The global "myopia boom" has raised significant international concerns. Despite a higher myopia prevalence in Asia, previous large-scale genome-wide association studies(GWASs) were mostly based on European d...The global "myopia boom" has raised significant international concerns. Despite a higher myopia prevalence in Asia, previous large-scale genome-wide association studies(GWASs) were mostly based on European descendants. Here, we report a GWAS of spherical equivalent(SE) in 1852 Chinese Han individuals with extreme SE from Guangzhou(631 <-6.00 D and 574 > 0.00 D) and Wenzhou(593 <-6.00 D and54 >-1.75 D), followed by a replication study in two independent cohorts with totaling 3538 East Asian individuals. The discovery GWAS and meta-analysis identify three novel loci, which show genome-wide significant associations with SE, including 1 q25.2 FAM163 A, 10 p11.22 NRP1/PRAD3, and 10 p11.21 ANKRD30 A/MTRNR2 L7, together explaining 3.34% of SE variance. 10 p11.21 is successfully replicated.The allele frequencies of all three loci show significant differences between major continental groups(P < 0.001). The SE reducing(more myopic) allele of rs10913877(1 q25.2 FAM163 A) demonstrates the highest frequency in East Asians and much lower frequencies in Europeans and Africans(EAS = 0.60,EUR = 0.20, and AFR = 0.18). The gene-based analysis additionally identifies three novel genes associated with SE, including EI24, LHX5, and ARPP19. These results provide new insights into myopia pathogenesis and indicate the role of genetic heterogeneity in myopia epidemiology among different ethnicities.展开更多
Diabetes poses a considerable global health challenge,with varying levels of diabetes knowledge among healthcare professionals,highlighting the importance of diabetes training.Large Language Models(LLMs)provide new in...Diabetes poses a considerable global health challenge,with varying levels of diabetes knowledge among healthcare professionals,highlighting the importance of diabetes training.Large Language Models(LLMs)provide new insights into diabetes training,but their performance in diabetes-related queries remains uncertain,especially outside the English language like Chinese.We first evaluated the performance of ten LLMs:ChatGPT-3.5,ChatGPT-4.0,Google Bard,LlaMA-7B,LlaMA2-7B,Baidu ERNIE Bot,Ali Tongyi Qianwen,MedGPT,HuatuoGPT,and Chinese LlaMA2-7B on diabetes-related queries,based on the Chinese National Certificate Examination for Primary Diabetes Care in China(NCE-CPDC)and the English Specialty Certificate Examination in Endocrinology and Diabetes of Membership of the Royal College of Physicians of the United Kingdom.Second,we assessed the training of primary care physicians(PCPs)without and with the assistance of ChatGPT-4.0 in the NCE-CPDC examination to ascertain the reliability of LLMs as medical assistants.We found that ChatGPT-4.0 outperformed other LLMs in the English examination,achieving a passing accuracy of 62.50%,which was significantly higher than that of Google Bard,LlaMA-7B,and LlaMA2-7B.For the NCE-CPFC examination,ChatGPT-4.0,Ali Tongyi Qianwen,Baidu ERNIE Bot,Google Bard,MedGPT,and ChatGPT-3.5 successfully passed,whereas LlaMA2-7B,HuatuoGPT,Chinese LLaMA2-7B,and LlaMA-7B failed.ChatGPT-4.0(84.82%)surpassed all PCPs and assisted most PCPs in the NCE-CPDC examination(improving by 1%–6.13%).In summary,LLMs demonstrated outstanding competence for diabetes-related questions in both the Chinese and English language,and hold great potential to assist future diabetes training for physicians globally.展开更多
ackground:Uncorrected refractive error is a major cause of vision impairment worldwide and its increasing prevalent necessitates effective screening and management strategies.Meanwhile,deep learning,a subset of Artifi...ackground:Uncorrected refractive error is a major cause of vision impairment worldwide and its increasing prevalent necessitates effective screening and management strategies.Meanwhile,deep learning,a subset of Artificial Intelligence,has significantly advanced ophthalmological diagnostics by automating tasks that required extensive clinical expertise.Although recent studies have investigated the use of deep learning models for refractive power detection through various imaging techniques,a comprehensive systematic review on this topic is has yet be done.This review aims to summarise and evaluate the performance of