Search

Climate change presents an unprecedented global challenge, demanding collective action to both mitigate its effects and adapt to its consequences. Soil health and function are profoundly impacted by climate change, particularly evident in the sensitivity of soil microbial respiration to warming, known as Q10. Q10 measures the rate of microbial respiration’s increase with a temperature rise of 10 degrees Celsius, playing a pivotal role in understanding soil carbon dynamics in response to climate change. Leveraging machine learning techniques, particularly explainable artificial intelligence (XAI), offers a promising avenue to analyze complex data and identify biomarkers crucial for developing innovative climate change mitigation strategies. This research aims to evaluate the extent to which chemical, physical, and microbiological soil characteristics are associated with high or low Q10 values, utilizing XAI approaches. The Extra Trees Classifier algorithm was employed, yielding an average accuracy of 0.923±0.009, an average AUCROC of 0.964±0.004, and an average AUCPRC of 0.963±0.006. Additionally, through XAI techniques, we elucidate the significant features contributing to the prediction of Q10 classes. The XAI analysis shows that the temperature sensitivity of soil respiration increases with microbiome variables but decreases with non-microbiome variables beyond a threshold. Our findings underscore the critical role of the soil microbiome in predicting soil Q10 dynamics, providing valuable insights for developing targeted climate change mitigation strategies.

Summary: Autism spectrum disorder (ASD) affects social interaction and communication. Emerging evidence links ASD to gut microbiome alterations, suggesting that microbial composition may play a role in the disorder. This study employs explainable artificial intelligence (XAI) to examine the contributions of individual microbial species to ASD. By using local explanation embeddings and unsupervised clustering, the research identifies distinct ASD subgroups, underscoring the disorder’s heterogeneity. Specific microbial biomarkers associated with ASD are revealed, and the best classifiers achieved an AU-ROC of 0.965 ± 0.005 and an AU-PRC of 0.967 ± 0.008. The findings support the notion that gut microbiome composition varies significantly among individuals with ASD. This work’s broader significance lies in its potential to inform personalized interventions, enhancing precision in ASD management and classification. These insights highlight the importance of individualized microbiome profiles for developing tailored therapeutic strategies for ASD.

Abstract Alzheimer’s disease (AD) is the most common type of dementia with millions of affected patients worldwide. Currently, there is still no cure and AD is often diagnosed long time after onset because there is no clear diagnosis. Thus, it is essential to study the physiology and pathogenesis of AD, investigating the risk factors that could be strongly connected to the disease onset. Despite AD, like other complex diseases, is the result of the combination of several factors, there is emerging agreement that environmental pollution should play a pivotal role in the causes of disease. In this work, we implemented an Artificial Intelligence model to predict AD mortality, expressed as Standardized Mortality Ratio, at Italian provincial level over 5 years. We employed a set of publicly available variables concerning pollution, health, society and economy to feed a Random Forest algorithm. Using methods based on eXplainable Artificial Intelligence (XAI) we found that air pollution (mainly $$O_3$$ O 3 and $$NO_2$$ N O 2 ) contribute the most to AD mortality prediction. These results could help to shed light on the etiology of Alzheimer’s disease and to confirm the urgent need to further investigate the relationship between the environment and the disease.

Abstract Chemical space modelling has great importance in unveiling and visualising latent information, which is critical in predictive toxicology related to drug discovery process. While the use of traditional molecular descriptors and fingerprints may suffer from the so-called curse of dimensionality, complex networks are devoid of the typical drawbacks of coordinate-based representations. Herein, we use chemical space networks (CSNs) to analyse the case of the developmental toxicity (Dev Tox), which remains a challenging endpoint for the difficulty of gathering enough reliable data despite very important for the protection of the maternal and child health. Our study proved that the Dev Tox CSN has a complex non-random organisation and can thus provide a wealth of meaningful information also for predictive purposes. At a phase transition, chemical similarities highlight well-established toxicophores, such as aryl derivatives, mostly neurotoxic hydantoins, barbiturates and amino alcohols, steroids, and volatile organic compounds ether-like chemicals, which are strongly suspected of the Dev Tox onset and can thus be employed as effective alerts for prioritising chemicals before testing.

