Lightweight transformers for clinical natural language processing.

Specialised pre-trained language models are becoming more frequent in Natural language Processing (NLP) since they can potentially outperform models trained on generic texts. BioBERT (Sanh et al., Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter.

Exploring the effectiveness of instruction tuning in biomedical language processing.

Large Language Models (LLMs), particularly those similar to ChatGPT, have significantly influenced the field of Natural Language Processing (NLP). While these models excel in general language tasks, their performance in domain-specific downstream tasks such as biomedical and clinical Named Entity Recognition (NER), Relation Extraction (RE), and Medical Natural Language Inference (NLI) is still evolving. In this context, our study investigates the potential of instruction tuning for biomedical language processing, applying this technique to two general LLMs of substantial scale.

Refined matrix completion for spectrum estimation of heart rate variability.

Heart rate variability (HRV) is an important metric in cardiovascular health monitoring. Spectral analysis of HRV provides essential insights into the functioning of the cardiac autonomic nervous system. However, data artefacts could degrade signal quality, potentially leading to unreliable assessments of cardiac activities.

At-admission prediction of mortality and pulmonary embolism in an international cohort of hospitalised patients with COVID-19 using statistical and machine learning methods.

By September 2022, more than 600 million cases of SARS-CoV-2 infection have been reported globally, resulting in over 6.5 million deaths. COVID-19 mortality risk estimators are often, however, developed with small unrepresentative samples and with methodological limitations.

Distance tuneable integral membrane protein containing floating bilayers directed self-assembly.

Model membranes allow for structural and biophysical studies on membrane biochemistry at the molecular level, albeit on systems of reduced complexity which can limit biological accuracy. Floating supported bilayers offer a means of producing planar lipid membrane models not adhered to a surface, which allows for improved accuracy compared to other model membranes. Here we communicate the incorporation of an integral membrane protein complex, the multidomain β-barrel assembly machinery (Bam), into our recently developed self-assembled floating supported bilayers.

Decoding 2.3 million ECGs: interpretable deep learning for advancing cardiovascular diagnosis and mortality risk stratification.

Aims: Electrocardiogram (ECG) is widely considered the primary test for evaluating cardiovascular diseases. However, the use of artificial intelligence (AI) to advance these medical practices and learn new clinical insights from ECGs remains largely unexplored. We hypothesize that AI models with a specific design can provide fine-grained interpretation of ECGs to advance cardiovascular diagnosis, stratify mortality risks, and identify new clinically useful information.

Incorporating polygenic risk into the Leicester Risk Assessment score for 10-year risk prediction of type 2 diabetes.

Aims: We evaluated whether incorporating information on ethnic background and polygenic risk enhanced the Leicester Risk Assessment (LRA) score for predicting 10-year risk of type 2 diabetes.

Methods: The sample included 202,529 UK Biobank participants aged 40-69 years. We computed the LRA score, and developed two new risk scores using training data (80% sample): LRArev, which incorporated additional information on ethnic background, and LRAprs, which incorporated polygenic risk for type 2 diabetes.

Lipid exchange of apolipoprotein A-I amyloidogenic variants in reconstituted high-density lipoprotein with artificial membranes.

High-density lipoproteins (HDLs) are responsible for removing cholesterol from arterial walls, through a process known as reverse cholesterol transport. The main protein in HDL, apolipoprotein A-I (ApoA-I), is essential to this process, and changes in its sequence significantly alter HDL structure and functions. ApoA-I amyloidogenic variants, associated with a particular hereditary degenerative disease, are particularly effective at facilitating cholesterol removal, thus protecting carriers from cardiovascular disease.

AutoNet-Generated Deep Layer-Wise Convex Networks for ECG Classification.

The design of neural networks typically involves trial-and-error, a time-consuming process for obtaining an optimal architecture, even for experienced researchers. Additionally, it is widely accepted that loss functions of deep neural networks are generally non-convex with respect to the parameters to be optimised. We propose the Layer-wise Convex Theorem to ensure that the loss is convex with respect to the parameters of a given layer, achieved by constraining each layer to be an overdetermined system of non-linear equations.

An octameric PqiC toroid stabilises the outer-membrane interaction of the PqiABC transport system.

The E. coli Paraquat Inducible (Pqi) Pathway is a putative Gram-negative phospholipid transport system. The pathway comprises three components: an integral inner membrane protein (PqiA), a periplasmic spanning MCE family protein (PqiB) and an outer membrane lipoprotein (PqiC).

Assessing the importance of primary care diagnoses in the UK Biobank.

The UK Biobank has made general practitioner (GP) data (censoring date 2016-2017) available for approximately 45% of the cohort, whilst hospital inpatient and death registry (referred to as "HES/Death") data are available cohort-wide through 2018-2022 depending on whether the data comes from England, Wales or Scotland. We assessed the importance of case ascertainment via different data sources in UKB for three diseases that are usually first diagnosed in primary care: Parkinson's disease (PD), type 2 diabetes (T2D), and all-cause dementia. Including GP data at least doubled the number of incident cases in the subset of the cohort with primary care data (e.

