Anemia is a global public health problem with major consequences for human health. About a quarter of the world population shows a hemoglobin concentration that is below the recommended thresholds. Non-invasive methods for monitoring and identifying potential risk of anemia and smartphone-based devices to perform this task are promising in addressing this pathology. We have considered some well-known studies carried out on this topic since the main purpose of this work was not to produce a review. The first group of papers describes the approaches for the clinical evaluation of anemia focused on different human exposed tissues, while we used a second group to overview some technologies, basic methods, and principles of operation of some devices and highlight some technical problems. Results extracted from the second group of papers examined were aggregated in two comparison tables. A growing interest in this topic is demonstrated by the increasing number of papers published recently. We believe we have identified several critical issues in the published studies, including those published by us. Just as an example, in many papers the dataset used is not described. With this paper we wish to open a discussion on these issues. Few papers have been sufficient to highlight differences in the experimental conditions and this makes the comparison of the results difficult. Differences are also found in the identification of the regions of interest in the tissue, descriptions of the datasets, and other boundary conditions. These critical issues are discussed together with open problems and common mistakes that probably we are making. We propose the definition of a road-map and a common agenda for research on this topic. In this sense, we want to highlight here some issues that seem worthy of common discussion and the subject of synergistic agreements. This paper, and in particular, the discussion could be the starting point for an open debate about the dissemination of our experiments and pave the way for further updates and improvements of what we have outlined.

The joint exploitation of data related to epidemiological, mobility, and restriction aspects of COVID-19 with machine learning algorithms can support the development of predictive models that can be used to forecast new positive cases and study the impact of more or less severe restrictions. In this work, we integrate heterogeneous data from several sources and solve a multivariate time series forecasting task, specifically targeting the Italian case at both national and regional levels, during the first three waves of the pandemic. The goal is to build a robust predictive model to predict the number of new cases over a given time horizon so that any restrictive actions can be better planned. In addition, we perform a what-if analysis based on the best-identified predictive models to evaluate the impact of specific restrictions on the trend of positive cases. Our focus on the first three waves is motivated by the fact that it represents a typical emergency scenario (when no stable cure or vaccine is available) that may occur when a new pandemic spreads. Our experimental results prove that exploiting the considered heterogeneous data leads to accurate predictive models, reaching a WAPE of 5.75% at the national level. Furthermore, in the subsequent what-if analysis, we observed that strong all-in-one initiatives, such as total lockdowns, may not be adequate, while more specific and targeted solutions should be adopted. The developed models can help policy and decision-makers better plan intervention strategies and retrospectively analyze the effects of the decisions made at different scales. Graphical abstract Joint exploitation of data on epidemiological, mobility, and restriction aspects of COVID-19 with machine learning algorithms to learn predictive models to forecast new positive cases.