Respiratory system cancer, encompassing lung, trachea and bronchus cancer, constitute a substantial and evolving public health challenge. Since pollution plays a prominent cause in the development of this disease, identifying which substances are most harmful is fundamental for implementing policies aimed at reducing exposure to these substances. We propose an approach based on explainable artificial intelligence (XAI) based on remote sensing data to identify the factors that most influence the prediction of the standard mortality ratio (SMR) for respiratory system cancer in the Italian provinces using environment and socio-economic data. First of all, we identified 10 clusters of provinces through the study of the SMR variogram. Then, a Random Forest regressor is used for learning a compact representation of data. Finally, we used XAI to identify which features were most important in predicting SMR values. Our machine learning analysis shows that NO, income and O3 are the first three relevant features for the mortality of this type of cancer, and provides a guideline on intervention priorities in reducing risk factors.

Abstract Correlation Plenoptic Imaging (CPI) is a novel volumetric imaging technique that uses two sensors and the spatio-temporal correlations of light to detect both the spatial distribution and the direction of light. This novel approach to plenoptic imaging enables refocusing and 3D imaging with significant enhancement of both resolution and depth of field. However, CPI is generally slower than conventional approaches due to the need to acquire sufficient statistics for measuring correlations with an acceptable signal-to-noise ratio (SNR). We address this issue by implementing a Deep Learning application to improve image quality with undersampled frame statistics. We employ a set of experimental images reconstructed by a standard CPI architecture, at three different sampling ratios, and use it to feed a CNN model pre-trained through the transfer learning paradigm U-Net architecture with VGG-19 net for the encoding part. We find that our model reaches a Structural Similarity (SSIM) index value close to 1 both for the test sample (SSIM = $$0.87 \pm 0.02$$ 0.87 ± 0.02 ) and in 5-fold cross validation (SSIM = $$0.92 \pm 0.07$$ 0.92 ± 0.07 ); the results are also shown to outperform classic denoising methods, in particular for images with lower SNR. The proposed work represents the first application of Artificial Intelligence in the field of CPI and demonstrates its high potential: speeding-up the acquisition by a factor 20 over the fastest CPI so far demonstrated, enabling recording potentially 200 volumetric images per second. The presented results open the way to scanning-free real-time volumetric imaging at video rate, which is expected to achieve a substantial influence in various applications scenarios, from monitoring neuronal activity to machine vision and security.

Abstract Raman spectroscopy shows great potential as a diagnostic tool for thyroid cancer due to its ability to detect biochemical changes during cancer development. This technique is particularly valuable because it is non-invasive and label/dye-free. Compared to molecular tests, Raman spectroscopy analyses can more effectively discriminate malignant features, thus reducing unnecessary surgeries. However, one major hurdle to using Raman spectroscopy as a diagnostic tool is the identification of significant patterns and peaks. In this study, we propose a Machine Learning procedure to discriminate healthy/benign versus malignant nodules that produces interpretable results. We collect Raman spectra obtained from histological samples, select a set of peaks with a data-driven and label independent approach and train the algorithms with the relative prominence of the peaks in the selected set. The performance of the considered models, quantified by area under the Receiver Operating Characteristic curve, exceeds 0.9. To enhance the interpretability of the results, we employ eXplainable Artificial Intelligence and compute the contribution of each feature to the prediction of each sample.

Abstract Dementia is on the rise in the world population and has been defined by the World Health Organization as a global public health priority. In Italy, according to demographic projections, in 2051 there will be 280 elderly people for every 100 young people, with an increase in all age-related chronic diseases, including dementia. Currently the total number of patients with dementia is estimated to be over 1 million (mainly with Alzheimer’s disease (AD) and Parkinson’s disease (PD)). In-depth studies of the etiology and physiology of dementia are complicated due to the complexity of these diseases and their long duration. In this work we present a dataset on mortality rates (in the form of Standardized Mortality Ratios, SMR) for AD e PD in Italy at provincial level over a period of 8 years (2012–2019). Access to long-term, spatially detailed and ready-to-use data could favor both health monitoring and the research of new treatments and new drugs as well as innovative methodologies for early diagnosis of dementia.

