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.

Disorders of histone methylation: Molecular basis and clinical syndromes.

Epigenetic modifications of DNA and histone tails are essential for gene expression regulation. They play an essential role in neurodevelopment as nervous system development is a complex process requiring a dynamic pattern of gene expression. Histone methylation is one of the vital epigenetic regulators and mostly occurs on lysine residues of histones H3 and H4. Histone methylation is catalyzed by two sets of enzymes: histone lysine methyltransferases (KMTs) and histone lysine demethylases (KDMs). KMT2 enzymes form a distinct multi-subunit complex known as COMPASS to enhance their catalytic activity and diversify their biologic functions. Several neurodevelopmental syndromes result from defects in histone methylation which can be caused by deficiencies in histone methyltransferases and demethylases, loss of the histone methyltransferase activator TASP1, or derangements in COMPASS formation. In this review article, the molecular mechanism of histone methylation is discussed followed by summarizing clinical syndromes caused by monogenic defects in histone methylation.

Expanding on the phenotypic spectrum of Woodhouse-Sakati syndrome due to founder pathogenic variant in DCAF17: Report of 58 additional patients from Qatar and literature review.

Woodhouse-Sakati syndrome (WSS) is a rare autosomal recessive neuroendocrine and ectodermal disorder caused by variants in the DCAF17 gene. In Qatar, the c.436delC variant has been reported as a possible founder pathogenic variant with striking phenotypic heterogeneity. In this retrospective study, we report on the clinical and molecular characteristics of additional 58 additional Qatari patients with WSS and compare them to international counterparts' findings. A total of 58 patients with WSS from 32 consanguineous families were identified. Ectodermal and endocrine (primary hypogonadism) manifestations were the most common presentations (100%), followed by diabetes mellitus (46%) and hypothyroidism (36%). Neurological manifestations were overlapping among patients with intellectual disability (ID) being the most common (75%), followed by sensorineural hearing loss (43%) and both ID and aggressive behavior (10%). Distinctive facial features were noted in all patients and extrapyramidal manifestations were uncommon (8.6%). This study is the largest to date on Qatari patients with WSS and highlights the high incidence and clinical heterogeneity of WSS in Qatar due to a founder variant c.436delC in the DCAF17 gene. Early suspicion of WSS among Qatari patients with hypogonadism and ID, even in the absence of other manifestations, would shorten the diagnostic odyssey, guide early and appropriate management, and avoid potential complications.

Gene therapy for spinal muscular atrophy: the Qatari experience.

Spinal muscular atrophy (SMA) is an autosomal recessive neuromuscular disorder characterized by hypotonia, progressive muscle weakness, and wasting. Onasemnogene abeparvovec (Zolgensma®) is a novel gene therapy medicine, FDA-approved in May 2019 for the treatment of SMA. This study aimed to describe Qatari experience with onasemnogene abeparvovec by reviewing the clinical outcomes of 9 SMA children (7 SMA type 1 and 2 with SMA type 2) aged 4‒23 months treated between November 2019 and July 2020. Children <2 years with 5q SMA with a bi-allelic mutation in the SMN1 gene were eligible for gene therapy. Liver function (aspartate aminotransferase [AST], alanine aminotransferase [ALT], and total bilirubin), platelet count, coagulation profile, troponin-I levels, and motor scores (Children's Hospital of Philadelphia Infant Test of Neuromuscular Disorders [CHOP INTEND]), were regularly monitored following gene therapy. All patients experienced elevated AST or ALT, two experienced high prothrombin time, and one experienced elevated bilirubin; all of these patients were asymptomatic. Furthermore, one event of vomiting after infusion was reported in one patient. Significant improvements in CHOP INTEND scores were observed following therapy. This study describes the short-term outcomes and safety of onasemnogene abeparvovec, which is well tolerated and shows promise for early efficacy.

A founder RAB27A variant causes Griscelli syndrome type 2 with phenotypic heterogeneity in Qatari families.

Griscelli syndrome type 2 (GS2) is a rare autosomal recessive disorder caused by pathogenic variants in the RAB27A gene and characterized by partial albinism, immunodeficiency, and occasional hematological and neurological involvement. We reviewed and analyzed the medical records of 12 individuals with GS2 from six families belonging to a highly consanguineous Qatari tribe and with a recurrent pathogenic variant in the RAB27A gene (NM_004580.4: c.244C > T, p.Arg82Cys). Detailed demographic, clinical, and molecular data were collected. Cutaneous manifestations were the most common presentation (42%), followed by neurological abnormalities (33%) and immunodeficiency (25%). The most severe manifestation was HLH (33%). Among the 12 patients, three patients (25%) underwent HSCT, and four (33%) died. The cause of death in all four patients was deemed HLH, providing evidence for this complication's fatal nature. Interestingly, two affected patients (16%) were asymptomatic. This report highlights the broad spectrum of clinical presentations of GS2 associated with a founder variant in the RAB27A gene (c.244C > T, p.Arg82Cys). Early suspicion of GS2 among Qatari patients with cutaneous manifestations, neurological findings, immunodeficiency, and HLH would shorten the diagnostic odyssey, guide early and appropriate treatment, and prevent fatal outcomes.

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.

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.

Behavioral, psychological, and clinical outcomes of Arabic-speaking people with type 2 diabetes during COVID-19 pandemic.

