A thorough understanding of the pros and cons of the various study designs is critical to correct interpretation of their results. Retrospective studies are an important tool to study rare diseases, manifestations and outcomes. Findings of these studies can form the basis on which prospective studies are planned. Retrospective studies however have several limitations owing to their design. Since they depend on review of charts that were originally not designed to collect data for research, some information is bound to be missing. Selection and recall biases also affect the results and reasons for differences in treatment between patients and lost follow ups can often not be ascertained and may lead to bias. Readers need to critically evaluate the methods and carefully interpret the results of retrospective studies before they put them to practice. Researchers should avoid over generalisation of results and be cautious in claiming cause-effect relationship in retrospective studies.

Sequential data is being generated at an unprecedented pace in various forms, including text and genomic data. This creates the need for efficient compression mechanisms to enable better storage, transmission and processing of such data. To solve this problem, many of the existing compressors attempt to learn models for the data and perform predictionbased compression. Since neural networks are known as universal function approximators with the capability to learn arbitrarily complex mappings, and in practice show excellent performance in prediction tasks, we explore and devise methods to compress sequential data using neural network predictors. We combine recurrent neural network predictors with an arithmetic coder and losslessly compress a variety of synthetic, text and genomic datasets. The proposed compressor outperforms Gzip on the real datasets and achieves near-optimal compression for the synthetic datasets. The results also help understand why and where neural networks are good alternatives for traditional finite context models.

Glottal Closure Instants (GCIs) correspond to the temporal locations of significant excitation to the vocal tract occurring during the production of voiced speech. GCI detection from speech signals is a well-studied problem given its importance in speech processing. Most of the existing approaches for GCI detection adopt a two-stage approach (i) Transformation of speech signal into a representative signal where GCIs are localized better, (ii) extraction of GCIs using the representative signal obtained in first stage. The former stage is accomplished using signal processing techniques based on the principles of speech production and the latter with heuristic-algorithms such as dynamicprogramming and peak-picking. These methods are thus taskspecific and rely on the methods used for representative signal extraction. However in this paper, we formulate the GCI detection problem from a representation learning perspective where appropriate representation is implicitly learned from the rawspeech data samples. Specifically, GCI detection is cast as a supervised multi-task learning problem solved using a deep convolutional neural network jointly optimizing a classification and regression cost. The learning capability is demonstrated with several experiments on standard datasets. The results compare well with the state-of-the-art algorithms while performing better in the case of presence of real-world non-stationary noise.

Patient and public involvement Patients and/or the public were not involved in the design, or conduct, or reporting, or dissemination plans of this research.

Table 1 Demographics and clinical characteristics of patients with SLE with confirmed or suspected COVID-19 COVID-19-like clinical picture (group A)* Contact with patient with COVID-19 (group B)*