Recent years have witnessed an increasing interest in air pollutants and their effects on human health. More generally, it has become evident how human, animal and environmental health are deeply interconnected within a One Health framework. Ground level air monitoring stations are sparse and thus have limited coverage due to high costs. Satellite and reanalysis data represent an alternative with high spatio-temporal resolution. The idea of this work is to build an Artificial Intelligence model for the estimation of surface-level daily concentrations of air pollutants over the entire Italian territory using satellite, climate reanalysis, geographical and social data. As ground truth we use data from the monitoring stations of the Regional Environmental Protection Agency (ARPA) covering the period 2019–2022 at municipal level. The analysis compares different models and applies an Explainable Artificial Intelligence approach to evaluate the role of individual features in the model. The best model reaches an average R2 of 0.84 ± 0.01 and MAE of 5.00 ± 0.01 μg/m3 across all pollutants which compare well with the body of literature. The XAI analysis highlights the pivotal role of satellite and climate reanalysis data. Our work can facilitate One Health surveys and help researchers and policy makers.

Abstract The European Quality of Government Index (EQI) measures the perceived level of government quality by European Union citizens, combining surveys on corruption, impartiality and quality of provided services. It is, thus, an index based on individual subjective evaluations. Understanding the most relevant objective factors affecting the EQI outcomes is important for both evaluators and policy makers, especially in view of the fact that perception of government integrity contributes to determine the level of civic engagement. In our research, we employ methods of Artificial Intelligence and complex systems physics to measure the impact on the perceived government quality of multifaceted variables, describing territorial development and citizen well-being, from an economic, social and environmental viewpoint. Our study, focused on a set of regions in European Union at a subnational scale, leads to identifying the territorial and demographic drivers of citizens’ confidence in government institutions. In particular, we find that the 2021 EQI values are significantly related to two indicators: the first one is the difference between female and male labour participation rates, and the second one is a proxy of wealth and welfare such as the average number of rooms per inhabitant. This result corroborates the idea of a central role played by labour gender equity and housing policies in government confidence building. In particular, the relevance of the former indicator in EQI prediction results from a combination of positive conditions such as equal job opportunities, vital labour market, welfare and availability of income sources, while the role of the latter is possibly amplified by the lockdown policies related to the COVID-19 pandemics. The analysis is based on combining regression, to predict EQI from a set of publicly available indicators, with the eXplainable Artificial Intelligence approach, that quantifies the impact of each indicator on the prediction. Such a procedure does not require any ad-hoc hypotheses on the functional dependence of EQI on the indicators used to predict it. Finally, using network science methods concerning community detection, we investigate how the impact of relevant indicators on EQI prediction changes throughout European regions. Thus, the proposed approach enables to identify the objective factors at the basis of government quality perception by citizens in different territorial contexts, providing the methodological basis for the development of a quantitative tool for policy design.

Measurement(s) Standardized Mortality Ratio Technology Type(s) Public database

Abstract The impacts and threats posed by wildfires are dramatically increasing due to climate change. In recent years, the wildfire community has attempted to estimate wildfire occurrence with machine learning models. However, to fully exploit the potential of these models, it is of paramount importance to make their predictions interpretable and intelligible. This study is a first attempt to provide an eXplainable artificial intelligence (XAI) framework for estimating wildfire occurrence using a Random Forest model with Shapley values for interpretation. Our findings accurately detected regions with a high presence of wildfires (area under the curve 81.3%) and outlined the drivers empowering occurrence, such as the Fire Weather Index and Normalized Difference Vegetation Index. Furthermore, our analysis suggests the presence of anomalous hotspots. In contexts where human and natural spheres constantly intermingle and interact, the XAI framework, suitably integrated into decision support systems, could support forest managers to prevent and mitigate future wildfire disasters and develop strategies for effective fire management, response, recovery, and resilience.

The advent of eXplainable Artificial Intelligence (XAI) has revolutionized the way human experts, especially from non-computational domains, approach artificial intelligence; this is particularly true for clinical applications where the transparency of the results is often compromised by the algorithmic complexity. Here, we investigate how Alzheimer's disease (AD) affects brain connectivity within a cohort of 432 subjects whose T1 brain Magnetic Resonance Imaging data (MRI) were acquired within the Alzheimer's Disease Neuroimaging Initiative (ADNI). In particular, the cohort included 92 patients with AD, 126 normal controls (NC) and 214 subjects with mild cognitive impairment (MCI). We show how graph theory-based models can accurately distinguish these clinical conditions and how Shapley values, borrowed from game theory, can be adopted to make these models intelligible and easy to interpret. Explainability analyses outline the role played by regions like putamen, middle and superior temporal gyrus; from a class-related perspective, it is possible to outline specific regions, such as hippocampus and amygdala for AD and posterior cingulate and precuneus for MCI. The approach is general and could be adopted to outline how brain connectivity affects specific brain regions.

