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.

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.

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.

Analysis of large-language model versus human performance for genetics questions.

Large-language models like ChatGPT have recently received a great deal of attention. One area of interest pertains to how these models could be used in biomedical contexts, including related to human genetics. To assess one facet of this, we compared the performance of ChatGPT versus human respondents (13,642 human responses) in answering 85 multiple-choice questions about aspects of human genetics. Overall, ChatGPT did not perform significantly differently (p = 0.8327) than human respondents; ChatGPT was 68.2% accurate, compared to 66.6% accuracy for human respondents. Both ChatGPT and humans performed better on memorization-type questions versus critical thinking questions (p < 0.0001). When asked the same question multiple times, ChatGPT frequently provided different answers (16% of initial responses), including for both initially correct and incorrect answers, and gave plausible explanations for both correct and incorrect answers. ChatGPT's performance was impressive, but currently demonstrates significant shortcomings for clinical or other high-stakes use. Addressing these limitations will be important to guide adoption in real-life situations.

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.

Analysis of large-language model versus human performance for genetics questions.

Large-language models like ChatGPT have recently received a great deal of attention. To assess ChatGPT in the field of genetics, we compared its performance to human respondents in answering genetics questions (involving 13,636 responses) that had been posted on social media platforms starting in 2021. Overall, ChatGPT did not perform significantly differently than human respondents, but did significantly better on memorization-type questions versus critical thinking questions, frequently provided different answers when asked questions multiple times, and provided plausible explanations for both correct and incorrect answers.

Investigating Determinants and Evaluating Deep Learning Training Approaches for Visual Acuity in Foveal Hypoplasia.

Purpose: To describe the relationships between foveal structure and visual function in a cohort of individuals with foveal hypoplasia (FH) and to estimate FH grade and visual acuity using a deep learning classifier. Design: Retrospective cohort study and experimental study. Participants: A total of 201 patients with FH were evaluated at the National Eye Institute from 2004 to 2018. Methods: Structural components of foveal OCT scans and corresponding clinical data were analyzed to assess their contributions to visual acuity. To automate FH scoring and visual acuity correlations, we evaluated the following 3 inputs for training a neural network predictor: (1) OCT scans, (2) OCT scans and metadata, and (3) real OCT scans and fake OCT scans created from a generative adversarial network. Main Outcome Measures: The relationships between visual acuity outcomes and determinants, such as foveal morphology, nystagmus, and refractive error. Results: The mean subject age was 24.4 years (range, 1-73 years; standard deviation = 18.25 years) at the time of OCT imaging. The mean best-corrected visual acuity (n = 398 eyes) was equivalent to a logarithm of the minimal angle of resolution (LogMAR) value of 0.75 (Snellen 20/115). Spherical equivalent refractive error (SER) ranged from -20.25 diopters (D) to +13.63 D with a median of +0.50 D. The presence of nystagmus and a high-LogMAR value showed a statistically significant relationship (P < 0.0001). The participants whose SER values were farther from plano demonstrated higher LogMAR values (n = 382 eyes). The proportion of patients with nystagmus increased with a higher FH grade. Variability in SER with grade 4 (range, -20.25 D to +13.00 D) compared with grade 1 (range, -8.88 D to +8.50 D) was statistically significant (P < 0.0001). Our neural network predictors reliably estimated the FH grading and visual acuity (correlation to true value > 0.85 and > 0.70, respectively) for a test cohort of 37 individuals (98 OCT scans). Training the predictor on real OCT scans with metadata and fake OCT scans improved the accuracy over the model trained on real OCT scans alone. Conclusions: Nystagmus and foveal anatomy impact visual outcomes in patients with FH, and computational algorithms reliably estimate FH grading and visual acuity.

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.

Neural Networks for Classification and Image Generation of Aging in Genetic Syndromes.

