目的:建立和验证一个涉及多级临床场景的白内障协作通用的人工智能(artificial intelligence,AI)管理平台,探索基于AI的医疗转诊模式,以提高协作效率和资源覆盖率。方法:训练和验证的数据集来自中国AI医学联盟,涵盖多级医疗机构和采集...目的:建立和验证一个涉及多级临床场景的白内障协作通用的人工智能(artificial intelligence,AI)管理平台,探索基于AI的医疗转诊模式,以提高协作效率和资源覆盖率。方法:训练和验证的数据集来自中国AI医学联盟,涵盖多级医疗机构和采集模式。使用三步策略对数据集进行标记:1)识别采集模式;2)白内障诊断包括正常晶体眼、白内障眼或白内障术后眼;3)从病因和严重程度检测需转诊的白内障患者。此外,将白内障AI系统与真实世界中的居家自我监测、初级医疗保健机构和专科医院等多级转诊模式相结合。结果:通用AI平台和多级协作模式在三步任务中表现出可靠的诊断性能:1)识别采集模式的受试者操作特征(receiver operating characteristic curve,ROC)曲线下面积(area under the curve,AUC)为99.28%~99.71%);2)白内障诊断对正常晶体眼、白内障或术后眼,在散瞳-裂隙灯模式下的AUC分别为99.82%、99.96%和99.93%,其他采集模式的AUC均>99%;3)需转诊白内障的检测(在所有测试中AUC>91%)。在真实世界的三级转诊模式中,该系统建议30.3%的人转诊,与传统模式相比,眼科医生与人群服务比率大幅提高了10.2倍。结论:通用AI平台和多级协作模式显示了准确的白内障诊断性能和有效的白内障转诊服务。建议AI的医疗转诊模式扩展应用到其他常见疾病和资源密集型情景当中。展开更多
Glaucoma is the leading cause of irreversible blindness worldwide.In the pathogen-esis of glaucoma,activated microglia can lead to retinal ganglion cells(RGCs)apoptosis and death,however,the molecular mechanisms remai...Glaucoma is the leading cause of irreversible blindness worldwide.In the pathogen-esis of glaucoma,activated microglia can lead to retinal ganglion cells(RGCs)apoptosis and death,however,the molecular mechanisms remain largely unknown.We demonstrate that phospholipid scramblase 1(PLSCR1)is a key regulator promoting RGCs apoptosis and their clearance by microglia.As evidenced in retinal progenitor cells and RGCs of the acute ocular hypertension(AOH)mouse model,overexpressed PLSCR1 induced its translocation from the nucleus to the cytoplasm and cytomembrane,as well as elevated phosphatidylserine exposure and reactive oxygen species generation with subsequent RGCs apoptosis and death.These damages were effectively attenuated by PLSCR1 inhibition.In the AOH model,PLSCR1 led to an increase in M1 type microglia activation and retinal neuroinflammation.Upregulation of PLSCR1 resulted in strongly elevated phagocytosis of apoptotic RGCs by activated microglia.Taken together,our study provides important insights linking activated microglia to RGCs death in the glaucoma pathogenesis and other RGC-related neurodegenerative diseases.展开更多
In recent years,the incidence of myopia has increased at an alarming rate among children and adolescents in China.The exploration of an effective prevention and control method for myopia is in urgent need.With the dev...In recent years,the incidence of myopia has increased at an alarming rate among children and adolescents in China.The exploration of an effective prevention and control method for myopia is in urgent need.With the development of information technology in the past decade,artificial intelligence with the Internet of Things technology(AIoT)is characterized by strong computing power,advanced algorithm,continuous monitoring,and accurate prediction of long-term progression.Therefore,big data and artificial intelligence technology have the potential to be applied to data mining of myopia etiology and prediction of myopia occurrence and development.More recently,there has been a growing recognition that myopia study involving AIoT needs to undergo a rigorous evaluation to demonstrate robust results.展开更多
