Rule-based space characterization for rumour detection in health

Last decades have witnessed a radical change in the way information spreads. Social networks provide a constantly updated pool of news to the end-users but the absence of systematic control and moderation of the posts easily leads to spread unverified news with an instrumental value and likely to be dangerous, which are referred to as rumours. To tackle this issue various systems for automatic rumour detection among conversations, i.e. an aggregated set of posts, have been recently presented in the literature. However, few efforts have been directed towards rumour detection at the level of single posts (micro-level), which is the challenging scenario that we tackle in this work. Moving at a finer scale is an urgent need since both rumour and non-rumour posts are included in the same conversation. Here the rumour detection issue is addressed presenting a novel feature selection approach, which characterizes the feature space aiming at minimizing samples in unreliable configurations. This approach is compared with other state-of-the-art methods using a pool of different learning algorithms on two health-related Twitter datasets, labelled at the micro-level. Our proposal yields promising results: it outperforms other feature selection approaches with a best accuracy of 96.8% and enhances the performance of our previous work up to 5%. These findings prove the potential of the feature selection method introduced, which gives access to samples distribution in the feature space, providing privileged information for the construction of the classifier decision boundaries. Nonetheless they also bring a step forward the micro-level rumour detection analysis.

AIforCOVID: Predicting the clinical outcomes in patients with COVID-19 applying AI to chest-X-rays. An Italian multicentre study.

Recent epidemiological data report that worldwide more than 53 million people have been infected by SARS-CoV-2, resulting in 1.3 million deaths. The disease has been spreading very rapidly and few months after the identification of the first infected, shortage of hospital resources quickly became a problem. In this work we investigate whether artificial intelligence working with chest X-ray (CXR) scans and clinical data can be used as a possible tool for the early identification of patients at risk of severe outcome, like intensive care or death. Indeed, further to induce lower radiation dose than computed tomography (CT), CXR is a simpler and faster radiological technique, being also more widespread. In this respect, we present three approaches that use features extracted from CXR images, either handcrafted or automatically learnt by convolutional neuronal networks, which are then integrated with the clinical data. As a further contribution, this work introduces a repository that collects data from 820 patients enrolled in six Italian hospitals in spring 2020 during the first COVID-19 emergency. The dataset includes CXR images, several clinical attributes and clinical outcomes. Exhaustive evaluation shows promising performance both in 10-fold and leave-one-centre-out cross-validation, suggesting that clinical data and images have the potential to provide useful information for the management of patients and hospital resources.

Pareto optimization of deep networks for COVID-19 diagnosis from chest X-rays.

The year 2020 was characterized by the COVID-19 pandemic that has caused, by the end of March 2021, more than 2.5 million deaths worldwide. Since the beginning, besides the laboratory test, used as the gold standard, many applications have been applying deep learning algorithms to chest X-ray images to recognize COVID-19 infected patients. In this context, we found out that convolutional neural networks perform well on a single dataset but struggle to generalize to other data sources. To overcome this limitation, we propose a late fusion approach where we combine the outputs of several state-of-the-art CNNs, introducing a novel method that allows us to construct an optimum ensemble determining which and how many base learners should be aggregated. This choice is driven by a two-objective function that maximizes, on a validation set, the accuracy and the diversity of the ensemble itself. A wide set of experiments on several publicly available datasets, accounting for more than 92,000 images, shows that the proposed approach provides average recognition rates up to 93.54% when tested on external datasets.