Domain-driven data mining of health care data poses unique challenges. The aim of this paper is to explore the advantages and the challenges of a ‘domain-led approach’ versus a data-driven approach to a k-means clustering experiment. For the purpose of this experiment, clinical experts in heart failure selected variables to be used during the k-means clustering, whilst during the ‘data-driven approach’ feature selection was performed by applying principal component analysis to the multidimensional dataset. Six out of seven features selected by physicians were amongst 26 features that contributed most to the significant principal components within the k-means algorithm. The data-driven approach showed advantage over the domain-led approach for feature selection by removing the risk of bias that can be introduced by domain experts. Whilst the ‘domain-led approach’ may potentially prohibit knowledge discovery that can be hidden behind variables not routinely taken into consideration as clinically important features, the domain knowledge played an important role at the interpretation stage of the clustering experiment providing insight into the context and preventing far fetched conclusions. The “data-driven approach” was accurate in identifying clusters with distinct features at the physiological level. To promote the domain-led data mining approach, as a result of this experiment we developed a practical checklist guiding how to enable the integration of the domain knowledge into the data mining project.

This paper presents a systematic literature review with respect to application of data science and machine learning (ML) to heart failure (HF) datasets with the intention of generating both a synthesis of relevant findings and a critical evaluation of approaches, applicability and accuracy in order to inform future work within this field. This paper has a particular intention to consider ways in which the low uptake of ML techniques within clinical practice could be resolved. Literature searches were performed on Scopus (2014-2021), ProQuest and Ovid MEDLINE databases (2014-2021). Search terms included ‘heart failure’ or ‘cardiomyopathy’ and ‘machine learning’, ‘data analytics’, ‘data mining’ or ‘data science’. 81 out of 1688 articles were included in the review. The majority of studies were retrospective cohort studies. The median size of the patient cohort across all studies was 1944 (min 46, max 93260). The largest patient samples were used in readmission prediction models with the median sample size of 5676 (min. 380, max. 93260). Machine learning methods focused on common HF problems: detection of HF from available dataset, prediction of hospital readmission following index hospitalization, mortality prediction, classification and clustering of HF cohorts into subgroups with distinctive features and response to HF treatment. The most common ML methods used were logistic regression, decision trees, random forest and support vector machines. Information on validation of models was scarce. Based on the authors’ affiliations, there was a median 3:1 ratio between IT specialists and clinicians. Over half of studies were co-authored by a collaboration of medical and IT specialists. Approximately 25% of papers were authored solely by IT specialists who did not seek clinical input in data interpretation. The application of ML to datasets, in particular clustering methods, enabled the development of classification models assisting in testing the outcomes of patients with HF. There is, however, a tendency to over-claim the potential usefulness of ML models for clinical practice. The next body of work that is required for this research discipline is the design of randomised controlled trials (RCTs) with the use of ML in an intervention arm in order to prospectively validate these algorithms for real-world clinical utility.

Nanomechanical sensors, due to their small size and high sensitivity to the environment, hold significant promise for various sensing applications. These sensors enable rapid, highly sensitive, and selective detection of biological and biochemical entities as well as mass spectrometry by utilizing the frequency shift of nanomechanical resonators. Nanomechanical systems have been employed to measure the mass of cells and biomolecules and study the fundamentals of surface science such as phase transitions and diffusion. Here, we develop a methodology using both experimental measurements and numerical simulations to explore the characteristics of nanomechanical resonators when the detection entities are absorbed on the cantilever surface and quantify the mass, density, and Young's modulus of adsorbed entities. Moreover, based on this proposed concept, we present an experimental method for measuring the mass of molecules and living biological entities in their physiological environment. This approach could find applications in predicting the behavior of bionanoelectromechanical resonators functionalized with biological capture molecules, as well as in label-free, nonfunctionalized micro/nanoscale biosensing and mass spectrometry of living bioentities.

The coronavirus (COVID-19) outbreak started in December 2019 and rapidly spread around the world affecting millions of people. With the growth of infection rate, many countries adopted different policies to control the spread of the disease. The UK implemented strict rules instructing individuals to stay at home except in some special circumstances starting from 23 March 2020. Accordingly, this study focuses on sensitivity analysis of transmissibility of the infection as the effects of removing restrictions, for example by returning different occupational groups to their normal working environment and its effect on the reproduction number in the UK. For this reason, available social contact matrices are adopted for the population of UK to account for the average number of contacts. Different scenarios are then considered to analyse the variability of total contacts on the reproduction number in the UK as a whole and each of its four nations. Our data-driven retrospective analysis shows that if more than 38.5% of UK working-age population return to their normal working environment, the reproduction number in the UK is expected to be higher than 1. However, analysis of each nation, separately, shows that local reproduction number in each nation may be different and requires more adequate analysis. Accordingly, we believe that using statistical methods and historical data can provide good estimation of local transmissibility and reproduction number in any region. As a consequence of this analysis, efforts to reduce the restrictions should be implemented locally via different control policies. It is important that these policies consider the social contacts, population density, and the occupational groups that are specific to each region.

Climate change and population growth have influenced social and physical water scarcity in many regions. Accordingly, the future performance of water storage reservoirs, as one of the fundamental elements in the water resource management, are anticipated to be affected by climate change. This study reports on a framework that can model Reliability-Resiliency-Vulnerability (RRV) measures of water reservoirs in the context of climate change. The framework first develops a hydrological model of a reservoir system using its historical data. The model is then optimised to minimise the water deficit and flooding around the catchment area of the reservoir. The resulting optimal policies are simulated back to the model considering the GCMs. Finally, RRV indices are calculated. RRV indices are effective measures for defining the performance of reservoir systems. Reliability is defined as the probability of the failure of the system, Resiliency is defined as the time needed for the system to go back to its satisfactory state once it entered the failure state, and Vulnerability is defined as the “magnitude of the failure” of a system. The proposed framework has been applied to a reservoir system located in the south-west of Iran on the Dez river. The results show climate change may increase the reliability and resiliency of the system under study while increasing its vulnerability. Therefore, the output of this framework can also provide supplementary information to authorities and decision-makers to inform future water management and planning policies.