Search

Abstract Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies. We establish an uncertainty-inspired open set (UIOS) model, which is trained with fundus images of 9 retinal conditions. Besides assessing the probability of each category, UIOS also calculates an uncertainty score to express its confidence. Our UIOS model with thresholding strategy achieves an F1 score of 99.55%, 97.01% and 91.91% for the internal testing set, external target categories (TC)-JSIEC dataset and TC-unseen testing set, respectively, compared to the F1 score of 92.20%, 80.69% and 64.74% by the standard AI model. Furthermore, UIOS correctly predicts high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images. UIOS provides a robust method for real-world screening of retinal anomalies.

Summary: Genomic researchers increasingly utilize commercial cloud service providers (CSPs) to manage data and analytics needs. CSPs allow researchers to grow Information Technology (IT) infrastructure on demand to overcome bottlenecks when combining large datasets. However, without adequate security controls, the risk of unauthorized access may be higher for data stored on the cloud. Additionally, regulators are mandating data access patterns and specific security protocols for the storage and use of genomic data. While CSP provides tools for security and regulatory compliance, building the necessary controls required for cloud solutions is not trivial. Research Assets Provisioning and Tracking Online Repository (RAPTOR) by the Genome Institute of Singapore is a cloud-native genomics data repository and analytics platform that implements a “five-safes” framework to provide security and governance controls to data contributors and users, leveraging CSP for sharing and analysis of genomic datasets without the risk of security breaches or running afoul of regulations.

PurposeThis study explores the association between the duration and variation of infant sleep trajectories and subsequent cognitive school readiness at 48–50 months.MethodsParticipants were 288 multi-ethnic children, within the Growing Up in Singapore Towards healthy Outcomes (GUSTO) cohort. Caregiver-reported total, night and day sleep durations were obtained at 3, 6, 9, 12, 18, 24 using the Brief Infant Sleep Questionnaire and 54 months using the Child Sleep Habits Questionnaire. Total, night and day sleep trajectories with varying durations (short, moderate, or long) and variability (consistent or variable; defined by standard errors) were identified. The cognitive school readiness test battery was administered when the children were between 48 and 50 months old. Both unadjusted adjusted analysis of variance models and adjusted analysis of covariance models (for confounders) were performed to assess associations between sleep trajectories and individual school readiness tests in the domains of language, numeracy, general cognition and memory.ResultsIn the unadjusted models, children with short variable total sleep trajectories had poorer performance on language tests compared to those with longer and more consistent trajectories. In both unadjusted and adjusted models, children with short variable night sleep trajectories had poorer numeracy knowledge compared to their counterparts with long consistent night sleep trajectories. There were no equivalent associations between sleep trajectories and school readiness performance for tests in the general cognition or memory domains. There were no significant findings for day sleep trajectories.ConclusionFindings suggest that individual differences in longitudinal sleep duration patterns from as early as 3 months of age may be associated with language and numeracy aspects of school readiness at 48–50 months of age. This is important, as early school readiness, particularly the domains of language and mathematics, is a key predictor of subsequent academic achievement.

Quantum computers have provided a promising tool for tackling NP hard problems. However, most of the existing work on quantum annealers assumes exclusive access to all resources available in a quantum annealer. This is not resource efficient if a task consumes only a small part of an annealer and leaves the rest wasted. We ask if we can run multiple tasks in parallel or concurrently on an annealer, just like the multitasking capability of a classical general-purpose processor. By far, multitasking is not natively supported by any of the existing annealers. In this paper, we explore Multitasking in Quantum Annealer (QAMT) by identifying the parallelism in a quantum annealer from the aspect of space and time. Based on commercialised quantum annealers from D-Wave, we propose a realisation scheme for QAMT, which packs multiple tasks into a quantum machine instruction (QMI) and uses predefined sampling time to emulate task preemption. We enumerate a few scheduling algorithms that match well with QAMT and discuss the challenges in QAMT. To demonstrate the potential of QAMT, we simulate a quantum annealing system, implement a demo QAMT scheduling algorithm, and evaluate the algorithm. Experimental results suggest that there is great potential in multitasking in quantum annealing.