Abstract In clinical practice, several standardized neuropsychological tests have been designed to assess and monitor the neurocognitive status of patients with neurodegenerative diseases such as Alzheimer’s disease. Important research efforts have been devoted so far to the development of multivariate machine learning models that combine the different test indexes to predict the diagnosis and prognosis of cognitive decline with remarkable results. However, less attention has been devoted to the explainability of these models. In this work, we present a robust framework to (i) perform a threefold classification between healthy control subjects, individuals with cognitive impairment, and subjects with dementia using different cognitive indexes and (ii) analyze the variability of the explainability SHAP values associated with the decisions taken by the predictive models. We demonstrate that the SHAP values can accurately characterize how each index affects a patient’s cognitive status. Furthermore, we show that a longitudinal analysis of SHAP values can provide effective information on Alzheimer’s disease progression.

Abstract In this work we use a network-based approach to investigate the complex system of interactions among the 17 Sustainable Development Goals (SDGs), that constitute the structure of the United Nations 2030 Agenda for a sustainable future. We construct a three-layer multiplex, in which SDGs represent nodes, and their connections in each layer are determined by similarity definitions based on conceptualization, communication, and achievement, respectively. In each layer of the multiplex, we investigate the presence of nodes with high centrality, corresponding to strategic SDGs. We then compare the networks to establish whether and to which extent similar patterns emerge. Interestingly, we observe a significant relation between the SDG similarity patterns determined by their achievement and their communication and perception, revealed by social network data. The proposed framework represents an instrument to unveil new and nontrivial aspects of sustainability, laying the foundation of a decision support system to define and implement SDG achievement strategies.

Abstract University rankings are increasingly adopted for academic comparison and success quantification, even to establish performance-based criteria for funding assignment. However, rankings are not neutral tools, and their use frequently overlooks disparities in the starting conditions of institutions. In this research, we detect and measure structural biases that affect in inhomogeneous ways the ranking outcomes of universities from diversified territorial and educational contexts. Moreover, we develop a fairer rating system based on a fully data-driven debiasing strategy that returns an equity-oriented redefinition of the achieved scores. The key idea consists in partitioning universities in similarity groups, determined from multifaceted data using complex network analysis, and referring the performance of each institution to an expectation based on its peers. Significant evidence of territorial biases emerges for official rankings concerning both the OECD and Italian university systems, hence debiasing provides relevant insights suggesting the design of fairer strategies for performance-based funding allocations.

Hepatocellular carcinoma (HCC) is one of the most common cancers worldwide, and the number of cases is constantly increasing. Early and accurate HCC diagnosis is crucial to improving the effectiveness of treatment. The aim of the study is to develop a supervised learning framework based on hierarchical community detection and artificial intelligence in order to classify patients and controls using publicly available microarray data. With our methodology, we identified 20 gene communities that discriminated between healthy and cancerous samples, with an accuracy exceeding 90%. We validated the performance of these communities on an independent dataset, and with two of them, we reached an accuracy exceeding 80%. Then, we focused on two communities, selected because they were enriched with relevant biological functions, and on these we applied an explainable artificial intelligence (XAI) approach to analyze the contribution of each gene to the classification task. In conclusion, the proposed framework provides an effective methodological and quantitative tool helping to find gene communities, which may uncover pivotal mechanisms responsible for HCC and thus discover new biomarkers.

Online reviews have been found very useful in decision-making. It is important to design and implement accurate systems to analyze the reviews and, based on textual information, predict their ratings. Given the different sources, languages and evaluating systems, intelligent systems are needed to use textual and numerical reviews to better understand the evaluation of the tourist experience and derive useful information to improve the offer. This paper aims to present an eXplainable Artificial Intelligence framework that contributes to the discussion on numerical and textual evaluations of the hospitality experience. It combines sentiment analysis and machine learning to accurately model and explain the evaluation of the tourist experience. The main findings are that review ratings should be used with caution and accompanied by a sentiment evaluation and explainability plays a central role in identifying which are the key concepts of positive or negative ratings, providing invaluable intelligence about the tourist experience.

