syndrome (WBS) is a common microdeletion syndrome characterized by a 1.5Mb deletion in 7q11.23. The phenotype of WBS has been well described in populations of European descent with not as much attention given to other ethnicities. In this study, individuals with WBS from diverse populations were assessed clinically and by facial analysis technology. Clinical data and images from 137 individuals with WBS were found in 19 countries with an average age of 11 years and female gender of 45%. The most common clinical phenotype elements were periorbital fullness and intellectual disability which were present in greater than 90% of our cohort. Additionally, 75% or greater of all individuals with WBS had malar flattening, long philtrum, wide mouth, and small jaw. Using facial analysis technology, we compared 286 Asian, African, Caucasian, and Latin American individuals with WBS with 286 gender and age matched controls and found that the accuracy to discriminate between WBS and controls was 0.90 when the entire cohort was evaluated concurrently. The test accuracy of the facial recognition technology increased significantly when the cohort was analyzed by specific ethnic population (P-value < 0.001 for all comparisons), with accuracies for Caucasian, African, Asian, and Latin American groups of 0.92, 0.96, 0.92, and 0.93, respectively. In summary, we present consistent clinical findings from global populations with WBS and demonstrate how facial analysis technology can support clinicians in making accurate WBS diagnoses.

Noonan syndrome in diverse populations.

Noonan syndrome (NS) is a common genetic syndrome associated with gain of function variants in genes in the Ras/MAPK pathway. The phenotype of NS has been well characterized in populations of European descent with less attention given to other groups. In this study, individuals from diverse populations with NS were evaluated clinically and by facial analysis technology. Clinical data and images from 125 individuals with NS were obtained from 20 countries with an average age of 8 years and female composition of 46%. Individuals were grouped into categories of African descent (African), Asian, Latin American, and additional/other. Across these different population groups, NS was phenotypically similar with only 2 of 21 clinical elements showing a statistically significant difference. The most common clinical characteristics found in all population groups included widely spaced eyes and low-set ears in 80% or greater of participants, short stature in more than 70%, and pulmonary stenosis in roughly half of study individuals. Using facial analysis technology, we compared 161 Caucasian, African, Asian, and Latin American individuals with NS with 161 gender and age matched controls and found that sensitivity was equal to or greater than 94% for all groups, and specificity was equal to or greater than 90%. In summary, we present consistent clinical findings from global populations with NS and additionally demonstrate how facial analysis technology can support clinicians in making accurate NS diagnoses. This work will assist in earlier detection and in increasing recognition of NS throughout the world.

Recognition of Genetic Conditions After Learning With Images Created Using Generative Artificial Intelligence.

Importance: The lack of standardized genetics training in pediatrics residencies, along with a shortage of medical geneticists, necessitates innovative educational approaches. Objective: To compare pediatric resident recognition of Kabuki syndrome (KS) and Noonan syndrome (NS) after 1 of 4 educational interventions, including generative artificial intelligence (AI) methods. Design, Setting, and Participants: This comparative effectiveness study used generative AI to create images of children with KS and NS. From October 1, 2022, to February 28, 2023, US pediatric residents were provided images through a web-based survey to assess whether these images helped them recognize genetic conditions. Interventions: Participants categorized 20 images after exposure to 1 of 4 educational interventions (text-only descriptions, real images, and 2 types of images created by generative AI). Main Outcomes and Measures: Associations between educational interventions with accuracy and self-reported confidence. Results: Of 2515 contacted pediatric residents, 106 and 102 completed the KS and NS surveys, respectively. For KS, the sensitivity of text description was 48.5% (128 of 264), which was not significantly different from random guessing (odds ratio [OR], 0.94; 95% CI, 0.69-1.29; P = .71). Sensitivity was thus compared for real images vs random guessing (60.3% [188 of 312]; OR, 1.52; 95% CI, 1.15-2.00; P = .003) and 2 types of generative AI images vs random guessing (57.0% [212 of 372]; OR, 1.32; 95% CI, 1.04-1.69; P = .02 and 59.6% [193 of 324]; OR, 1.47; 95% CI, 1.12-1.94; P = .006) (denominators differ according to survey responses). The sensitivity of the NS text-only description was 65.3% (196 of 300). Compared with text-only, the sensitivity of the real images was 74.3% (205 of 276; OR, 1.53; 95% CI, 1.08-2.18; P = .02), and the sensitivity of the 2 types of images created by generative AI was 68.0% (204 of 300; OR, 1.13; 95% CI, 0.77-1.66; P = .54) and 71.0% (247 of 328; OR, 1.30; 95% CI, 0.92-1.83; P = .14). For specificity, no intervention was statistically different from text only. After the interventions, the number of participants who reported being unsure about important diagnostic facial features decreased from 56 (52.8%) to 5 (7.6%) for KS (P < .001) and 25 (24.5%) to 4 (4.7%) for NS (P < .001). There was a significant association between confidence level and sensitivity for real and generated images. Conclusions and Relevance: In this study, real and generated images helped participants recognize KS and NS; real images appeared most helpful. Generated images were noninferior to real images and could serve an adjunctive role, particularly for rare conditions.

