Federated machine learning in healthcare: A systematic review on clinical applications and technical architecture.

Federated learning (FL) is a distributed machine learning framework that is gaining traction in view of increasing health data privacy protection needs. By conducting a systematic review of FL applications in healthcare, we identify relevant articles in scientific, engineering, and medical journals in English up to August 31st, 2023. Out of a total of 22,693 articles under review, 612 articles are included in the final analysis. The majority of articles are proof-of-concepts studies, and only 5.2% are studies with real-life application of FL. Radiology and internal medicine are the most common specialties involved in FL. FL is robust to a variety of machine learning models and data types, with neural networks and medical imaging being the most common, respectively. We highlight the need to address the barriers to clinical translation and to assess its real-world impact in this new digital data-driven healthcare scene.

Synthetic artificial intelligence using generative adversarial network for retinal imaging in detection of age-related macular degeneration.

Introduction: Age-related macular degeneration (AMD) is one of the leading causes of vision impairment globally and early detection is crucial to prevent vision loss. However, the screening of AMD is resource dependent and demands experienced healthcare providers. Recently, deep learning (DL) systems have shown the potential for effective detection of various eye diseases from retinal fundus images, but the development of such robust systems requires a large amount of datasets, which could be limited by prevalence of the disease and privacy of patient. As in the case of AMD, the advanced phenotype is often scarce for conducting DL analysis, which may be tackled via generating synthetic images using Generative Adversarial Networks (GANs). This study aims to develop GAN-synthesized fundus photos with AMD lesions, and to assess the realness of these images with an objective scale. Methods: To build our GAN models, a total of 125,012 fundus photos were used from a real-world non-AMD phenotypical dataset. StyleGAN2 and human-in-the-loop (HITL) method were then applied to synthesize fundus images with AMD features. To objectively assess the quality of the synthesized images, we proposed a novel realness scale based on the frequency of the broken vessels observed in the fundus photos. Four residents conducted two rounds of gradings on 300 images to distinguish real from synthetic images, based on their subjective impression and the objective scale respectively. Results and discussion: The introduction of HITL training increased the percentage of synthetic images with AMD lesions, despite the limited number of AMD images in the initial training dataset. Qualitatively, the synthesized images have been proven to be robust in that our residents had limited ability to distinguish real from synthetic ones, as evidenced by an overall accuracy of 0.66 (95% CI: 0.61-0.66) and Cohen's kappa of 0.320. For the non-referable AMD classes (no or early AMD), the accuracy was only 0.51. With the objective scale, the overall accuracy improved to 0.72. In conclusion, GAN models built with HITL training are capable of producing realistic-looking fundus images that could fool human experts, while our objective realness scale based on broken vessels can help identifying the synthetic fundus photos.

Development and testing of a multi-lingual Natural Language Processing-based deep learning system in 10 languages for COVID-19 pandemic crisis: A multi-center study.

Purpose: The COVID-19 pandemic has drastically disrupted global healthcare systems. With the higher demand for healthcare and misinformation related to COVID-19, there is a need to explore alternative models to improve communication. Artificial Intelligence (AI) and Natural Language Processing (NLP) have emerged as promising solutions to improve healthcare delivery. Chatbots could fill a pivotal role in the dissemination and easy accessibility of accurate information in a pandemic. In this study, we developed a multi-lingual NLP-based AI chatbot, DR-COVID, which responds accurately to open-ended, COVID-19 related questions. This was used to facilitate pandemic education and healthcare delivery. Methods: First, we developed DR-COVID with an ensemble NLP model on the Telegram platform (https://t.me/drcovid_nlp_chatbot). Second, we evaluated various performance metrics. Third, we evaluated multi-lingual text-to-text translation to Chinese, Malay, Tamil, Filipino, Thai, Japanese, French, Spanish, and Portuguese. We utilized 2,728 training questions and 821 test questions in English. Primary outcome measurements were (A) overall and top 3 accuracies; (B) Area Under the Curve (AUC), precision, recall, and F1 score. Overall accuracy referred to a correct response for the top answer, whereas top 3 accuracy referred to an appropriate response for any one answer amongst the top 3 answers. AUC and its relevant matrices were obtained from the Receiver Operation Characteristics (ROC) curve. Secondary outcomes were (A) multi-lingual accuracy; (B) comparison to enterprise-grade chatbot systems. The sharing of training and testing datasets on an open-source platform will also contribute to existing data. Results: Our NLP model, utilizing the ensemble architecture, achieved overall and top 3 accuracies of 0.838 [95% confidence interval (CI): 0.826-0.851] and 0.922 [95% CI: 0.913-0.932] respectively. For overall and top 3 results, AUC scores of 0.917 [95% CI: 0.911-0.925] and 0.960 [95% CI: 0.955-0.964] were achieved respectively. We achieved multi-linguicism with nine non-English languages, with Portuguese performing the best overall at 0.900. Lastly, DR-COVID generated answers more accurately and quickly than other chatbots, within 1.12-2.15 s across three devices tested. Conclusion: DR-COVID is a clinically effective NLP-based conversational AI chatbot, and a promising solution for healthcare delivery in the pandemic era.

