Autoimmune uveitis is one of the most common inflammatory eye diseases leading to blindness globally.Its etiology is primarily associated with autoimmune responses.Patients with this condition often exhibit complex an...Autoimmune uveitis is one of the most common inflammatory eye diseases leading to blindness globally.Its etiology is primarily associated with autoimmune responses.Patients with this condition often exhibit complex and chronic disease courses,with a high propensity for recurrence.Current treatments mainly involve corticosteroids and immunosuppressive agents,which,despite their effectiveness,entail significant side effects that severely impact patients'vision and quality of life.There are still unresolved questions regarding the etiology and immunopathogenesis of autoimmune uveitis,and traditional high-throughput sequencing techniques fall short of adequately elucidating its pathogenic mechanisms at the cellular level.With the continuous advancement of single-cell sequencing technology,an increasing number of studies are leveraging this approach to deeply investigate the pathogenesis of autoimmune uveitis,thereby offering new insights for identifying novel diagnostic and therapeutic targets.This paper reviews the latest applications of single-cell sequencing technology in exploring the pathogenesis of autoimmune uveitis.Through the utilization of this technology,researchers can gain a more comprehensive understanding of cellular-level changes in patients,providing robust support for the search for new therapeutic avenues.These studies offer new directions for the diagnosis and treatment of autoimmune uveitis and provide valuable information for the development of future therapeutic strategies and approaches.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
Dear Editor,While trends in scientific collaborations between the US and China have now been described in a general context1,2-revealing a significant decline in productivity compared to other international partnershi...Dear Editor,While trends in scientific collaborations between the US and China have now been described in a general context1,2-revealing a significant decline in productivity compared to other international partnerships-such trends have yet to be specifically evaluated for the field of ophthalmology,where there is an ever-important emphasis on multinational partnerships for the delivery of state-of-the-art,rigorous,and equitable eye care.1,3,4,5 In this study,we explore collaborations between researchers in the US and China in ophthalmology-related literature from 2000 to 2021.展开更多
Age-associated changes in immune cells have been linked to an increased risk for infection.However,a global and detailed characterization of the changes that human circulating immune cells undergo with age is lacking....Age-associated changes in immune cells have been linked to an increased risk for infection.However,a global and detailed characterization of the changes that human circulating immune cells undergo with age is lacking.Here,we combined scRNA-seq,mass cytometry and sCATAC-seq to compare immune cell types in peripheral blood collected from young and old subjects and patients with COVID-19.We found that the immune cell landscape was reprogrammed with age and was characterized by T cell polarization from naive and memory cells to effector,cytotoxic,exhausted and reg-ulatory cells,along with increased late natural killer cells,age-associated B cells,inflammatory monocytes and age-associated dendritic cells.In addition,the expression of genes,which were implicated in coron-avirus susceptibility,was upregulated in a cell subtype-specific manner with age.Notably,COVID-19 promoted age-induced immune cell polarization and gene expression related to inflammation and cellular senes-cence.Therefore,these findings suggest that a dysreg-ulated immune system and increased gene expression associated with SARS-CoV-2 susceptibility may at least partially account for COVID-19 vulnerability in the elderly.展开更多
The increasing prevalence of diabetes has become a global public health concern in the 21st century.In 2021,it was estimated that 537 million people had diabetes,and this number is projected to reach 643 million by 20...The increasing prevalence of diabetes has become a global public health concern in the 21st century.In 2021,it was estimated that 537 million people had diabetes,and this number is projected to reach 643 million by 2030,and 783 million by 2045[1].Such a huge burden of diabetes brings great challenges in its prevention and management,including early diagnosis,timely interventions,and regular monitoring of risk factor control and complications screening.Continuous self-care support and patient empowerment can enhance clinical and psychobehavioural outcomes[2],although these require additional resources including manpower,infrastructure(hard and technology),and finances.The emergence of digital health technologies(DHTs),especially artificial intelligence(AI),may help address these obstacles and alleviate the burden of diabetes[3].Large language models(LLMs),a generative AI that can accept image and text inputs and produce text outputs,have shown promise in various aspects of medical care.展开更多