Background: In medical genetics, one application of neural networks is the diagnosis of genetic diseases based on images of patient faces. While these applications have been validated in the literature with primarily pediatric subjects, it is not known whether these applications can accurately diagnose patients across a lifespan. We aimed to extend previous works to determine whether age plays a factor in facial diagnosis as well as to explore other factors that may contribute to the overall diagnostic accuracy. Methods: To investigate this, we chose two relatively common conditions, Williams syndrome and 22q11.2 deletion syndrome. We built a neural network classifier trained on images of affected and unaffected individuals of different ages and compared classifier accuracy to clinical geneticists. We analyzed the results of saliency maps and the use of generative adversarial networks to boost accuracy. Results: Our classifier outperformed clinical geneticists at recognizing face images of these two conditions within each of the age groups (the performance varied between the age groups): 1) under 2 years old, 2) 2-9 years old, 3) 10-19 years old, 4) 20-34 years old, and 5) ≥35 years old. The overall accuracy improvement by our classifier over the clinical geneticists was 15.5 and 22.7% for Williams syndrome and 22q11.2 deletion syndrome, respectively. Additionally, comparison of saliency maps revealed that key facial features learned by the neural network differed with respect to age. Finally, joint training real images with multiple different types of fake images created by a generative adversarial network showed up to 3.25% accuracy gain in classification accuracy. Conclusion: The ability of clinical geneticists to diagnose these conditions is influenced by the age of the patient. Deep learning technologies such as our classifier can more accurately identify patients across the lifespan based on facial features. Saliency maps of computer vision reveal that the syndromic facial feature attributes change with the age of the patient. Modest improvements in the classifier accuracy were observed when joint training was carried out with both real and fake images. Our findings highlight the need for a greater focus on age as a confounder in facial diagnosis.

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.

Prevalence and pregnancy outcomes of gestational diabetes mellitus by different international diagnostic criteria: a prospective cohort study in Vietnam.

Background: Several diagnostic criteria for gestational diabetes mellitus (GDM) have been developed and used internationally. This study estimated the prevalence of GDM and pregnancy outcomes among Vietnamese women.Methods: A prospective cohort study of 2030 women was undertaken in Vietnam between 2015 and 2016. Baseline interview and a single-step 75-g oral glucose tolerance test (OGTT) were conducted at 24-28 weeks of gestation. GDM was defined by five international diagnostic criteria: America Diabetes Association (ADA), European Association for the Study of Diabetes (EASD), International Association of the Diabetes and Pregnancy study groups (IADPSG), National Institute of Health and Clinical Excellence (NICE), and World Health Organization (WHO). Maternal and neonatal outcomes were assessed using medical records. Besides descriptive statistics and univariate analyses, logistic regressions were performed to ascertain the associations between GDM and maternal and neonatal outcomes.Results: The prevalence of GDM varied considerably by the diagnostic criteria: 6.4% (ADA), 7.9% (EASD), 22.8% (IADPSG/WHO), and 24.2% (NICE). Women with GDM according to EASD were more likely to have macrosomic infants (adjusted odds ratio (OR) 4.35, 95% confidence interval [CI]: 1.49-12.72), despite no apparent increase in risk under other criteria. Babies born to mothers with GDM appeared to be large-for-gestational age (LGA) by ADA criteria (adjusted OR 2.10, 95% CI: 1.10-4.02) or EASD criteria (adjusted OR 2.15, 95% CI: 1.16-3.98), when compared to their counterparts in the normal group. No significant differences in maternal and other neonatal outcomes were found between the normal and GDM groups.Conclusions: A global guideline is needed for the diagnosis, prevention and management of GDM.

Prelacteal and early formula feeding increase risk of infant hospitalisation: a prospective cohort study.

OBJECTIVE: To ascertain the relationship between prelacteal feeding, early formula feeding and adverse health outcomes, especially hospitalisation during the first year of life. DESIGN: Multicentre prospective cohort study. SETTING: Six hospitals across three cities in Vietnam. PATIENTS: A total of 2030 pregnant women were recruited at 24-28 weeks of gestation and followed up at hospital discharge, 1, 3, 6 and 12 months post partum. MAIN OUTCOME MEASURES: Rates of infant hospitalisation, diarrhoea and lower respiratory tract infection during the first 12 months. RESULTS: For the final complete sample (n=1709, 84%), about one-quarter of the infants experienced diarrhoea (25.5%) or were admitted to hospital with at least one episode (24.8%), and almost half (47.6%) the cohort contracted lower respiratory tract infection by 12 months. The prevalence of prelacteal feeding was high (56.5%) while formula feeding was common (79.5%) before hospital discharge, both of which increased the risks of adverse health outcomes particularly hospitalisation by approximately 1.5-fold, with adjusted OR (95% CI) 1.43 (1.09 to 1.88) and 1.48 (1.07 to 2.05), respectively for these infants by 12 months, when compared with others who were exclusively breast fed. CONCLUSIONS: Prelacteal feeding and early formula feeding before hospital discharge are associated with higher risks of infection and hospital admission in Vietnamese infants. Support for exclusive breast feeding should be provided to mothers to avoid the adverse consequences of giving formula milk and prelateal foods.