Acceptance and Perception of Artificial Intelligence Usability in Eye Care (APPRAISE) for Ophthalmologists: A Multinational Perspective.

Background: Many artificial intelligence (AI) studies have focused on development of AI models, novel techniques, and reporting guidelines. However, little is understood about clinicians' perspectives of AI applications in medical fields including ophthalmology, particularly in light of recent regulatory guidelines. The aim for this study was to evaluate the perspectives of ophthalmologists regarding AI in 4 major eye conditions: diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD) and cataract. Methods: This was a multi-national survey of ophthalmologists between March 1st, 2020 to February 29th, 2021 disseminated via the major global ophthalmology societies. The survey was designed based on microsystem, mesosystem and macrosystem questions, and the software as a medical device (SaMD) regulatory framework chaired by the Food and Drug Administration (FDA). Factors associated with AI adoption for ophthalmology analyzed with multivariable logistic regression random forest machine learning. Results: One thousand one hundred seventy-six ophthalmologists from 70 countries participated with a response rate ranging from 78.8 to 85.8% per question. Ophthalmologists were more willing to use AI as clinical assistive tools (88.1%, n = 890/1,010) especially those with over 20 years' experience (OR 3.70, 95% CI: 1.10-12.5, p = 0.035), as compared to clinical decision support tools (78.8%, n = 796/1,010) or diagnostic tools (64.5%, n = 651). A majority of Ophthalmologists felt that AI is most relevant to DR (78.2%), followed by glaucoma (70.7%), AMD (66.8%), and cataract (51.4%) detection. Many participants were confident their roles will not be replaced (68.2%, n = 632/927), and felt COVID-19 catalyzed willingness to adopt AI (80.9%, n = 750/927). Common barriers to implementation include medical liability from errors (72.5%, n = 672/927) whereas enablers include improving access (94.5%, n = 876/927). Machine learning modeling predicted acceptance from participant demographics with moderate to high accuracy, and area under the receiver operating curves of 0.63-0.83. Conclusion: Ophthalmologists are receptive to adopting AI as assistive tools for DR, glaucoma, and AMD. Furthermore, ML is a useful method that can be applied to evaluate predictive factors on clinical qualitative questionnaires. This study outlines actionable insights for future research and facilitation interventions to drive adoption and operationalization of AI tools for Ophthalmology.

Metaverse and Virtual Health Care in Ophthalmology: Opportunities and Challenges.

ABSTRACT: The outbreak of the coronavirus disease 2019 has further increased the urgent need for digital transformation within the health care settings, with the use of artificial intelligence/deep learning, internet of things, telecommunication network/virtual platform, and blockchain. The recent advent of metaverse, an interconnected online universe, with the synergistic combination of augmented, virtual, and mixed reality described several years ago, presents a new era of immersive and real-time experiences to enhance human-to-human social interaction and connection. In health care and ophthalmology, the creation of virtual environment with three-dimensional (3D) space and avatar, could be particularly useful in patient-fronting platforms (eg, telemedicine platforms), operational uses (eg, meeting organization), digital education (eg, simulated medical and surgical education), diagnostics, and therapeutics. On the other hand, the implementation and adoption of these emerging virtual health care technologies will require multipronged approaches to ensure interoperability with real-world virtual clinical settings, user-friendliness of the technologies and clinical efficiencies while complying to the clinical, health economics, regulatory, and cybersecurity standards. To serve the urgent need, it is important for the eye community to continue to innovate, invent, adapt, and harness the unique abilities of virtual health care technology to provide better eye care worldwide.

Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology.

PURPOSE OF REVIEW: The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each. RECENT FINDINGS: Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks. SUMMARY: AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.

Application of artificial intelligence in cataract management: current and future directions.

