Objective: To investigate the lifestyle and myopia among primary school students in urban areas of Fujian with the context of myopia prevention and control measures, aiming to provide scientific evidence for identifying high-risk myopia population and formulating effective intervention strategies. 

Methods: A cross-sectional study was conducted from October to November 2023, enrolling 811 fourth-grade students from three primary schools in three cities across Fujian. Personal information and lifestyle-related pattern were collected using customized questionnaire. Participants underwent comprehensive ophthalmic assessments including distance visual acuity tests and refractive examinations. Logistic regression analysis was used to assess the impact of lifestyle on the onset of myopia.

Results: The prevalence of myopia among fourth-grade students in urban primary schools in Fujian was 46.4%. Only 25.8% students engaged in outdoor activities for more than 2 hours daily, while63.3% participated in outdoor activities during class breaks. Multivariate Logistic regression analysis revealed that outdoor activities during class breaks (OR= 0.646 [95% confidence interval(CI): 0.473-0.881], P = 0.006) and daily time spent outdoors (2-3 hours, OR=0.682 [95%CI：0.466-0.993], P=0.047; more than 3 hours, OR=0.403 [95%CI: 0.192-0.796], P = 0.01) were independent protective factors against myopia. Lifestyle significantly enhanced the predictive performance for myopia (P = 0.01). Additionally, parental myopia (one parent with myopia, OR=2.247 [95%CI: 1.612- 3.145], P < 0.001; both parents with myopia, OR=4.824 [95%CI: 3.262-7.204], P < 0.001) emerged as a key risk factor for myopia.

Conclusion: There is considerable scope for improving the lifestyle of primary school students in urban areas of Fujian. Lifestyle is strongly associated with myopia onset, highlighting the need for schools and families to actively encourage students to engage in more outdoor activities and take breaks outdoors to prevent and control myopia. Students with parents, especially both parents, having myopia should be considered as a key target group for myopia prevention efforts.

Objective: To investigate the lifestyle and myopia among primary school students in urban areas of Fujian with the context of myopia prevention and control measures, aiming to provide scientific evidence for identifying high-risk myopia population and formulating effective intervention strategies. 

Methods: A cross-sectional study was conducted from October to November 2023, enrolling 811 fourth-grade students from three primary schools in three cities across Fujian. Personal information and lifestyle-related pattern were collected using customized questionnaire. Participants underwent comprehensive ophthalmic assessments including distance visual acuity tests and refractive examinations. Logistic regression analysis was used to assess the impact of lifestyle on the onset of myopia.

Results: The prevalence of myopia among fourth-grade students in urban primary schools in Fujian was 46.4%. Only 25.8% students engaged in outdoor activities for more than 2 hours daily, while63.3% participated in outdoor activities during class breaks. Multivariate Logistic regression analysis revealed that outdoor activities during class breaks (OR= 0.646 [95% confidence interval(CI): 0.473-0.881], P = 0.006) and daily time spent outdoors (2-3 hours, OR=0.682 [95%CI：0.466-0.993], P=0.047; more than 3 hours, OR=0.403 [95%CI: 0.192-0.796], P = 0.01) were independent protective factors against myopia. Lifestyle significantly enhanced the predictive performance for myopia (P = 0.01). Additionally, parental myopia (one parent with myopia, OR=2.247 [95%CI: 1.612- 3.145], P < 0.001; both parents with myopia, OR=4.824 [95%CI: 3.262-7.204], P < 0.001) emerged as a key risk factor for myopia.

Conclusion: There is considerable scope for improving the lifestyle of primary school students in urban areas of Fujian. Lifestyle is strongly associated with myopia onset, highlighting the need for schools and families to actively encourage students to engage in more outdoor activities and take breaks outdoors to prevent and control myopia. Students with parents, especially both parents, having myopia should be considered as a key target group for myopia prevention efforts.

Background: Research innovations inoculardisease screening, diagnosis, and management have been boosted by deep learning (DL) in the last decade. To assess historical research trends and current advances, we conducted an artifcial intelligence (AI)–human hybrid analysis of publications on DL in ophthalmology.

Methods: All DL-related articles in ophthalmology, which were published between 2012 and 2022 from Web of Science, were included. 500 high-impact articles annotated with key research information were used to fne-tune alarge language models (LLM) for reviewing medical literature and extracting information. After verifying the LLM's accuracy in extracting diseases and imaging modalities, we analyzed trend of DL in ophthalmology with 2 535 articles. 

Results: Researchers using LLM for literature analysis were 70% (p= 0.000 1) faster than those who did not, while achieving comparable accuracy (97% versus 98%, p = 0.768 1). The field of DL in ophthalmology has grown 116% annually, paralleling trends of the broader DL domain. The publications focused mainly on diabetic retinopathy (p = 0.000 3), glaucoma (p = 0.001 1), and age-related macular diseases (p = 0.000 1) using retinal fundus photographs (FP, p = 0.001 5) and optical coherence tomography (OCT, p = 0.000 1). DL studies utilizing multimodal images have been growing, with FP and OCT combined being the most frequent. Among the 500 high-impact articles, laboratory studies constituted the majority at 65.3%. Notably, a discernible decline in model accuracy was observed when categorizing by study design, notwithstanding its statistical insignificance. Furthermore, 43 publicly available ocular image datasets were summarized. 

Conclusion: This study has characterized the landscape of publications on DL in ophthalmology, by identifying the trends and breakthroughs among research topics and the fast-growing areas. This study provides an efcient framework for combined AI–human analysis to comprehensively assess the current status and future trends in the feld. 

Background: Research innovations inoculardisease screening, diagnosis, and management have been boosted by deep learning (DL) in the last decade. To assess historical research trends and current advances, we conducted an artifcial intelligence (AI)–human hybrid analysis of publications on DL in ophthalmology.

Methods: All DL-related articles in ophthalmology, which were published between 2012 and 2022 from Web of Science, were included. 500 high-impact articles annotated with key research information were used to fne-tune alarge language models (LLM) for reviewing medical literature and extracting information. After verifying the LLM's accuracy in extracting diseases and imaging modalities, we analyzed trend of DL in ophthalmology with 2 535 articles. 

Results: Researchers using LLM for literature analysis were 70% (p = 0.000 1) faster than those who did not, while achieving comparable accuracy (97% versus 98%, p = 0.768 1). The field of DL in ophthalmology has grown 116% annually, paralleling trends of the broader DL domain. The publications focused mainly on diabetic retinopathy (p = 0.000 3), glaucoma (p = 0.001 1), and age-related macular diseases (p = 0.000 1) using retinal fundus photographs (FP, p = 0.001 5) and optical coherence tomography (OCT, p = 0.000 1). DL studies utilizing multimodal images have been growing, with FP and OCT combined being the most frequent. Among the 500 high-impact articles, laboratory studies constituted the majority at 65.3%. Notably, a discernible decline in model accuracy was observed when categorizing by study design, notwithstanding its statistical insignificance. Furthermore, 43 publicly available ocular image datasets were summarized. 

Conclusion: This study has characterized the landscape of publications on DL in ophthalmology, by identifying the trends and breakthroughs among research topics and the fast-growing areas. This study provides an efcient framework for combined AI–human analysis to comprehensively assess the current status and future trends in the feld.