Background:Fundus Autofluorescence(FAF)is a valuable imaging technique used to assess metabolic alterations in the retinal pigment epithelium(RPE)associated with various age-related and disease-related changes.The pra...Background:Fundus Autofluorescence(FAF)is a valuable imaging technique used to assess metabolic alterations in the retinal pigment epithelium(RPE)associated with various age-related and disease-related changes.The practical uses of FAF are ever-growing.This study aimed to evaluate the effectiveness of a generative deep learning(DL)model in translating color fundus(CF)images into synthetic FAF images and explore its potential for enhancing screening of age-related macular degeneration(AMD).Methods:A generative adversarial network(GAN)model was trained on pairs of CF and FAF images to generate synthetic FAF images.The quality of synthesized FAF images was assessed objectively by common generation metrics.Additionally,the clinical effectiveness of the generated FAF images in AMD classification was evaluated by measuring the area under the curve(AUC),using the LabelMe dataset.Results:A total of 8410 FAF images from 2586 patients were analyzed.The synthesized FAF images exhibited an impressive objectively assessed quality,achieving a multi-scale structural similarity index(MS-SSIM)of 0.67.When evaluated on the LabelMe dataset,the combination of generated FAF images and CF images resulted in a noteworthy improvement in AMD classification accuracy,with the AUC increasing from 0.931 to 0.968.Conclusions:This study presents the first attempt to use a generative deep learning model to create authentic and high-quality FAF images from CF images.The incorporation of the translated FAF images on top of CF images improved the accuracy of AMD classification.Overall,this study presents a promising approach to enhance largescale AMD screening.展开更多
Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide,including diseases associated with corneal pathologies,anterior chamber abnormalities(e.g.blood or inflammat...Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide,including diseases associated with corneal pathologies,anterior chamber abnormalities(e.g.blood or inflammation),and lens diseases.The construction of an automatic tool for segmentation of anterior segment eye lesions would greatly improve the efficiency of clinical care.With research on artificial intelligence progressing in recent years,deep learning models have shown their superiority in image classification and segmentation.The training and evaluation of deep learning models should be based on a large amount of data annotated with expertise;however,such data are relatively scarce in the domain of medicine.Herein,the authors developed a new medical image annotation system,called EyeHealer.It is a large-scale anterior eye segment dataset with both eye structures and lesions annotated at the pixel level.Comprehensive experiments were conducted to verify its performance in disease classification and eye lesion segmentation.The results showed that semantic segmentation models outperformed medical segmentation models.This paper describes the establishment of the system for automated classification and segmentation tasks.The dataset will be made publicly available to encourage future research in this area.展开更多
基金supported by the CAMS Innovation Fund for Medical Sciences(2019-I2M-5-005)the State Key Laboratory of Ophthalmology,Zhongshan Ophthalmic Center,Sun Yat-sen University.
文摘Autoimmune uveitis is one of the most common inflammatory eye diseases leading to blindness globally.Its etiology is primarily associated with autoimmune responses.Patients with this condition often exhibit complex and chronic disease courses,with a high propensity for recurrence.Current treatments mainly involve corticosteroids and immunosuppressive agents,which,despite their effectiveness,entail significant side effects that severely impact patients'vision and quality of life.There are still unresolved questions regarding the etiology and immunopathogenesis of autoimmune uveitis,and traditional high-throughput sequencing techniques fall short of adequately elucidating its pathogenic mechanisms at the cellular level.With the continuous advancement of single-cell sequencing technology,an increasing number of studies are leveraging this approach to deeply investigate the pathogenesis of autoimmune uveitis,thereby offering new insights for identifying novel diagnostic and therapeutic targets.This paper reviews the latest applications of single-cell sequencing technology in exploring the pathogenesis of autoimmune uveitis.Through the utilization of this technology,researchers can gain a more comprehensive understanding of cellular-level changes in patients,providing robust support for the search for new therapeutic avenues.These studies offer new directions for the diagnosis and treatment of autoimmune uveitis and provide valuable information for the development of future therapeutic strategies and approaches.
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Dear Editor,While trends in scientific collaborations between the US and China have now been described in a general context1,2-revealing a significant decline in productivity compared to other international partnerships-such trends have yet to be specifically evaluated for the field of ophthalmology,where there is an ever-important emphasis on multinational partnerships for the delivery of state-of-the-art,rigorous,and equitable eye care.1,3,4,5 In this study,we explore collaborations between researchers in the US and China in ophthalmology-related literature from 2000 to 2021.
基金This work was supported by the National Key Research and Development Program of China(2017YFA0105804)the Strategic Priority Research Program of the Chinese Academy of Sciences(XDA16010000)+8 种基金the National Key Research and Development Program of China(2018YFC2000100,2017YFA0103304,2017YFA0102802,2018YFA0107203)the National Natural Science Foundation of China(81670897,81625009,91749202.81861168034,81921006,31671429,91949209,91749123,81671377,81822018,81870228,81922027,81701388,81601233)the Program of the Beijing Municipal Science and Technology Commission(Z191100001519005)Bejing Natural Science Foun-dation(Z190019)Bejing Municipal Commission of Health and Family Planning(PXM2018026283_000002)Advanced Innovation Center for Human Brain Protection(3500-1192012)the Key Research Program of the Chinese Academy of Sciences(KFZD-SW-221)K.C.Wong Education Foundation(GJTD-2019-06,GJTD-2019-08),Youth Innovation Promotion Association of CAS(2016093)the State Key Laboratory of Membrane Biology and the State Key Laboratory of Stem Cell and Reproductive Biology.