The rise of artificial intelligence (AI) has brought breakthroughs in many areas of medicine. In ophthalmology, AI has delivered robust results in the screening and detection of diabetic retinopathy, age-related macular degeneration, glaucoma, and retinopathy of prematurity. Cataract management is another field that can benefit from greater AI application. Cataract  is the leading cause of reversible visual impairment with a rising global clinical burden. Improved diagnosis, monitoring, and surgical management are necessary to address this challenge. In addition, patients in large developing countries often suffer from limited access to tertiary care, a problem further exacerbated by the ongoing COVID-19 pandemic. AI on the other hand, can help transform cataract management by improving automation, efficacy and overcoming geographical barriers. First, AI can be applied as a telediagnostic platform to screen and diagnose patients with cataract using slit-lamp and fundus photographs. This utilizes a deep-learning, convolutional neural network (CNN) to detect and classify referable cataracts appropriately. Second, some of the latest intraocular lens formulas have used AI to enhance prediction accuracy, achieving superior postoperative refractive results compared to traditional formulas. Third, AI can be used to augment cataract surgical skill training by identifying different phases of cataract surgery on video and to optimize operating theater workflows by accurately predicting the duration of surgical procedures. Fourth, some AI CNN models are able to effectively predict the progression of posterior capsule opacification and eventual need for YAG laser capsulotomy. These advances in AI could transform cataract management and enable delivery of efficient ophthalmic services. The key challenges include ethical management of data, ensuring data security and privacy, demonstrating clinically acceptable performance, improving the generalizability of AI models across heterogeneous populations, and improving the trust of end-users.

Updates in deep learning research in ophthalmology.

Ophthalmology has been one of the early adopters of artificial intelligence (AI) within the medical field. Deep learning (DL), in particular, has garnered significant attention due to the availability of large amounts of data and digitized ocular images. Currently, AI in Ophthalmology is mainly focused on improving disease classification and supporting decision-making when treating ophthalmic diseases such as diabetic retinopathy, age-related macular degeneration (AMD), glaucoma and retinopathy of prematurity (ROP). However, most of the DL systems (DLSs) developed thus far remain in the research stage and only a handful are able to achieve clinical translation. This phenomenon is due to a combination of factors including concerns over security and privacy, poor generalizability, trust and explainability issues, unfavorable end-user perceptions and uncertain economic value. Overcoming this challenge would require a combination approach. Firstly, emerging techniques such as federated learning (FL), generative adversarial networks (GANs), autonomous AI and blockchain will be playing an increasingly critical role to enhance privacy, collaboration and DLS performance. Next, compliance to reporting and regulatory guidelines, such as CONSORT-AI and STARD-AI, will be required to in order to improve transparency, minimize abuse and ensure reproducibility. Thirdly, frameworks will be required to obtain patient consent, perform ethical assessment and evaluate end-user perception. Lastly, proper health economic assessment (HEA) must be performed to provide financial visibility during the early phases of DLS development. This is necessary to manage resources prudently and guide the development of DLS.

Blockchain applications in health care for COVID-19 and beyond: a systematic review.

The COVID-19 pandemic has had a substantial and global impact on health care, and has greatly accelerated the adoption of digital technology. One of these emerging digital technologies, blockchain, has unique characteristics (eg, immutability, decentralisation, and transparency) that can be useful in multiple domains (eg, management of electronic medical records and access rights, and mobile health). We conducted a systematic review of COVID-19-related and non-COVID-19-related applications of blockchain in health care. We identified relevant reports published in MEDLINE, SpringerLink, Institute of Electrical and Electronics Engineers Xplore, ScienceDirect, arXiv, and Google Scholar up to July 29, 2021. Articles that included both clinical and technical designs, with or without prototype development, were included. A total of 85 375 articles were evaluated, with 415 full length reports (37 related to COVID-19 and 378 not related to COVID-19) eventually included in the final analysis. The main COVID-19-related applications reported were pandemic control and surveillance, immunity or vaccine passport monitoring, and contact tracing. The top three non-COVID-19-related applications were management of electronic medical records, internet of things (eg, remote monitoring or mobile health), and supply chain monitoring. Most reports detailed technical performance of the blockchain prototype platforms (277 [66·7%] of 415), whereas nine (2·2%) studies showed real-world clinical application and adoption. The remaining studies (129 [31·1%] of 415) were themselves of a technical design only. The most common platforms used were Ethereum and Hyperledger. Blockchain technology has numerous potential COVID-19-related and non-COVID-19-related applications in health care. However, much of the current research remains at the technical stage, with few providing actual clinical applications, highlighting the need to translate foundational blockchain technology into clinical use.

Deep learning-based natural language processing in ophthalmology: applications, challenges and future directions.

