Too much of a good thing: A case series of rare yet pertinent causes of hypercalcaemia and acute kidney injury.

Calcium compounds and vitamin D supplements are readily available as over-the-counter preparations. Whilst integral in maintaining calcium homeostasis in certain patients, excess exogenous intake of these preparations can have deleterious effects, particularly in terms of renal function. We look at the cases of two patients, aged 52 and 34, who were referred into hospital with hypercalcaemia and acute kidney injury (AKI). Both individuals reported regular and prolonged self-medication with unregulated over-the-counter supplements containing calcium carbonate and vitamin D, respectively. Prompt investigation and treatment enabled an element of reversibility of the AKI in both the cases, with further improvement in renal function over time. We emphasise the importance of recognising the overuse of exogenous vitamin D supplements and calcium compounds as rare yet treatable causes of AKI associated with hypercalcaemia and discuss how raising public awareness into the risks posed by self-medication of over-the-counter medicines is paramount.

FuseAD: Unsupervised Anomaly Detection in Streaming Sensors Data by Fusing Statistical and Deep Learning Models.

The need for robust unsupervised anomaly detection in streaming data is increasing rapidly in the current era of smart devices, where enormous data are gathered from numerous sensors. These sensors record the internal state of a machine, the external environment, and the interaction of machines with other machines and humans. It is of prime importance to leverage this information in order to minimize downtime of machines, or even avoid downtime completely by constant monitoring. Since each device generates a different type of streaming data, it is normally the case that a specific kind of anomaly detection technique performs better than the others depending on the data type. For some types of data and use-cases, statistical anomaly detection techniques work better, whereas for others, deep learning-based techniques are preferred. In this paper, we present a novel anomaly detection technique, FuseAD, which takes advantage of both statistical and deep-learning-based approaches by fusing them together in a residual fashion. The obtained results show an increase in area under the curve (AUC) as compared to state-of-the-art anomaly detection methods when FuseAD is tested on a publicly available dataset (Yahoo Webscope benchmark). The obtained results advocate that this fusion-based technique can obtain the best of both worlds by combining their strengths and complementing their weaknesses. We also perform an ablation study to quantify the contribution of the individual components in FuseAD, i.e., the statistical ARIMA model as well as the deep-learning-based convolutional neural network (CNN) model.