Concerned with predicting equipment failures, predictive maintenance has a high impact both at a technical and at a financial level. Most modern equipments have logging systems that allow us to collect a diversity of data regarding their operation and health. Using data mining models for anomaly and novelty detection enables us to explore those datasets, building predictive systems that can detect and issue an alert when a failure starts evolving, avoiding the unknown development up to breakdown. In the present case, we use a failure detection system to predict train door breakdowns before they happen using data from their logging system. We use sensor data from pneumatic valves that control the open and close cycles of a door. Still, the failure of a cycle does not necessarily indicates a breakdown. A cycle might fail due to user interaction. The goal of this study is to detect structural failures in the automatic train door system, not when there is a cycle failure, but when there are sequences of cycle failures. We study three methods for such structural failure detection: outlier detection, anomaly detection and novelty detection, using different windowing strategies. We propose a two-stage approach, where the output of a point-anomaly algorithm is post-processed by a low-pass filter to obtain a subsequence-anomaly detection. The main result of the two-level architecture is a strong impact in the false alarm rate.

Diabetic kidney disease (DKD) is one of the most prevalent comorbidities of diabetes mellitus and the leading cause of the end‐stage renal disease (ESRD). DKD results from chronic exposure to hyperglycemia, leading to progressive alterations in kidney structure and function. The early development of DKD is clinically silent and when albuminuria is detected the lesions are often at advanced stages, leading to rapid kidney function decline towards ESRD. DKD progression can be arrested or substantially delayed if detected and addressed at early stages. A major limitation of current methods is the absence of albuminuria in non‐albuminuric phenotypes of diabetic nephropathy, which becomes increasingly prevalent and lacks focused therapy. Metabolomics is an ever‐evolving omics technology that enables the study of metabolites, downstream products of every biochemical event that occurs in an organism. Metabolomics disclosures complex metabolic networks and provide knowledge of the very foundation of several physiological or pathophysiological processes, ultimately leading to the identification of diseases' unique metabolic signatures. In this sense, metabolomics is a promising tool not only for the diagnosis but also for the identification of pre‐disease states which would confer a rapid and personalized clinical practice. Herein, the use of metabolomics as a tool to identify the DKD metabolic signature of tubule interstitial lesions to diagnose or predict the time‐course of DKD will be discussed. In addition, the proficiency and limitations of the currently available high‐throughput metabolomic techniques will be discussed.

In the last few years, many works have addressed Predictive Maintenance (PdM) by the use of Machine Learning (ML) and Deep Learning (DL) solutions, especially the latter. The monitoring and logging of industrial equipment events, like temporal behavior and fault events—anomaly detection in time-series—can be obtained from records generated by sensors installed in different parts of an industrial plant. However, such progress is incipient because we still have many challenges, and the performance of applications depends on the appropriate choice of the method. This article presents a survey of existing ML and DL techniques for handling PdM in the railway industry. This survey discusses the main approaches for this specific application within a taxonomy defined by the type of task, employed methods, metrics of evaluation, the specific equipment or process, and datasets. Lastly, we conclude and outline some suggestions for future research.