PURPOSE OF REVIEW: Artificial intelligence (AI) is the fourth industrial revolution in mankind's history. Natural language processing (NLP) is a type of AI that transforms human language, to one that computers can interpret and process. NLP is still in the formative stages of development in healthcare, with promising applications and potential challenges in its applications. This review provides an overview of AI-based NLP, its applications in healthcare and ophthalmology, next-generation use case, as well as potential challenges in deployment. RECENT FINDINGS: The integration of AI-based NLP systems into existing clinical care shows considerable promise in disease screening, risk stratification, and treatment monitoring, amongst others. Stakeholder collaboration, greater public acceptance, and advancing technologies will continue to shape the NLP landscape in healthcare and ophthalmology. SUMMARY: Healthcare has always endeavored to be patient centric and personalized. For AI-based NLP systems to become an eventual reality in larger-scale applications, it is pertinent for key stakeholders to collaborate and address potential challenges in application. Ultimately, these would enable more equitable and generalizable use of NLP systems for the betterment of healthcare and society.

Generative adversarial networks in ophthalmology: what are these and how can they be used?

PURPOSE OF REVIEW: The development of deep learning (DL) systems requires a large amount of data, which may be limited by costs, protection of patient information and low prevalence of some conditions. Recent developments in artificial intelligence techniques have provided an innovative alternative to this challenge via the synthesis of biomedical images within a DL framework known as generative adversarial networks (GANs). This paper aims to introduce how GANs can be deployed for image synthesis in ophthalmology and to discuss the potential applications of GANs-produced images. RECENT FINDINGS: Image synthesis is the most relevant function of GANs to the medical field, and it has been widely used for generating 'new' medical images of various modalities. In ophthalmology, GANs have mainly been utilized for augmenting classification and predictive tasks, by synthesizing fundus images and optical coherence tomography images with and without pathologies such as age-related macular degeneration and diabetic retinopathy. Despite their ability to generate high-resolution images, the development of GANs remains data intensive, and there is a lack of consensus on how best to evaluate the outputs produced by GANs. SUMMARY: Although the problem of artificial biomedical data generation is of great interest, image synthesis by GANs represents an innovation with yet unclear relevance for ophthalmology.

Artificial intelligence in myopia: current and future trends.

PURPOSE OF REVIEW: Myopia is one of the leading causes of visual impairment, with a projected increase in prevalence globally. One potential approach to address myopia and its complications is early detection and treatment. However, current healthcare systems may not be able to cope with the growing burden. Digital technological solutions such as artificial intelligence (AI) have emerged as a potential adjunct for myopia management. RECENT FINDINGS: There are currently four significant domains of AI in myopia, including machine learning (ML), deep learning (DL), genetics and natural language processing (NLP). ML has been demonstrated to be a useful adjunctive for myopia prediction and biometry for cataract surgery in highly myopic individuals. DL techniques, particularly convoluted neural networks, have been applied to various image-related diagnostic and predictive solutions. Applications of AI in genomics and NLP appear to be at a nascent stage. SUMMARY: Current AI research is mainly focused on disease classification and prediction in myopia. Through greater collaborative research, we envision AI will play an increasingly critical role in big data analysis by aggregating a greater variety of parameters including genomics and environmental factors. This may enable the development of generalizable adjunctive DL systems that could help realize predictive and individualized precision medicine for myopic patients.

CHOROIDAL VASCULAR HYPERPERMEABILITY AS A PREDICTOR OF TREATMENT RESPONSE FOR POLYPOIDAL CHOROIDAL VASCULOPATHY.

PURPOSE: To investigate the influence of choroidal vascular hyperpermeability (CVH) and choroidal thickness on treatment outcomes in eyes with polypoidal choroidal vasculopathy (PCV) undergoing anti-vascular endothelial growth factor monotherapy or combination therapy of photodynamic therapy and anti-vascular endothelial growth factor injections. METHODS: The authors performed a prospective, observational cohort study involving 72 eyes of 72 patients with polypoidal choroidal vasculopathy (mean age 68.6 years, 51% men) treated with either monotherapy (n = 41) or combination therapy (n = 31). Each eye was imaged with color fundus photography, fluorescent angiography, indocyanine green angiography, and spectral domain optical coherence tomography. Indocyanine green angiography images were used to evaluate CVH, and spectral domain optical coherence tomography was used to measure central choroidal thickness. Changes in visual acuity over 12 months, and number of anti-vascular endothelial growth factor injections were investigated. RESULTS: Choroidal vascular hyperpermeability was present in 31 eyes (43.1%). Visual acuity change over 12 months was numerically better in the CVH group compared with the CVH (-) group (-0.099 and -0.366 logarithm of the minimal angle of resolution unit in the CVH (-) and CVH (+) groups, respectively, multivariate P = 0.063) and significantly better in a matched pair analysis (P = 0.033). Furthermore, in the combination therapy group, the number of injection was significantly lower in the CVH (+) group compared with the CVH (-) group (4.68 vs. 2.58 injections/year in the CVH (-) and CVH (+) groups; P = 0.0044). There was no significant relationship between treatment response and choroidal thickening. CONCLUSION: The presence of CVH is associated with better visual outcome in eyes with polypoidal choroidal vasculopathy and lower injection number in combination therapy. Thus, CVH, but not choroidal thickness, should be further evaluated as a potential biomarker for selecting patients for combination therapy.