ocular image-based deep learning models in predicting refractive errors.Main text:We search on three databases(PubMed,Scopus,Web of Science)up till June 2023,focusing on deep learning applications in detecting refractive error from ocular images.We included studies that had reported refractive error outcomes,regardless of publication years.We systematically extracted and evaluated the continuous outcomes(sphere,SE,cylinder)and categorical outcomes(myopia),ground truth measurements,ocular imaging modalities,deep learning models,and performance metrics,adhering to PRISMA guidelines.Nine studies were identified and categorised into three groups:retinal photo-based(n=5),OCT-based(n=1),and external ocular photo-based(n=3).For high myopia prediction,retinal photo-based models achieved AUC between 0.91 and 0.98,sensitivity levels between 85.10%and 97.80%,and specificity levels between 76.40%and 94.50%.For continuous prediction,retinal photo-based models reported MAE ranging from 0.31D to 2.19D,and R^(2) between 0.05 and 0.96.The OCT-based model achieved an AUC of 0.79–0.81,sensitivity of 82.30%and 87.20%and specificity of 61.70%–68.90%.For external ocular photo-based models,the AUC ranged from 0.91 to 0.99,sensitivity of 81.13%–84.00%and specificity of 74.00%–86.42%,MAE ranges from 0.07D to 0.18D and accuracy ranges from 81.60%to 96.70%.The reported papers collectively showed promising performances,in particular the retinal photo-based and external eye photo-based DL models.Conclusions:The integration of deep learning model and ocular imaging for refractive error detection appear promising.However,their real-world clinical utility in current screening workflow have yet been evaluated and would require thoughtful consideration in design and implementation.展开更多
基金supported by the Strategic Priority Research Program of Chinese Academy of Sciences (XDB38010400)National Key R&D Program of China (2018YFC0116500)+4 种基金Science and Technology Service Network Initiative of Chinese Academy of Sciences (KFJSTS-ZDTP-079)Science and Technology Planning Project of Guangdong Province (2013B20400003)the Fundamental Research Funds of the State Key Laboratory of Ophthalmologythe Open Project of Key Laboratory of Genomic and Precision Medicine of the CASsupported by the China Scholarship Council (CSC) and China Postdoctoral Science Foundation (2019TQ0365)。
文摘The global "myopia boom" has raised significant international concerns. Despite a higher myopia prevalence in Asia, previous large-scale genome-wide association studies(GWASs) were mostly based on European descendants. Here, we report a GWAS of spherical equivalent(SE) in 1852 Chinese Han individuals with extreme SE from Guangzhou(631 <-6.00 D and 574 > 0.00 D) and Wenzhou(593 <-6.00 D and54 >-1.75 D), followed by a replication study in two independent cohorts with totaling 3538 East Asian individuals. The discovery GWAS and meta-analysis identify three novel loci, which show genome-wide significant associations with SE, including 1 q25.2 FAM163 A, 10 p11.22 NRP1/PRAD3, and 10 p11.21 ANKRD30 A/MTRNR2 L7, together explaining 3.34% of SE variance. 10 p11.21 is successfully replicated.The allele frequencies of all three loci show significant differences between major continental groups(P < 0.001). The SE reducing(more myopic) allele of rs10913877(1 q25.2 FAM163 A) demonstrates the highest frequency in East Asians and much lower frequencies in Europeans and Africans(EAS = 0.60,EUR = 0.20, and AFR = 0.18). The gene-based analysis additionally identifies three novel genes associated with SE, including EI24, LHX5, and ARPP19. These results provide new insights into myopia pathogenesis and indicate the role of genetic heterogeneity in myopia epidemiology among different ethnicities.
基金supported by the Noncommunicable Chronic Diseases-National Science and Technology Major Project(2023ZD0509202 and 2023ZD0509201)National Natural Science Foundation of China(62077037,8238810007,82022012,81870598,62272298 and 82388101)+4 种基金the National Key Research and Development Program of China(2022YFC2502800 and 2022YFC2407000)the Shanghai Municipal Key Clinical Specialty,Shanghai Research Center for Endocrine and Metabolic Diseases(2022ZZ01002)the Chinese Academy of Engineering(2022-XY-08)the Innovative Research Team of High-level Local Universities in Shanghai(SHSMUZDCX20212700)Beijing Natural Science Foundation(IS23096).
