Clinical studies from WHO have demonstrated that only 50–70% of patients adhere properly to prescribed drug therapy. Such adherence failure can impact therapeutic efficacy for the patients in question and compromises data quality around the population-level efficacy of the drug for the indications targeted. In this study, we applied various ensemble learning and deep learning models to predict medication adherence among patients. Our contribution to this endeavour involves targeting the problem of adherence prediction for a particularly challenging class of patients who self-administer injectable medication at home. Our prediction pipeline, based on event history, comprises a connected sharps bin which aims to help patients better manage their condition and improve outcomes. In other words, the efficiency of interventions can be significantly improved by prioritizing the patients who are most likely to be non-adherent. The collected data comprising a rich event feature set may be exploited for the purposes of predicting the status of the next adherence state for individual patients. This paper reports on how this concept can be realized through an investigation using a wide range of ensemble learning and deep learning models on a real-world dataset collected from such a system. The dataset investigated comprises 342,174 historic injection disposal records collected over the course of more than 5 years. A comprehensive comparison of different models is given in this paper. Moreover, we demonstrate that the selected best performer, long short-term memory (LSTM), generalizes well by deploying it in a true future testing dataset. The proposed end-to-end pipeline is capable of predicting patient failure in adhering to their therapeutic regimen with 77.35 % accuracy (Specificity: 78.28 %, Sensitivity: 76.42%, Precision: 77.87%,F1 score: 0.7714, ROC AUC: 0.8390).

This review updates recent progress in the understanding of the behaviour of polymers at surfaces and interfaces, highlighting examples in the areas of wetting, dewetting, crystallization, and ‘smart’ materials. Recent developments in analysis tools have yielded a large increase in the study of biological systems, and some of these will also be discussed, focussing on areas where surfaces are important. These areas include molecular binding events and protein adsorption as well as the mapping of the surfaces of cells. Important techniques commonly used for the analysis of surfaces and interfaces are discussed separately to aid the understanding of their application.

Direct glycan–glycan interactions are increasingly implicated in survival and pathogenicity of bacteria. Here, we show that they can be exploited by protozoan parasites in their insect hosts. Force spectroscopy revealed that Leishmania promastigotes display a high-affinity biomolecular interaction between their lipophosphoglycan glycocalyx and mimics of N-acetyl-D-galactosamine, commonly expressed on the midguts of a wide range of sand fly vector species. This enabled gut-adhesive nectomonad promastigotes of Leishmania mexicana to efficiently bind to membrane-bound mucin-like, O-linked glycoproteins of the sand fly Lutzomyia longipalpis, an event crucial for parasite survival, and accounts for a permissive mode of binding. Thus, direct interaction between parasite and sand fly midgut glycans are key to permitting vector competence for all forms of leishmaniasis worldwide. In addition, these studies demonstrate the feasibility of interfering with these interactions as transmission-blocking vaccines.

The adhesion between a grafted polyelectrolyte layer (brush) and a gel of an oppositely charged polyelectrolyte has been measured as a function of applied pressure, and the interface has been traced using neutron reflectometry. The interface (in aqueous medium at pH 6) between the (polycationic) brush and the (polyanionic) gel has a limited pressure dependence, with a small amount of deformation of the interface at the brush–gel contact. Brushes with a dry thickness of up to 13 nm exhibit weak adhesion (measured using a mechanical force tester) with an adhesive failure when the gel is detached. Thicker brushes result in the gel exhibiting cohesive failure. Reversing the geometry, whereby a polycationic brush is replaced with a polyanion and the polyanionic gel is replaced with a polycation, reveals that the pH dependence of the adhesion is moderately symmetric about pH 6, but that the maximum force required to separate the polycation gel from the polyanion brush over the range of pH is greater than that for the polycation brush and polyanion gel. The polyanion used is poly(methacrylic acid) (PMAA) and polycations of poly[2-(diethylamino)ethyl methacrylate] (PDEAEMA) and poly[2-(dimethylamino)ethyl methacrylate] (PDMAEMA) were used.

In this paper, we investigate different scenarios of anomaly detection on decentralised Internet of Things (IoT) applications. Specifically, an anomaly detector is devised to detect different types of anomalies for an IoT data management system, based on the decentralised alternating direction method of multipliers (ADMM), which was proposed in our previous work. The anomaly detector only requires limited information from the IoT system, and can be operated using both a mathematical-rule-based approach and the deep learning approach proposed in the paper. Our experimental results show that detection based on mathematical approach is simple to implement, but it also comes with lower detection accuracy ($78.88\%$). In contrast, the deep-learning-enabled approach can easily achieve a higher detection accuracy ($96.28\%$) in the real world working environment.