Search

Chronic liver disease (CLD) is an ignored epidemic. Premature mortality is considerable and in the United Kingdom (UK) liver disease is in the top three for inequitable healthcare alongside heart and respiratory disease. Fifty percentage of patients with CLD are first diagnosed with cirrhosis after an emergency presentation translating to poorer patient outcomes. Traditional models of care have been based in secondary care when the need is at community level. Investigating patients for disease based on their risk factors at a population level in the community will identify its presence early when there is potential reversibility. Innovation is needed in three broad areas to improve clinical care in this area: better access to diagnostics within the community, integrating diagnostics across primary and secondary care and utilizing digital healthcare to enhance patient care. In this article, we describe how the Integrated Diagnostics for Early Detection of Liver Disease (ID-LIVER) project, funded by UK Research and Innovation, is developing solutions in Greater Manchester to approach the issue of diagnosis of liver disease at a population level. The ambition is to build on innovative pathways previously established in Nottingham by bringing together NHS organizations, academic partners and commercial organizations. The motivation is to co-create and implement a commercial solution that integrates multimodal diagnostics via cutting edge data science to drive growth and disrupt the currently inadequate model. The ambitious vision is for this to be widely adopted for early diagnosis and stratification of liver disease at a population level within the NHS.

Introduction The COVID-19 pandemic has led to over 100 million cases worldwide. The UK has had over 4 million cases, 400 000 hospital admissions and 100 000 deaths. Many patients with COVID-19 suffer long-term symptoms, predominantly breathlessness and fatigue whether hospitalised or not. Early data suggest potentially severe long-term consequence of COVID-19 is development of long COVID-19-related interstitial lung disease (LC-ILD).Methods and analysis The UK Interstitial Lung Disease Consortium (UKILD) will undertake longitudinal observational studies of patients with suspected ILD following COVID-19. The primary objective is to determine ILD prevalence at 12 months following infection and whether clinically severe infection correlates with severity of ILD. Secondary objectives will determine the clinical, genetic, epigenetic and biochemical factors that determine the trajectory of recovery or progression of ILD. Data will be obtained through linkage to the Post-Hospitalisation COVID platform study and community studies. Additional substudies will conduct deep phenotyping. The Xenon MRI investigation of Alveolar dysfunction Substudy will conduct longitudinal xenon alveolar gas transfer and proton perfusion MRI. The POST COVID-19 interstitial lung DiseasE substudy will conduct clinically indicated bronchoalveolar lavage with matched whole blood sampling. Assessments include exploratory single cell RNA and lung microbiomics analysis, gene expression and epigenetic assessment.Ethics and dissemination All contributing studies have been granted appropriate ethical approvals. Results from this study will be disseminated through peer-reviewed journals.Conclusion This study will ensure the extent and consequences of LC-ILD are established and enable strategies to mitigate progression of LC-ILD.

Additional file 1 Appendices.

Deep learning (DL) has proven to be very effective for image recognition tasks, with a large body of research on various model architectures for object classification. Straight-forward application of DL to side-channel analysis (SCA) has already shown promising success, with experimentation on open-source variable key datasets showing that secret keys can be revealed with 100s traces even in the presence of countermeasures. This paper aims to further improve the application of DL for SCA, by enhancing the power of DL when targeting the secret key of cryptographic algorithms when protected with SCA countermeasures. We propose a new model, CNN-based model with Plaintext feature extension (CNNP) together with multiple convolutional filter kernel sizes and structures with deeper and narrower neural networks, which has empirically proven its effectiveness by outperforming reference profiling attack methods such as template attacks (TAs), convolutional neural networks (CNNs) and multilayer perceptron (MLP) models. Our model generates state-of-the art results when attacking the ASCAD variable-key database, which has a restricted number of training traces per key, recovering the key within 40 attack traces in comparison with order of 100s traces required by straightforward machine learning (ML) application. During the profiling stage an attacker needs no additional knowledge on the implementation, such as the masking scheme or random mask values, only the ability to record the power consumption or electromagnetic field traces, plaintext/ciphertext and the key. Additionally, no heuristic pre-processing is required in order to break the high-order masking countermeasures of the target implementation., IACR Transactions on Cryptographic Hardware and Embedded Systems, Volume 2020, Issue 4