Abstract The identification of factors associated to COVID-19 mortality is important to design effective containment measures and safeguard at-risk categories. In the last year, several investigations have tried to ascertain key features to predict the COVID-19 mortality tolls in relation to country-specific dynamics and population structure. Most studies focused on the first wave of the COVID-19 pandemic observed in the first half of 2020. Numerous studies have reported significant associations between COVID-19 mortality and relevant variables, for instance obesity, healthcare system indicators such as hospital beds density, and bacillus Calmette-Guerin immunization. In this work, we investigated the role of ABO/Rh blood groups at three different stages of the pandemic while accounting for demographic, economic, and health system related confounding factors. Using a machine learning approach, we found that the “B+” blood group frequency is an important factor at all stages of the pandemic, confirming previous findings that blood groups are linked to COVID-19 severity and fatal outcome.

IntroductionDementia is an umbrella term indicating a group of diseases that affect the cognitive sphere. Dementia is not a mere individual health issue, since its interference with the ability to carry out daily activities entails a series of collateral problems, comprising exclusion of patients from civil rights and welfare, unpaid caregiving work, mostly performed by women, and an additional burden on the public healthcare systems. Thus, gender and wealth inequalities (both among individuals and among countries) tend to amplify the social impact of such a disease. Since at present there is no cure for dementia but only drug treatments to slow down its progress and mitigate the symptoms, it is essential to work on prevention and early diagnosis, identifying the risk factors that increase the probability of its onset. The complex and multifactorial etiology of dementia, resulting from an interplay between genetics and environmental factors, can benefit from a multidisciplinary approach that follows the “One Health” guidelines of the World Health Organization.MethodsIn this work, we apply methods of Artificial Intelligence and complex systems physics to investigate the possibility to predict dementia prevalence throughout world countries from a set of variables concerning individual health, food consumption, substance use and abuse, healthcare system efficiency. The analysis uses publicly available indicator values at a country level, referred to a time window of 26 years.ResultsEmploying methods based on eXplainable Artificial Intelligence (XAI) and complex networks, we identify a group of lifestyle factors, mostly concerning nutrition, that contribute the most to dementia incidence prediction.DiscussionThe proposed approach provides a methodological basis to develop quantitative tools for action patterns against such a disease, which involves issues deeply related with sustainable, such as good health and resposible food consumption.

Radiomics is a challenging development area in imaging field that is greatly capturing interest of radiologists and neuroscientists. However, radiomics features show a strong non-biological variability determined by different facilities and imaging protocols, limiting the reproducibility and generalizability of analysis frameworks. Our study aimed to investigate the usefulness of harmonization to reduce site-effects on radiomics features over specific brain regions. We selected T1-weighted magnetic resonance imaging (MRI) by using the MRI dataset Parkinson’s Progression Markers Initiative (PPMI) from different sites with healthy controls (HC) and Parkinson’s disease (PD) patients. First, the investigation of radiomics measure discrepancies were assessed on healthy brain regions-of-interest (ROIs) via a classification pipeline based on LASSO feature selection and support vector machine (SVM) model. Then, a ComBat-based harmonization approach was applied to correct site-effects. Finally, a validation step on PD subjects evaluated diagnostic accuracy before and after harmonization of radiomics data. Results on healthy subjects demonstrated a dependence from site-effects that could be corrected with ComBat harmonization. LASSO regressor after harmonization was unable to select any feature to distinguish controls by site. Moreover, harmonized radiomics features achieved an area under the receiving operating characteristic curve (AUC) of 0.77 (compared to AUC of 0.71 for raw radiomics measures) in distinguish Parkinson’s patients from HC. We found a not-negligible site-effect studying radiomics of HC pre- and post-harmonization of features. Our validation study on PD patients demonstrated a significant influence of non-biological noise source in diagnostic performances. Finally, harmonization of multicenter radiomic data represent a necessary step to make analysis pipelines reliable and replicable for multisite neuroimaging studies.

