An artificial intelligence platform for the multihospital collaborative management of congenital cataracts

Using artificial intelligence (AI) to prevent and treat diseases is an ultimate goal in computational medicine. Although AI has been developed for screening and assisted decision-making in disease prevention and management, it has not yet been validated for systematic application in the clinic. In the context of rare diseases, the main strategy has been to build specialized care centres; however, these centres are scattered and their coverage is insufficient, which leaves a large proportion of rare-disease patients with inadequate care. Here, we show that an AI agent using deep learning, and involving convolutional neural networks for diagnostics, risk stratification and treatment suggestions, accurately diagnoses and provides treatment decisions for congenital cataracts in an in silico test, in a website-based study, in a ‘finding a needle in a haystack’ test and in a multihospital clinical trial. We also show that the AI agent and individual ophthalmologists perform equally well. Moreover, we have integrated the AI agent with a cloud-based platform for multihospital collaboration, designed to improve disease management for the benefit of patients with rare diseases. An artificial intelligence agent integrated with a cloud-based platform for multihospital collaboration performs equally as well as ophthalmologists in the diagnosis of congenital cataracts in a series of online tests and a multihospital clinical trial.

[1]  J. Cano,et al.  Innovative tools for assessing risks for severe adverse events in areas of overlapping Loa loa and other filarial distributions: the application of micro-stratification mapping , 2014, Parasites & Vectors.

[2]  Jia Deng,et al.  Large scale visual recognition , 2012 .

[3]  Richard Bowman,et al.  Global challenges in the management of congenital cataract: proceedings of the 4th International Congenital Cataract Symposium held on March 7, 2014, New York, New York. , 2015, Journal of AAPOS : the official publication of the American Association for Pediatric Ophthalmology and Strabismus.

[4]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[5]  Patrick Blake,et al.  Clinical decision support systems for improving diagnostic accuracy and achieving precision medicine , 2015, Journal of Clinical Bioinformatics.

[6]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[7]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[8]  Shaochen Chen,et al.  Lens regeneration using endogenous stem cells with gain of visual function , 2016, Nature.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Si Jin,et al.  Current progress in the management of rare diseases and orphan drugs in China. , 2012, Intractable & Rare Diseases Research.

[11]  Arrigo Schieppati,et al.  Why rare diseases are an important medical and social issue , 2008, The Lancet.

[12]  Luca Maria Gambardella,et al.  High-Performance Neural Networks for Visual Object Classification , 2011, ArXiv.

[13]  Anagha Medsinge,et al.  Pediatric cataract: challenges and future directions , 2015, Clinical ophthalmology.

[14]  A. Rai,et al.  A smartphone dongle for diagnosis of infectious diseases at the point of care , 2015, Science Translational Medicine.

[15]  Domenica Taruscio,et al.  National plans and strategies on rare diseases in Europe. , 2010, Advances in experimental medicine and biology.

[16]  Jianqiang Li,et al.  A computer-aided healthcare system for cataract classification and grading based on fundus image analysis , 2015, Comput. Ind..

[17]  Jeff J Guo,et al.  China's first rare-disease registry is under development , 2011, The Lancet.

[18]  Peter Szolovits,et al.  The coming of age of artificial intelligence in medicine , 2009, Artif. Intell. Medicine.

[19]  Isabelle Russell-Eggitt,et al.  The morphology and natural history of childhood cataracts. , 2003, Survey of ophthalmology.

[20]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[21]  Weirong Chen,et al.  Documenting rare disease data in China. , 2015, Science.

[22]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[23]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[24]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[25]  Giuseppe Remuzzi,et al.  Rare diseases: what's next? , 2008, The Lancet.

[26]  Yann LeCun,et al.  Convolutional networks and applications in vision , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[27]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[28]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[30]  Jianqiang Li,et al.  Exploiting ensemble learning for automatic cataract detection and grading , 2016, Comput. Methods Programs Biomed..

[31]  Carl Mitcham,et al.  Acknowledging AI's dark side. , 2015, Science.

[32]  Ruben Abagyan,et al.  Lanosterol reverses protein aggregation in cataracts , 2015, Nature.

[33]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.