CHOROIDAL VASCULARITY INDEX: A Novel Optical Coherence Tomography Based Parameter in Patients With Exudative Age-Related Macular Degeneration.

PURPOSE: To evaluate choroidal structural changes in exudative age-related macular degeneration (AMD) using choroidal vascularity index computed from image binarization on spectral domain optical coherence tomography with enhanced depth imaging. METHODS: This prospective case series included 42 consecutive patients with unilateral exudative AMD. Choroidal images were segmented into luminal area and stromal area. Choroidal vascularity index was defined as the ratio of luminal area to total choroid area. Mean choroidal vascularity index and mean choroidal thickness between study and fellow eyes of the same patient with dry AMD were compared using Student's t-test. RESULTS: There was a significantly lower choroidal vascularity index in eyes with exudative AMD (60.14 ± 4.55 vs. 62.75 ± 4.82, P < 0.01). Luminal area (P < 0.01) was decreased in eyes with exudative AMD but there was no significant difference in total choroid area (P = 0.05) and choroidal thickness (P = 0.93) between study and fellow eyes. CONCLUSION: Eyes with exudative AMD demonstrated reduced choroidal vascularity index but insignificant differences in choroidal thickness compared with their fellow eyes. Choroidal vascularity index may be a potential noninvasive tool for studying structural changes in choroid and monitoring choroidal disease in exudative AMD.

Choroidal Structural Changes in Myopic Choroidal Neovascularization After Treatment With Antivascular Endothelial Growth Factor Over 1 Year.

PURPOSE: To evaluate choroidal structural changes in eyes with myopic choroidal neovascularization (mCNV) treated with anti-VEGF over 12 months. METHODS: We prospectively evaluated subfoveal choroidal thickness (SFCT) and choroidal vascularity index (CVI) using spectral-domain optical coherence tomography (SD-OCT) at baseline, 6, and 12 months in both eyes in patients presenting with unilateral mCNV. Choroidal vascularity index was defined as the ratio of luminal area to total choroidal area after SD-OCT images were binarized digitally. RESULTS: We included 20 patients (20 eyes with mCNV and 20 fellow eyes without mCNV) with mean age of 60.35 ± 10.85 years. At baseline, mean SFCT and CVI was similar between eyes with mCNV and fellow eyes (69.20 ± 63.04 µm vs. 67.10 ± 65.74 µm, P = 0.713 for SFCT and 59.44 ± 3.92% vs. 59.03 ±. 5.58%, P = 0.958 for CVI). Subfoveal choroidal thickness decreased significantly in the mCNV eyes to 54.75 ± 45.43 µm (P = 0.017) at 12 months after anti-VEGF therapy, whereas SFCT in the contralateral eyes did not change significantly. There was no significant change in CVI in mCNV eyes or contralateral eyes from baseline to 12 months. Thinning of SFCT did not influence final BCVA. CONCLUSIONS: Thinning of subfoveal choroid without alteration in CVI was observed in eyes with mCNV treated with anti-VEGF therapy over 12 months. This finding may be explained by mechanical stretching in response to globe expansion.

Management of Myopic Choroidal Neovascularization: Focus on Anti-VEGF Therapy.

Myopic choroidal neovascularization (mCNV) is the second most common form of CNV after age-related macular degeneration (AMD). It is a sight-threatening complication of pathologic myopia (PM) and often affects patients in their working years causing significant impact on quality of life. Previous therapies such as photodynamic therapy with verteporfin have shown limited success. Due to the similarities in pathogenesis of mCNV and AMD CNV, anti-vascular endothelial growth factor therapy (anti-VEGF), which has so far been the mainstay of treatment for AMD CNV, has been shown to be effective in the treatment of mCNV and has become the first-line treatment of choice. This article aims to examine briefly the epidemiology and pathophysiology of mCNV, as well as review the evidence for efficacy, safety, and clinical use of anti-VEGF treatment for mCNV.