Caesarean delivery associated with adverse breastfeeding practices: a prospective cohort study.

Caesarean delivery rates are increasing in many Asian countries. This study investigated the effects of caesarean section on breastfeeding practices from delivery to twelve months postpartum. A prospective cohort study was conducted on 2030 pregnant women recruited from three cities in Vietnam during 2015-2017. The overall caesarean rate was 38.1%. Mothers who underwent caesarean section were more likely to give prelacteal feeds to their infants (adjusted odds ratio (OR) 13.91, 95% confidence interval (CI) 10.52-18.39) and as a result have lower rates of early initiation of breastfeeding (adjusted OR 0.04, 95%CI 0.02-0.05). Having a caesarean section reduced the likelihood of (any, predominant and exclusive) breastfeeding from discharge to 6 months postpartum. After 1 year, the any breastfeeding rate was still lower in the caesarean delivery (70.2%) compared with the vaginal delivery group (72.9%), p = .232. Vietnamese women who give birth by caesarean section need extra support to initiate and maintain breastfeeding.IMPACT STATEMENTWhat is already known on this subject? Early initiation of breastfeeding, and 'exclusive' or 'predominant' breastfeeding rates at discharge are lower in mothers delivering by caesarean section compared to vaginal delivery. Prelacteal feeding rates are higher following caesarean section. However, the association between 'any' breastfeeding duration and caesarean delivery has not been established.What the results of this study add? This study showed that caesarean delivery reduced all breastfeeding rates from discharge to six months and any breastfeeding rate at 12 months postpartum in Vietnamese women.What the implications are of these findings for clinical practice and/or further research? Further breastfeeding interventions are needed during the postpartum period for mothers who deliver by caesarean section.

Challenges and recommendations to improve the installability and archival stability of omics computational tools.

Developing new software tools for analysis of large-scale biological data is a key component of advancing modern biomedical research. Scientific reproduction of published findings requires running computational tools on data generated by such studies, yet little attention is presently allocated to the installability and archival stability of computational software tools. Scientific journals require data and code sharing, but none currently require authors to guarantee the continuing functionality of newly published tools. We have estimated the archival stability of computational biology software tools by performing an empirical analysis of the internet presence for 36,702 omics software resources published from 2005 to 2017. We found that almost 28% of all resources are currently not accessible through uniform resource locators (URLs) published in the paper they first appeared in. Among the 98 software tools selected for our installability test, 51% were deemed "easy to install," and 28% of the tools failed to be installed at all because of problems in the implementation. Moreover, for papers introducing new software, we found that the number of citations significantly increased when authors provided an easy installation process. We propose for incorporation into journal policy several practical solutions for increasing the widespread installability and archival stability of published bioinformatics software.

Physical Activity During Pregnancy is Associated with Improved Breastfeeding Outcomes: A Prospective Cohort Study.

Physical activity is important for health, but little is known about associations between physical activity during pregnancy and breastfeeding. The aim of this study was to investigate any association between antenatal physical activity and breastfeeding duration. A prospective cohort of 2030 Vietnamese women, recruited between 24 and 28 week-gestation was followed up to twelve months postpartum. Physical activity was determined using the pregnancy physical activity questionnaire at baseline interview. Data was available for 1715 participants at 12 months, a 15.5% attrition rate. At 12 months 71.8% of mothers were still breastfeeding. A total of 20.9% women met physical activity targets and those mothers undertaking higher levels of physical activity had a lower risk of breastfeeding cessation by twelve months [hazard ratios HR = 0.59 (95% CI 0.47-0.74), p < 0.001, and HR = 0.74 (0.60-0.92), p = 0.006; respectively] when compared to the lowest tertile. Similarly, women with increased levels of physical activity have higher rates of breastfeeding at twelve months, compared to the lowest level [odds ratio OR = 1.71 (95% CI 1.29-2.25) and 1.38 (1.06-1.79)]. Higher levels of physical activity by pregnant women are associated with improved breastfeeding outcomes.