BackgroundThe 2019 novel COVID-19 has severely burdened the health care system through its rapid transmission. Mobile health (mHealth) is a viable solution to facilitate remote monitoring and continuity of care for patients with COVID-19 in a home environment. However, the conceptualization and development of mHealth apps are often time and labor-intensive and are laden with concerns relating to data security and privacy. Implementing mHealth apps is also a challenging feat as language-related barriers limit adoption, whereas its perceived lack of benefits affects sustained use. The rapid development of an mHealth app that is cost-effective, secure, and user-friendly will be a timely enabler. ObjectiveThis project aimed to develop an mHealth app, DrCovid+, to facilitate remote monitoring and continuity of care for patients with COVID-19 by using the rapid development approach. It also aimed to address the challenges of mHealth app adoption and sustained use. MethodsThe Rapid Application Development approach was adopted. Stakeholders including decision makers, physicians, nurses, health care administrators, and research engineers were engaged. The process began with requirements gathering to define and finalize the project scope, followed by an iterative process of developing a working prototype, conducting User Acceptance Tests, and improving the prototype before implementation. Co-designing principles were applied to ensure equal collaborative efforts and collective agreement among stakeholders. ResultsDrCovid+ was developed on Telegram Messenger and hosted on a cloud server. It features a secure patient enrollment and data interface, a multilingual communication channel, and both automatic and personalized push messaging. A back-end dashboard was also developed to collect patients’ vital signs for remote monitoring and continuity of care. To date, 400 patients have been enrolled into the system, amounting to 2822 hospital bed–days saved. ConclusionsThe rapid development and implementation of DrCovid+ allowed for timely clinical care management for patients with COVID-19. It facilitated early patient hospital discharge and continuity of care while addressing issues relating to data security and labor-, time-, and cost-effectiveness. The use case for DrCovid+ may be extended to other medical conditions to advance patient care and empowerment within the community, thereby meeting existing and rising population health challenges.

PurposeThe 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.MethodsFirst, 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.ResultsOur 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.ConclusionDR-COVID is a clinically effective NLP-based conversational AI chatbot, and a promising solution for healthcare delivery in the pandemic era.

Federated learning (FL) allows a number of parties collectively train models without revealing private datasets. There is a possibility of extracting personal or confidential data from the shared models even-though sharing of raw data is prevented by federated learning. Secure Multi Party Computation (MPC) is leveraged to aggregate the locally-trained models in a privacy preserving manner. However, it results in high communication cost and poor scalability in a decentralized environment. We design a novel communication-efficient MPC enabled federated learning called CE-Fed. In particular, the proposed CE-Fed is a hierarchical mechanism which forms model aggregation committee with a small number of members and aggregates the global model only among committee members, instead of all participants. We develop a prototype and demonstrate the effectiveness of our mechanism with different datasets. Our proposed CE-Fed achieves high accuracy, communication efficiency and scalability without compromising privacy.

Chest X-rays (CXRs) are essential in the preliminary radiographic assessment of patients affected by COVID-19. Junior residents, as the first point-of-contact in the diagnostic process, are expected to interpret these CXRs accurately. We aimed to assess the effectiveness of a deep neural network in distinguishing COVID-19 from other types of pneumonia, and to determine its potential contribution to improving the diagnostic precision of less experienced residents. A total of 5051 CXRs were utilized to develop and assess an artificial intelligence (AI) model capable of performing three-class classification, namely non-pneumonia, non-COVID-19 pneumonia, and COVID-19 pneumonia. Additionally, an external dataset comprising 500 distinct CXRs was examined by three junior residents with differing levels of training. The CXRs were evaluated both with and without AI assistance. The AI model demonstrated impressive performance, with an Area under the ROC Curve (AUC) of 0.9518 on the internal test set and 0.8594 on the external test set, which improves the AUC score of the current state-of-the-art algorithms by 1.25% and 4.26%, respectively. When assisted by the AI model, the performance of the junior residents improved in a manner that was inversely proportional to their level of training. Among the three junior residents, two showed significant improvement with the assistance of AI. This research highlights the novel development of an AI model for three-class CXR classification and its potential to augment junior residents’ diagnostic accuracy, with validation on external data to demonstrate real-world applicability. In practical use, the AI model effectively supported junior residents in interpreting CXRs, boosting their confidence in diagnosis. While the AI model improved junior residents’ performance, a decline in performance was observed on the external test compared to the internal test set. This suggests a domain shift between the patient dataset and the external dataset, highlighting the need for future research on test-time training domain adaptation to address this issue.