文摘Diabetes poses a considerable global health challenge,with varying levels of diabetes knowledge among healthcare professionals,highlighting the importance of diabetes training.Large Language Models(LLMs)provide new insights into diabetes training,but their performance in diabetes-related queries remains uncertain,especially outside the English language like Chinese.We first evaluated the performance of ten LLMs:ChatGPT-3.5,ChatGPT-4.0,Google Bard,LlaMA-7B,LlaMA2-7B,Baidu ERNIE Bot,Ali Tongyi Qianwen,MedGPT,HuatuoGPT,and Chinese LlaMA2-7B on diabetes-related queries,based on the Chinese National Certificate Examination for Primary Diabetes Care in China(NCE-CPDC)and the English Specialty Certificate Examination in Endocrinology and Diabetes of Membership of the Royal College of Physicians of the United Kingdom.Second,we assessed the training of primary care physicians(PCPs)without and with the assistance of ChatGPT-4.0 in the NCE-CPDC examination to ascertain the reliability of LLMs as medical assistants.We found that ChatGPT-4.0 outperformed other LLMs in the English examination,achieving a passing accuracy of 62.50%,which was significantly higher than that of Google Bard,LlaMA-7B,and LlaMA2-7B.For the NCE-CPFC examination,ChatGPT-4.0,Ali Tongyi Qianwen,Baidu ERNIE Bot,Google Bard,MedGPT,and ChatGPT-3.5 successfully passed,whereas LlaMA2-7B,HuatuoGPT,Chinese LLaMA2-7B,and LlaMA-7B failed.ChatGPT-4.0(84.82%)surpassed all PCPs and assisted most PCPs in the NCE-CPDC examination(improving by 1%–6.13%).In summary,LLMs demonstrated outstanding competence for diabetes-related questions in both the Chinese and English language,and hold great potential to assist future diabetes training for physicians globally.
文摘ackground:Uncorrected refractive error is a major cause of vision impairment worldwide and its increasing prevalent necessitates effective screening and management strategies.Meanwhile,deep learning,a subset of Artificial Intelligence,has significantly advanced ophthalmological diagnostics by automating tasks that required extensive clinical expertise.Although recent studies have investigated the use of deep learning models for refractive power detection through various imaging techniques,a comprehensive systematic review on this topic is has yet be done.This review aims to summarise and evaluate the performance of ocular image-based deep learning models in predicting refractive errors.Main text:We search on three databases(PubMed,Scopus,Web of Science)up till June 2023,focusing on deep learning applications in detecting refractive error from ocular images.We included studies that had reported refractive error outcomes,regardless of publication years.We systematically extracted and evaluated the continuous outcomes(sphere,SE,cylinder)and categorical outcomes(myopia),ground truth measurements,ocular imaging modalities,deep learning models,and performance metrics,adhering to PRISMA guidelines.Nine studies were identified and categorised into three groups:retinal photo-based(n=5),OCT-based(n=1),and external ocular photo-based(n=3).For high myopia prediction,retinal photo-based models achieved AUC between 0.91 and 0.98,sensitivity levels between 85.10%and 97.80%,and specificity levels between 76.40%and 94.50%.For continuous prediction,retinal photo-based models reported MAE ranging from 0.31D to 2.19D,and R^(2) between 0.05 and 0.96.The OCT-based model achieved an AUC of 0.79–0.81,sensitivity of 82.30%and 87.20%and specificity of 61.70%–68.90%.For external ocular photo-based models,the AUC ranged from 0.91 to 0.99,sensitivity of 81.13%–84.00%and specificity of 74.00%–86.42%,MAE ranges from 0.07D to 0.18D and accuracy ranges from 81.60%to 96.70%.The reported papers collectively showed promising performances,in particular the retinal photo-based and external eye photo-based DL models.Conclusions:The integration of deep learning model and ocular imaging for refractive error detection appear promising.However,their real-world clinical utility in current screening workflow have yet been evaluated and would require thoughtful consideration in design and implementation.