文摘Age-associated changes in immune cells have been linked to an increased risk for infection.However,a global and detailed characterization of the changes that human circulating immune cells undergo with age is lacking.Here,we combined scRNA-seq,mass cytometry and sCATAC-seq to compare immune cell types in peripheral blood collected from young and old subjects and patients with COVID-19.We found that the immune cell landscape was reprogrammed with age and was characterized by T cell polarization from naive and memory cells to effector,cytotoxic,exhausted and reg-ulatory cells,along with increased late natural killer cells,age-associated B cells,inflammatory monocytes and age-associated dendritic cells.In addition,the expression of genes,which were implicated in coron-avirus susceptibility,was upregulated in a cell subtype-specific manner with age.Notably,COVID-19 promoted age-induced immune cell polarization and gene expression related to inflammation and cellular senes-cence.Therefore,these findings suggest that a dysreg-ulated immune system and increased gene expression associated with SARS-CoV-2 susceptibility may at least partially account for COVID-19 vulnerability in the elderly.
基金supported by the National Key R&D Program of China(2022YFC2502800 and 2022YFC2407000)the National Natural Science Foundation of China(8238810007,82022012,81870598 and 62272298)+3 种基金the Shanghai Municipal Key Clinical SpecialtyShanghai 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(SHSMU-ZDCX20212700)。
文摘The increasing prevalence of diabetes has become a global public health concern in the 21st century.In 2021,it was estimated that 537 million people had diabetes,and this number is projected to reach 643 million by 2030,and 783 million by 2045[1].Such a huge burden of diabetes brings great challenges in its prevention and management,including early diagnosis,timely interventions,and regular monitoring of risk factor control and complications screening.Continuous self-care support and patient empowerment can enhance clinical and psychobehavioural outcomes[2],although these require additional resources including manpower,infrastructure(hard and technology),and finances.The emergence of digital health technologies(DHTs),especially artificial intelligence(AI),may help address these obstacles and alleviate the burden of diabetes[3].Large language models(LLMs),a generative AI that can accept image and text inputs and produce text outputs,have shown promise in various aspects of medical care.
基金This research received support from the Global STEM Professorship Scheme(P0046113).
文摘Background:Fundus Autofluorescence(FAF)is a valuable imaging technique used to assess metabolic alterations in the retinal pigment epithelium(RPE)associated with various age-related and disease-related changes.The practical uses of FAF are ever-growing.This study aimed to evaluate the effectiveness of a generative deep learning(DL)model in translating color fundus(CF)images into synthetic FAF images and explore its potential for enhancing screening of age-related macular degeneration(AMD).Methods:A generative adversarial network(GAN)model was trained on pairs of CF and FAF images to generate synthetic FAF images.The quality of synthesized FAF images was assessed objectively by common generation metrics.Additionally,the clinical effectiveness of the generated FAF images in AMD classification was evaluated by measuring the area under the curve(AUC),using the LabelMe dataset.Results:A total of 8410 FAF images from 2586 patients were analyzed.The synthesized FAF images exhibited an impressive objectively assessed quality,achieving a multi-scale structural similarity index(MS-SSIM)of 0.67.When evaluated on the LabelMe dataset,the combination of generated FAF images and CF images resulted in a noteworthy improvement in AMD classification accuracy,with the AUC increasing from 0.931 to 0.968.Conclusions:This study presents the first attempt to use a generative deep learning model to create authentic and high-quality FAF images from CF images.The incorporation of the translated FAF images on top of CF images improved the accuracy of AMD classification.Overall,this study presents a promising approach to enhance largescale AMD screening.
基金This study was funded by the National Key Research and Development Program of China(Grant No.2017YFC1104600)Recruitment Program of Leading Talents of Guangdong Province(Grant No.2016LJ06Y375).
文摘Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide,including diseases associated with corneal pathologies,anterior chamber abnormalities(e.g.blood or inflammation),and lens diseases.The construction of an automatic tool for segmentation of anterior segment eye lesions would greatly improve the efficiency of clinical care.With research on artificial intelligence progressing in recent years,deep learning models have shown their superiority in image classification and segmentation.The training and evaluation of deep learning models should be based on a large amount of data annotated with expertise;however,such data are relatively scarce in the domain of medicine.Herein,the authors developed a new medical image annotation system,called EyeHealer.It is a large-scale anterior eye segment dataset with both eye structures and lesions annotated at the pixel level.Comprehensive experiments were conducted to verify its performance in disease classification and eye lesion segmentation.The results showed that semantic segmentation models outperformed medical segmentation models.This paper describes the establishment of the system for automated classification and segmentation tasks.The dataset will be made publicly available to encourage future research in this area.