This paper studies privacy-preserving weighted federated learning within the secret sharing framework, where individual private data is split into random shares which are distributed among a set of pre-defined computing servers. The contribution of this paper mainly comprises the following four-fold: •In the first fold, the relationship between federated learning (FL) and multi-party computation (MPC) as well as that of secure federated learning (SFL) and secure multi-party computation (SMPC) is investigated. We show that FL is a subset of MPC from the m-ary functionality point of view. Furthermore, if the underlying FL instance privately computes the defined m-ary functionality in the simulation-based framework, then the simulation-based FL solution is an instance of SMPC.•In the second fold, a new notion which we call weighted federated learning (wFL) is introduced and formalized. Then an oracle-aided SMPC for computing wFL is presented and analysed by decoupling the security of FL from that of MPC. Our decoupling formulation of wFL benefits FL developers selecting their best security practices from the state-of-the-art security tools.•In the third-fold, a concrete implementation of wFL leveraging the random splitting technique in the framework of the 3-party computation is presented and analysed. The security of our implementation is guaranteed by the security composition theorem within the secret share framework.•In the fourth-fold, a complement to MASCOT is introduced and formalized in the framework of SPDZ, where a novel solution to the Beaver triple generator is constructed from the standard El Gamal encryption. Our solution is formalized as a three-party computation and a generation of the Beaver triple requires roughly 5 invocations of the El Gamal encryptions. We are able to show that the proposed implementation is secure against honest-but-curious adversary assuming that the underlying El Gamal encryption is semantically secure.

Summary: Background: By 2050, almost 5 billion people globally are projected to have myopia, of whom 20% are likely to have high myopia with clinically significant risk of sight-threatening complications such as myopic macular degeneration. These are diagnoses that typically require specialist assessment or measurement with multiple unconnected pieces of equipment. Artificial intelligence (AI) approaches might be effective for risk stratification and to identify individuals at highest risk of visual loss. However, unresolved challenges for AI medical studies remain, including paucity of transparency, auditability, and traceability. Methods: In this retrospective multicohort study, we developed and tested retinal photograph-based deep learning algorithms for detection of myopic macular degeneration and high myopia, using a total of 226 686 retinal images. First we trained and internally validated the algorithms on datasets from Singapore, and then externally tested them on datasets from China, Taiwan, India, Russia, and the UK. We also compared the performance of the deep learning algorithms against six human experts in the grading of a randomly selected dataset of 400 images from the external datasets. As proof of concept, we used a blockchain-based AI platform to demonstrate the real-world application of secure data transfer, model transfer, and model testing across three sites in Singapore and China. Findings: The deep learning algorithms showed robust diagnostic performance with areas under the receiver operating characteristic curves [AUC] of 0·969 (95% CI 0·959–0·977) or higher for myopic macular degeneration and 0·913 (0·906–0·920) or higher for high myopia across the external testing datasets with available data. In the randomly selected dataset, the deep learning algorithms outperformed all six expert graders in detection of each condition (AUC of 0·978 [0·957–0·994] for myopic macular degeneration and 0·973 [0·941–0·995] for high myopia). We also successfully used blockchain technology for data transfer, model transfer, and model testing between sites and across two countries. Interpretation: Deep learning algorithms can be effective tools for risk stratification and screening of myopic macular degeneration and high myopia among the large global population with myopia. The blockchain platform developed here could potentially serve as a trusted platform for performance testing of future AI models in medicine. Funding: None.

The topology of a supply chain network affects the impacts of disruptions in it. We formulate a network-based measure of the impact of a disruption loss in a supply chain propagating downstream from an originating node. The measure takes into account the loss profile of the originating node, the structure of the supply network, and the resilience of the network components. We obtain an analytical expression for the impact measure under a beta-distributed initial loss (generalizable to any continuous distribution supported on the interval 0,1), under a breakthrough scenario (in which a fraction of the initial production loss reaches a focal company downstream as opposed to containment upstream or at the originating point). Furthermore, we obtain a closed-form solution for a supply chain network with a k-ary tree topology; a numerical study is performed for a scale-free network and a random network. Our proposed approach enables the evaluation of potential losses for a focal company considering its supply chain network structure, which may help the company to plan or redesign a robust and resilient network in response to different types of disruptions.

We conducted in-depth analysis on the use of a popular Chinese social networking and microblogging site, Sina Weibo, to monitor an avian influenza A(H7N9) outbreak in China and to assess the value of social networking sites in the surveillance of disease outbreaks that occur overseas. Two data sets were employed for our analysis: a line listing of confirmed cases obtained from conventional public health information channels and case information from Weibo posts. Our findings showed that the level of activity on Weibo corresponded with the number of new cases reported. In addition, the reporting of new cases on Weibo was significantly faster than those of conventional reporting sites and non-local news media. A qualitative review of the functions of Weibo also revealed that Weibo enabled timely monitoring of other outbreak-relevant information, provided access to additional crowd-sourced epidemiological information and was leveraged by the local government as an interactive platform for risk communication and monitoring public sentiment on the policy response. Our analysis demonstrated the potential for social networking sites to be used by public health agencies to enhance traditional communicable disease surveillance systems for the global surveillance of overseas public health threats. Social networking sites also can be used by governments for calibration of response policies and measures and for risk communication.