AIMS: Assess self-care activities, health behaviors, self-efficacy, diabetes distress, challenges, and changes in diabetes treatment and clinical parameters among Arabic-speaking people with T2DM during the COVID-19 pandemic. METHODS: A cross-sectional study was conducted at a tertiary hospital in the United Arab Emirates. The study instrument collected self-reported data using validated tools about health behaviors, self-efficacy, and diabetes distress, and challenges in accessing and using healthcare services during the pandemic and documented clinical data and treatment before and during the pandemic from medical records. RESULTS: 206 patients participated with a mean age of 58.7 years and 15.7 years since diabetes diagnosis. Non-adherence to healthful eating and exercise was reported by 38.3% and 73.7%, respectively. Exercise was the self-care activity that decreased the most (36.8%). Most participants had low diabetes distress (85.9%). There were no significant differences in clinical parameters before and during the pandemic, and diabetes treatment was unchanged for 72.8% of participants. Having two or more challenges with accessing and using diabetes healthcare services was significantly associated with decreased adherence to healthy eating (p = 0.025) and exercise (p = 0.003). CONCLUSIONS: Arabic-speaking people with T2DM appeared to maintain relatively similar self-care levels, except exercise, with no deterioration in clinical parameters compared to pre-pandemic.

A global assessment of distance pharmacy education amid COVID-19: teaching, assessment and experiential training.

OBJECTIVES: To explore pharmacy colleges' experiences and challenges worldwide with the transition to online teaching during the coronavirus disease 2019 (COVID-19) pandemic. METHODS: From the six World Health Organization regions, 28 countries with the highest number of COVID-19 cases were identified, and 111 pharmacy colleges were randomly selected from these countries. Two online surveys were sent to faculty members and senior administrators. They assessed changes in teaching and learning, experiential training, assessment, readiness for and challenges with distance e-learning and work-related stress. KEY FINDINGS: Data were collected from 46 colleges. The majority (80.4%) of colleges transitioned to distance e-learning. On-site experiential training was discontinued in 55.5% of colleges and 25.0% redesigned on-site training into remote learning experiences. Assessments were modified in 75.9% of colleges. Assuring the integrity of assessments and delivering practical classes were the most prominent faculty challenges. The majority of faculty (75.0%) and administrators (61.9%) reported moderate work-related stress. Nevertheless, most academics felt that they received adequate support from their institutions and had positive perceptions of the transition to distance e-learning during the pandemic. CONCLUSIONS: The COVID-19 pandemic required drastic changes for most programs' teaching methods. Our results showed that educational institutions were somewhat able to support faculty and the needs of educational programs were largely met. However, academic rigour and provision of experiential training can be improved. Faculty emotional support and training needs were not fully addressed in these difficult times. These results shed light on how the global pharmacy academy has addressed the COVID-19 pandemic and help rethink crisis response models.

Prevalence Of Self-Medication With Antibiotics Among Residents In United Arab Emirates.

BACKGROUND: Self-Medication with antibiotics is a human practice and attitude in which an individual uses antibiotics to treat self-diagnosed symptoms. The self-medication with antibiotics is a common practice among residents in the UAE. PURPOSE: The present study aimed to determine the prevalence of self-medication of antibiotics among residents in the UAE population to determine its associated risk factors and to increase awareness regarding the abuse of antibiotics. PATIENTS AND METHODS: Three hundred and fifteen participants from different public places in Abu Dhabi, Dubai and Sharjah,UAE received the validated questionnaire over the five-month study period. Collected data were analyzed using SPSS statistical software and the Chi-square test to assess the relationships between categorical variables. RESULTS: Of 315 participants, 31.7% (n=100) of the respondents reported the use of non-prescription antibiotics within a three-month study period. Self-medication with antibiotics was significantly associated with ethnicity and employment. The participants reported their previous experience with the disease (69; 21.9%), as the main reason for self-medication with antibiotics. The primary sources of antibiotics were those purchased from community pharmacies (70; 22.2%) and household (21; 6.7%). CONCLUSION: Our study showed a high prevalence of self-medication behaviour even with the enforcement of the new legislation regarding the prohibition of selling antibiotics without a prescription. Therefore, there is a need to raise public awareness towards the safe use of antibiotics in our community.

Consumer medication information: legislative gap and challenges of practice

Objectives: To assess and evaluate OTC package inserts in terms of availability of key medical information and patient understanding of such information, as well as package insert user satisfaction and perceptions. Methods: This study used two quantitative methods: Evaluation of the Over-the-Counter Package Inserts and assessing package inserts user’s satisfaction and perspectives using a cross-sectional survey. Descriptive analysis was used to calculate the response proportion of each group of respondents. Results: A total of 60 package inserts of Over-the-Counter drugs were evaluated. Less than onethird (30%) of the medication under investigation was found to have information about the unit of measurement of the active ingredient. Less than half (44.5%) of respondents reported they usually use the package inserts for information about their medication, and 42.2% rarely use or read package inserts. Difficulty reading or finding information in the package inserts was reported by 37.3 % of respondents. Conclusion: This research identified several factors associated with the proper use of package inserts among the general population in the United Arab Emirates and potential opportunities. Also, due to the lack of binding legislative texts, consumers are dissatisfied with the packaging inserts regarding their appearance and content. A mandatory guideline should be enacted by the competent authorities to ensure the comprehensiveness and readability of pharmacological information. (AU)