A medical multimodal large language model for future pandemics.

Deep neural networks have been integrated into the whole clinical decision procedure which can improve the efficiency of diagnosis and alleviate the heavy workload of physicians. Since most neural networks are supervised, their performance heavily depends on the volume and quality of available labels. However, few such labels exist for rare diseases (e.

Kidney function, albuminuria, and their modification by genetic factors and risk of incident dementia in UK Biobank.

Background: Associations between kidney function and dementia risk are inconclusive. Chronic kidney disease (CKD) severity is determined by levels of both estimated glomerular filtration rate (eGFR) and the urine albumin to creatinine ratio (ACR). However, whether there is a graded increase in dementia risk for worse eGFR in each ACR category is unclear.

Independent external validation of the QRISK3 cardiovascular disease risk prediction model using UK Biobank.

Objective: To externally evaluate the performance of QRISK3 for predicting 10 year risk of cardiovascular disease (CVD) in the UK Biobank cohort.

Methods: We used data from the UK Biobank, a large-scale prospective cohort study of 403 370 participants aged 40-69 years recruited between 2006 and 2010 in the UK. We included participants with no previous history of CVD or statin treatment and defined the outcome to be the first occurrence of coronary heart disease, ischaemic stroke or transient ischaemic attack, derived from linked hospital inpatient records and death registrations.

Combining machine learning with Cox models to identify predictors for incident post-menopausal breast cancer in the UK Biobank.

We aimed to identify potential novel predictors for breast cancer among post-menopausal women, with pre-specified interest in the role of polygenic risk scores (PRS) for risk prediction. We utilised an analysis pipeline where machine learning was used for feature selection, prior to risk prediction by classical statistical models. An "extreme gradient boosting" (XGBoost) machine with Shapley feature-importance measures were used for feature selection among [Formula: see text] 1.

Creation of distinctive Bax-lipid complexes at mitochondrial membrane surfaces drives pore formation to initiate apoptosis.

Apotosis is an essential process tightly regulated by the Bcl-2 protein family where proapoptotic Bax triggers cell death by perforating the mitochondrial outer membrane. Although intensively studied, the molecular mechanism by which these proteins create apoptotic pores remains elusive. Here, we show that Bax creates pores by extracting lipids from outer mitochondrial membrane mimics by formation of Bax/lipid clusters that are deposited on the membrane surface.

Fully Aqueous Self-Assembly of a Gold-Nanoparticle-Based Pathogen Sensor.

Surface plasmon resonance (SPR) is a very sensitive measure of biomolecular interactions but is generally too expensive for routine analysis of clinical samples. Here we demonstrate the simplified formation of virus-detecting gold nanoparticle (AuNP) assemblies on glass using only aqueous buffers at room temperature. The AuNP assembled on silanized glass and displayed a distinctive absorbance peak due to the localized SPR (LSPR) response of the AuNPs.

Polygenic Risk of Prediabetes, Undiagnosed Diabetes, and Incident Type 2 Diabetes Stratified by Diabetes Risk Factors.

Context: Early diagnosis of type 2 diabetes is crucial to reduce severe comorbidities and complications. Current screening recommendations for type 2 diabetes include traditional risk factors, primarily body mass index (BMI) and family history, however genetics also plays a key role in type 2 diabetes risk. It is important to understand whether genetic predisposition to type 2 diabetes modifies the effect of these traditional factors on type 2 diabetes risk.

Suspended phospholipid bilayers: A new biological membrane mimetic.

Hypothesis: The attractive interaction between a cationic surfactant monolayer at the air-water interface and vesicles, incorporating anionic lipids, is sufficient to drive the adsorption and deformation of the vesicles. Osmotic rupture of the vesicles produces a continuous lipid bilayer beneath the monolayer.

Experimental: Specular neutron reflectivity has been measured from the surface of a purpose-built laminar flow trough, which allows for rapid adsorption of vesicles, the changes in salt concentration required for osmotic rupture of the adsorbed vesicles into a bilayer, and for neutron contrast variation of the sub-phase without disturbing the monolayer.

Incidence of fractures in people with intellectual disabilities over the life course: a retrospective matched cohort study.

Background: Current osteoporosis guidelines do not identify individuals with intellectual disabilities (ID) as at risk of fracture, potentially missing opportunities for prevention. We aimed to assess the incidence of fractures in people with ID over the life course.

Methods: Descriptive analysis of open cohort study using anonymised electronic health records from the UK Clinical Practice Research Datalink, linked to the Hospital Episode Statistics database (Jan 1, 1998-Dec 31, 2017).

Assessing agreement between different polygenic risk scores in the UK Biobank.

Polygenic risk scores (PRS) are proposed for use in clinical and research settings for risk stratification. However, there are limited investigations on how different PRS diverge from each other in risk prediction of individuals. We compared two recently published PRS for each of three conditions, breast cancer, hypertension and dementia, to assess the stability of using these algorithms for risk prediction in a single large population.