文摘目的:建立和验证一个涉及多级临床场景的白内障协作通用的人工智能(artificial intelligence,AI)管理平台,探索基于AI的医疗转诊模式,以提高协作效率和资源覆盖率。方法:训练和验证的数据集来自中国AI医学联盟,涵盖多级医疗机构和采集模式。使用三步策略对数据集进行标记:1)识别采集模式;2)白内障诊断包括正常晶体眼、白内障眼或白内障术后眼;3)从病因和严重程度检测需转诊的白内障患者。此外,将白内障AI系统与真实世界中的居家自我监测、初级医疗保健机构和专科医院等多级转诊模式相结合。结果:通用AI平台和多级协作模式在三步任务中表现出可靠的诊断性能:1)识别采集模式的受试者操作特征(receiver operating characteristic curve,ROC)曲线下面积(area under the curve,AUC)为99.28%~99.71%);2)白内障诊断对正常晶体眼、白内障或术后眼,在散瞳-裂隙灯模式下的AUC分别为99.82%、99.96%和99.93%,其他采集模式的AUC均>99%;3)需转诊白内障的检测(在所有测试中AUC>91%)。在真实世界的三级转诊模式中,该系统建议30.3%的人转诊,与传统模式相比,眼科医生与人群服务比率大幅提高了10.2倍。结论:通用AI平台和多级协作模式显示了准确的白内障诊断性能和有效的白内障转诊服务。建议AI的医疗转诊模式扩展应用到其他常见疾病和资源密集型情景当中。
基金supported by The National Natural Science Foundation of China(No.81670894,81721003,81570862,82000915)The National Key Research and Development Program of China(No.2020YFA0112701)+5 种基金The Pearl River Talents Program-Local Innovative and Research Teams(No.2017BT01S138)The“100 talents plan”from Sun Yat-sen Universitythe Open Research Funds of the State Key Laboratory of Ophthalmology(No.2022KF04)The Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science(No.2017B030314025)The NSFC/Macao Science and Technology Development Fund(No.015/2017/AFJ to KZ)the Fundamental Research Funds for the Central Universities,Sun Yat-sen University(No.22qntd3902).
文摘Glaucoma is the leading cause of irreversible blindness worldwide.In the pathogen-esis of glaucoma,activated microglia can lead to retinal ganglion cells(RGCs)apoptosis and death,however,the molecular mechanisms remain largely unknown.We demonstrate that phospholipid scramblase 1(PLSCR1)is a key regulator promoting RGCs apoptosis and their clearance by microglia.As evidenced in retinal progenitor cells and RGCs of the acute ocular hypertension(AOH)mouse model,overexpressed PLSCR1 induced its translocation from the nucleus to the cytoplasm and cytomembrane,as well as elevated phosphatidylserine exposure and reactive oxygen species generation with subsequent RGCs apoptosis and death.These damages were effectively attenuated by PLSCR1 inhibition.In the AOH model,PLSCR1 led to an increase in M1 type microglia activation and retinal neuroinflammation.Upregulation of PLSCR1 resulted in strongly elevated phagocytosis of apoptotic RGCs by activated microglia.Taken together,our study provides important insights linking activated microglia to RGCs death in the glaucoma pathogenesis and other RGC-related neurodegenerative diseases.
基金The Science and Technology Planning Projects of Guangdong Province(Grant No.2018B010109008)National Key R&D Program of China(Grant No.2018YFC0116500).
文摘In recent years,the incidence of myopia has increased at an alarming rate among children and adolescents in China.The exploration of an effective prevention and control method for myopia is in urgent need.With the development of information technology in the past decade,artificial intelligence with the Internet of Things technology(AIoT)is characterized by strong computing power,advanced algorithm,continuous monitoring,and accurate prediction of long-term progression.Therefore,big data and artificial intelligence technology have the potential to be applied to data mining of myopia etiology and prediction of myopia occurrence and development.More recently,there has been a growing recognition that myopia study involving AIoT needs to undergo a rigorous evaluation to demonstrate robust results.