Bridging the language gap - A call for the wider use of Human phenotype ontology by non-geneticist clinicians when requesting genomic tests.

Advances in genomic technology including the development of next-generation sequencing (NGS) have enabled the identification of thousands of variations at a time, allowing the discovery of novel genetic diseases. Given the volume of data generated by these investigations, attention is drawn towards reporting relevant clinical features by clinicians to guide the diagnosis and management of their patients. The Human Phenotype Ontology (HPO) developed in 2008, revolutionized the semantic vocabulary of phenotypic descriptions in genomic medicine allowing researchers, laboratories and clinical geneticists to better understand each other. In this era of personalized medicine where genetic tests are becoming more accessible, non-geneticist clinicians are expected to be more involved than ever in the process of ordering genetic tests and interpreting genetic reports. It is therefore essential that they understand and adequately apply HPO nomenclature to integrate the patient care chain and seize the opportunity offered by this tailored language. The current article highlights the importance of using HPO vocabularies in clinical practice and advocates for its wider use by non-geneticist clinicians. Correct use of HPO will reduce misunderstandings between healthcare professionals and ultimately improve the healthcare system.

Generative Methods for Pediatric Genetics Education.

Artificial intelligence (AI) is used in an increasing number of areas, with recent interest in generative AI, such as using ChatGPT to generate programming code or DALL-E to make illustrations. We describe the use of generative AI in medical education. Specifically, we sought to determine whether generative AI could help train pediatric residents to better recognize genetic conditions. From publicly available images of individuals with genetic conditions, we used generative AI methods to create new images, which were checked for accuracy with an external classifier. We selected two conditions for study, Kabuki (KS) and Noonan (NS) syndromes, which are clinically important conditions that pediatricians may encounter. In this study, pediatric residents completed 208 surveys, where they each classified 20 images following exposure to one of 4 possible educational interventions, including with and without generative AI methods. Overall, we find that generative images perform similarly but appear to be slightly less helpful than real images. Most participants reported that images were useful, although real images were felt to be more helpful. We conclude that generative AI images may serve as an adjunctive educational tool, particularly for less familiar conditions, such as KS.

Human and computer attention in assessing genetic conditions.

Deep learning (DL) and other types of artificial intelligence (AI) are increasingly used in many biomedical areas, including genetics. One frequent use in medical genetics involves evaluating images of people with potential genetic conditions to help with diagnosis. A central question involves better understanding how AI classifiers assess images compared to humans. To explore this, we performed eye-tracking analyses of geneticist clinicians and non-clinicians. We compared results to DL-based saliency maps. We found that human visual attention when assessing images differs greatly from the parts of images weighted by the DL model. Further, individuals tend to have a specific pattern of image inspection, and clinicians demonstrate different visual attention patterns than non-clinicians.

Neural network classifiers for images of genetic conditions with cutaneous manifestations.

Neural networks have shown strong potential in research and in healthcare. Mainly due to the need for large datasets, these applications have focused on common medical conditions, where more data are typically available. Leveraging publicly available data, we trained a neural network classifier on images of rare genetic conditions with skin findings. We used approximately 100 images per condition to classify 6 different genetic conditions. We analyzed both preprocessed images that were cropped to show only the skin lesions as well as more complex images showing features such as the entire body segment, the person, and/or the background. The classifier construction process included attribution methods to visualize which pixels were most important for computer-based classification. Our classifier was significantly more accurate than pediatricians or medical geneticists for both types of images and suggests steps for further research involving clinical scenarios and other applications.