Artificial Intelligence for Early Detection of Pediatric Eye Diseases Using Mobile Photos.

IMPORTANCE: Identifying pediatric eye diseases at an early stage is a worldwide issue. Traditional screening procedures depend on hospitals and ophthalmologists, which are expensive and time-consuming. Using artificial intelligence (AI) to assess children's eye conditions from mobile photographs could facilitate convenient and early identification of eye disorders in a home setting. OBJECTIVE: To develop an AI model to identify myopia, strabismus, and ptosis using mobile photographs. DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional study was conducted at the Department of Ophthalmology of Shanghai Ninth People's Hospital from October 1, 2022, to September 30, 2023, and included children who were diagnosed with myopia, strabismus, or ptosis. MAIN OUTCOMES AND MEASURES: A deep learning-based model was developed to identify myopia, strabismus, and ptosis. The performance of the model was assessed using sensitivity, specificity, accuracy, the area under the curve (AUC), positive predictive values (PPV), negative predictive values (NPV), positive likelihood ratios (P-LR), negative likelihood ratios (N-LR), and the F1-score. GradCAM++ was utilized to visually and analytically assess the impact of each region on the model. A sex subgroup analysis and an age subgroup analysis were performed to validate the model's generalizability. RESULTS: A total of 1419 images obtained from 476 patients (225 female [47.27%]; 299 [62.82%] aged between 6 and 12 years) were used to build the model. Among them, 946 monocular images were used to identify myopia and ptosis, and 473 binocular images were used to identify strabismus. The model demonstrated good sensitivity in detecting myopia (0.84 [95% CI, 0.82-0.87]), strabismus (0.73 [95% CI, 0.70-0.77]), and ptosis (0.85 [95% CI, 0.82-0.87]). The model showed comparable performance in identifying eye disorders in both female and male children during sex subgroup analysis. There were differences in identifying eye disorders among different age subgroups. CONCLUSIONS AND RELEVANCE: In this cross-sectional study, the AI model demonstrated strong performance in accurately identifying myopia, strabismus, and ptosis using only smartphone images. These results suggest that such a model could facilitate the early detection of pediatric eye diseases in a convenient manner at home.

Influencing factors for pediatric eye disorders and health related quality of life: a cross-sectional study in Shanghai, China.

Background: Myopia, strabismus, and ptosis are common pediatric eye diseases, which have a negative impact on children and adolescents in terms of visual function, mental health, and health-related quality of life (HRQoL). Therefore, this study focused on those pediatric eye diseases by analyzing their risk factors and HRQoL for the comprehensive management of myopia, strabismus, and ptosis. Methods: A total of 363 participants (2-18 years old) were included in this study for risk factors analysis of myopia, strabismus, and ptosis. We collected demographic characteristics, lifestyle habits and eye care habits of these children and analyzed them by using univariable and multivariable logistic regression. In addition, we applied the Chinese version of Pediatric Quality of Life Inventory-Version 4.0 (PedsQL 4.0) to assess HRQoL in 256 children with strabismus and ptosis. Univariable and multivariable linear regression models were applied to evaluate potential influencing factors of HRQoL. Results: Of all the participants, 140 had myopia, 127 had strabismus, and 145 had ptosis. Based on the multivariable logistic regression analysis model, we found that the history of parental myopia and daily average near-distance eye usage time were risk factors for myopia, and increased body mass index (BMI) was identified as a risk factor for strabismus and ptosis. Individuals with ptosis possessed decreased HRQoL. The multivariable linear regression model suggested that daily average near-distance eye usage time, light intensity during visual tasks, and daily average sleep duration had potential influences on HRQoL. Conclusion: This is the first study to assess the risk factors and HRQoL of myopia, strabismus, and ptosis together. We identified risk factors for these common pediatric eye diseases to help doctors, parents, and teachers better manage them. Our study discovered that children with eye disorders exhibit a notably diminished HRQoL. Consequently, it emphasizes the necessity for increased social attention and mental health assistance for these children.

Targeting AQP9 enhanced the anti-TNF therapy response in Crohn's disease by inhibiting LPA-hippo pathway.

Although anti-TNF antibodies are extensively used to treat Crohn's disease (CD), a significant proportion of patients, up to 40%, exhibit an inadequate response to this therapy. Our objective was to identify potential targets that could improve the effectiveness of anti-TNF therapy in CD. Through the integration and analysis of transcriptomic data from various CD databases, we found that the expression of AQP9 was significantly increased in anti-TNF therapy-resistant specimens. The response to anti-TNF therapy in the CD mouse model was significantly enhanced by specifically inhibiting AQP9. Further experiments found that the blockade of AQP9, which is dominantly expressed in macrophages, decreased inflamed macrophage functions and cytokine expression. Mechanistic studies revealed that AQP9 transported glycerol into macrophages, where it was metabolized to LPA, which was further metabolized to LPA, resulting in the activation of the LPAR2 receptor and downstream hippo pathway, finally promoting the expression of cytokines, especially IL23 and IL1ß⊡ Taken together, the expansion of AQP9+ macrophages is associated with resistance to anti-TNF therapy in Crohn's disease. These findings indicated that AQP9 could be a potential target for enhancing anti-TNF therapy in Crohn's disease.