Macrophages play a central role in orchestrating immune responses to foreign materials, which are often responsible for the failure of implanted medical devices. Material topography is known to influence macrophage attachment and phenotype, providing opportunities for the rational design of “immune‐instructive” topographies to modulate macrophage function and thus foreign body responses to biomaterials. However, no generalizable understanding of the inter‐relationship between topography and cell response exists. A high throughput screening approach is therefore utilized to investigate the relationship between topography and human monocyte–derived macrophage attachment and phenotype, using a diverse library of 2176 micropatterns generated by an algorithm. This reveals that micropillars 5–10 µm in diameter play a dominant role in driving macrophage attachment compared to the many other topographies screened, an observation that aligns with studies of the interaction of macrophages with particles. Combining the pillar size with the micropillar density is found to be key in modulation of cell phenotype from pro to anti‐inflammatory states. Machine learning is used to successfully build a model that correlates cell attachment and phenotype with a selection of descriptors, illustrating that materials can potentially be designed to modulate inflammatory responses for future applications in the fight against foreign body rejection of medical devices.

Deep learning has been employed to prognostic and health management of automotive and aerospace with promising results. Literature in this area has revealed that most contributions regarding deep learning is largely focused on the model’s architecture. However, contributions regarding improvement of different aspects in deep learning, such as custom loss function for prognostic and health management are scarce. There is therefore an opportunity to improve upon the effectiveness of deep learning for the system’s prognostics and diagnostics without modifying the models’ architecture. To address this gap, the use of two different dynamically weighted loss functions, a newly proposed weighting mechanism and a focal loss function for prognostics and diagnostics task are investigated. A dynamically weighted loss function is expected to modify the learning process by augmenting the loss function with a weight value corresponding to the learning error of each data instance. The objective is to force deep learning models to focus on those instances where larger learning errors occur in order to improve their performance. The two loss functions used are evaluated using four popular deep learning architectures, namely, deep feedforward neural network, one-dimensional convolutional neural network, bidirectional gated recurrent unit and bidirectional long short-term memory on the commercial modular aero-propulsion system simulation data from NASA and air pressure system failure data for Scania trucks. Experimental results show that dynamically-weighted loss functions helps us achieve significant improvement for remaining useful life prediction and fault detection rate over non-weighted loss function predictions.

There is great potential to be explored regarding the use of agent-based modelling and simulation as an alternative paradigm to investigate early-stage cancer interactions with the immune system. It does not suffer from some limitations of ordinary differential equation models, such as the lack of stochasticity, representation of individual behaviours rather than aggregates and individual memory. In this paper we investigate the potential contribution of agent-based modelling and simulation when contrasted with stochastic versions of ODE models using early-stage cancer examples. We seek answers to the following questions: (1) Does this new stochastic formulation produce similar results to the agent-based version? (2) Can these methods be used interchangeably? (3) Do agent-based models outcomes reveal any benefit when compared to the Gillespie results? To answer these research questions we investigate three well-established mathematical models describing interactions between tumour cells and immune elements. These case studies were re-conceptualised under an agent-based perspective and also converted to the Gillespie algorithm formulation. Our interest in this work, therefore, is to establish a methodological discussion regarding the usability of different simulation approaches, rather than provide further biological insights into the investigated case studies. Our results show that it is possible to obtain equivalent models that implement the same mechanisms; however, the incapacity of the Gillespie algorithm to retain individual memory of past events affects the similarity of some results. Furthermore, the emergent behaviour of ABMS produces extra patters of behaviour in the system, which was not obtained by the Gillespie algorithm.

We aimed to explore university students’ perceptions and experiences of SARS-CoV-2 mass asymptomatic testing, social distancing and self-isolation, during the COVID-19 pandemic. This qualitative study comprised of four rapid online focus groups conducted at a higher education institution in England, during high alert (tier 2) national COVID-19 restrictions. Participants were purposively sampled university students (n = 25) representing a range of gender, age, living circumstances (on/off campus), and SARS-CoV-2 testing/self-isolation experiences. Data were analysed using an inductive thematic approach. Six themes with 16 sub-themes emerged from the analysis of the qualitative data: ‘Term-time Experiences’, ‘Risk Perception and Worry’, ‘Engagement in Protective Behaviours’, ‘Openness to Testing’, ‘Barriers to Testing’ and ‘General Wellbeing’. Students described feeling safe on campus, believed most of their peers are adherent to protective behaviours and were positive towards asymptomatic testing in university settings. University communications about COVID-19 testing and social behaviours need to be timely and presented in a more inclusive way to reach groups of students who currently feel marginalised. Barriers to engagement with SARS-CoV-2 testing, social distancing and self-isolation were primarily associated with fear of the mental health impacts of self-isolation, including worry about how they will cope, high anxiety, low mood, guilt relating to impact on others and loneliness. Loneliness in students could be mitigated through increased intra-university communications and a focus on establishment of low COVID-risk social activities to help students build and enhance their social support networks. These findings are particularly pertinent in the context of mass asymptomatic testing programmes being implemented in educational settings and high numbers of students being required to self-isolate. Universities need to determine the support needs of students during self-isolation and prepare for the long-term impacts of the pandemic on student mental health and welfare support services.

When machine learning supports decision-making in safety-critical systems, it is important to verify and understand the reasons why a particular output is produced. Although feature importance calculation approaches assist in interpretation, there is a lack of consensus regarding how features’ importance is quantified, which makes the explanations offered for the outcomes mostly unreliable. A possible solution to address the lack of agreement is to combine the results from multiple feature importance quantifiers to reduce the variance in estimates and to improve the quality of explanations. Our hypothesis is that this leads to more robust and trustworthy explanations of the contribution of each feature to machine learning predictions. To test this hypothesis, we propose an extensible model-agnostic framework divided in four main parts: (i) traditional data pre-processing and preparation for predictive machine learning models, (ii) predictive machine learning, (iii) feature importance quantification, and (iv) feature importance decision fusion using an ensemble strategy. Our approach is tested on synthetic data, where the ground truth is known. We compare different fusion approaches and their results for both training and test sets. We also investigate how different characteristics within the datasets affect the quality of the feature importance ensembles studied. The results show that, overall, our feature importance ensemble framework produces 15% less feature importance errors compared with existing methods. Additionally, the results reveal that different levels of noise in the datasets do not affect the feature importance ensembles’ ability to accurately quantify feature importance, whereas the feature importance quantification error increases with the number of features and number of orthogonal informative features. We also discuss the implications of our findings on the quality of explanations provided to safety-critical systems.