Gestational Diabetes and Breastfeeding Outcomes: A Systematic Review.

Studies of gestational diabetes mellitus in relation to breastfeeding are limited, while their findings are inconsistent. This systematic review was conducted to assess the associations between gestational diabetes and breastfeeding outcomes. An initial search of PubMed, Web of Science, and ProQuest identified 518 studies, and after applying the inclusion criteria, 16 studies were finally included in the review. Four studies reported that "exclusive/predominant/full breastfeeding" rates at discharge were lower in mothers with gestational diabetes than in those without gestational diabetes, and 2 studies showed a shorter duration of "exclusive/predominant breastfeeding" in the former than in the latter. However, most studies found no apparent difference in the rate of "breastfeeding initiation", "any breastfeeding" duration, or "any breastfeeding" in hospital and at discharge between mothers with and without gestational diabetes. In summary, mothers with gestational diabetes were less likely to exclusively breastfeed their infants and may have a shorter breastfeeding duration than other mothers.

Fully Automated Segmentation of Alveolar Bone Using Deep Convolutional Neural Networks from Intraoral Ultrasound Images.

Delineation of alveolar bone aids the diagnosis and treatment of periodontal diseases. In current practice, conventional 2D radiography and 3D cone-beam computed tomography (CBCT) imaging are used as the non-invasive approaches to image and delineate alveolar bone structures. Recently, high-frequency ultrasound imaging is proposed as an alternative to conventional imaging methods to prevent the harmful effects of ionizing radiation. However, the manual delineation of alveolar bone from ultrasound imaging is time-consuming and subject to inter and intraobserver variability. This study proposes to use a convolutional neural network-based machine learning framework to automatically segment the alveolar bone from ultrasound images. The proposed method consists of a homomorphic filtering based noise reduction and a u-net machine learning framework for automated delineation. The proposed method was evaluated over 15 ultrasound images of tooth acquired from procine specimens. The comparisons against manual ground truth delineations performed by three experts in terms of mean Dice score and Hausdorff distance values demonstrate that the proposed method yielded an improved performance over a recent state of the art graph cuts based method.

Gestational Diabetes Mellitus Reduces Breastfeeding Duration: A Prospective Cohort Study.

BACKGROUND: Gestational diabetes mellitus (GDM) and its complications are major concerns because of the negative effects of GDM during antenatal period and on the future health of mothers and infants. Breastfeeding is beneficial for GDM mothers and their babies to reduce future health risks. Little is known about the link between GDM and the duration of "any" breastfeeding. Therefore, the aim of this study was to investigate the relationship between GDM and the duration for which Vietnamese women breastfeed their babies postpartum. MATERIALS AND METHODS: A prospective cohort of 2,030 pregnant women between 24 and 28 weeks of gestation was recruited. GDM status was determined using a 75 g oral glucose tolerance test. Included mothers were then followed up from discharge after childbirth until 12 months postpartum to determine their breastfeeding duration. Kaplan-Meier estimates, log-rank tests, logistic and Cox regression models were used to examine the association between GDM and breastfeeding outcomes. RESULTS: In our cohort, 94.4% of all women reported "any" breastfeeding at discharge and 72.9% of women were still breastfeeding at 12 months postpartum. The risk of early breastfeeding cessation was higher in GDM women than their non-GDM counterparts after adjustment for demographic factors (hazard ratios [HR] = 1.39, 95% confidence intervals [CI] = 1.13-1.71, p = 0.002), and all potential confounding factors (HR = 1.38, 95% CI = 1.12-1.70, p = 0.002). There were no significant differences in breastfeeding outcomes at discharge (early initiation, prelacteal feeding, and "any" breastfeeding rate) between GDM and non-GDM mothers. CONCLUSIONS: GDM was associated with shorter breastfeeding duration. Women with GDM require ongoing support after hospital discharge to maintain long-term breastfeeding.