PSI data are extremely useful for monitoring on-ground displacements. In many cases, clustering algorithms are adopted to highlight the presence of homogeneous patterns; however, clustering algorithms can fail to consider spatial constraints and be poorly specific in revealing patterns at lower scales or possible anomalies. Hence, we proposed a novel framework which combines a spatially-constrained clustering algorithm (SKATER) with a hypothesis testing procedure which evaluates and establishes the presence of significant local spatial correlations, namely the LISA method. The designed workflow ensures the retrieval of homogeneous clusters and a reliable anomaly detection; to validate this workflow, we collected Sentinel-1 time series from the Sibari and Metaponto coastal plains in Italy, ranging from 2015 to 2021. This particular study area is interesting due to the presence of important industrial and agricultural settlements. The proposed workflow effectively outlines the presence of both subsidence and uplifting that deserve to be focused and continuous monitoring, both for environmental and infrastructural purposes.

High throughput sequencing technologies have enabled the study of complex biological aspects at single nucleotide resolution, opening the big data era. The analysis of large volumes of heterogeneous “omic” data, however, requires novel and efficient computational algorithms based on the paradigm of Artificial Intelligence. In the present review, we introduce and describe the most common machine learning methodologies, and lately deep learning, applied to a variety of genomics tasks, trying to emphasize capabilities, strengths and limitations through a simple and intuitive language. We highlight the power of the machine learning approach in handling big data by means of a real life example, and underline how described methods could be relevant in all cases in which large amounts of multimodal genomic data are available.

Abstract Nowadays, world rankings are promoted and used by international agencies, governments and corporations to evaluate country performances in a specific domain, often providing a guideline for decision makers. Although rankings allow a direct and quantitative comparison of countries, sometimes they provide a rather oversimplified representation, in which relevant aspects related to socio-economic development are either not properly considered or still analyzed in silos. In an increasingly data-driven society, a new generation of cutting-edge technologies is breaking data silos, enabling new use of public indicators to generate value for multiple stakeholders. We propose a complex network framework based on publicly available indicators to extract important insight underlying global rankings, thus adding value and significance to knowledge provided by these rankings. This approach enables the unsupervised identification of communities of countries, establishing a more targeted, fair and meaningful criterion to detect similarities. Hence, the performance of states in global rankings can be assessed based on their development level. We believe that these evaluations can be crucial in the interpretation of global rankings, making comparison between countries more significant and useful for citizens and governments and creating ecosystems for new opportunities for development.

University psychological counseling (UPC) is receiving growing attention as a means to promote mental health and academic success among young adults and prevent irregular attendance and dropout. However, thus far, little effort has been directed towards the implementation of services attuned to students' expectations and needs. This work intends to contribute to the existing literature on this topic, by exploring the perceptions of UPC among a population of 39,277 students attending one of the largest universities in the South of Italy. Almost half of the total population correctly identified the UPC target population as university students, and about one third correctly expected personal distress to be the main need that UPC should target. However, a large percentage did not have a clear idea about UPC target needs, activities, and population. When two specific student subsamples were analyzed using a person-centered analysis, namely (i) those who expressed their intention to use the counseling service but had not yet done so and (ii) those who had already used it, the first subsample clustered into two groups, characterized by an "emotional" and a "psychopathological" focus, respectively, while the second subsample clustered into three groups with a "clinical", "socioemotional", and "learning" focus, respectively. This result shows a somewhat more "superficial" and "common" representation of UPC in the first subsample and a more "articulated" and "flexible" vision in the second subsample. Taken together, these findings suggest that UPC services could adopt "student-centered" strategies to both identify and reach wider audiences and specific student subgroups. Recommended strategies include robust communication campaigns to help students develop a differentiated perception of the available and diverse academic services, and the involvement of active students to remove the barriers of embarrassment and shame often linked to the stigma of using mental health services.

A great deal of attention has been devoted to the analysis of particulate matter (PM) concentrations in various scenarios because of their negative effects on human health. Here, we investigate how meteorological conditions can affect PM concentrations in the peculiar case of the district of the city of Lecce in the Apulia region (Southern Italy), which is characterized by the highest tumor rate of the whole region despite the absence of nearby heavy industries. We present a unified machine learning framework which combines air quality and meteorological data, either measured on ground or forecast. Our findings show that the concentrations of PM10, PM2.5, NO2 and CO are significantly associated with the meteorological conditions and suggest that it is possible to predict air quality using either ground weather observations or weather forecasts.

Rankings are a well-established tool to evaluate the performance of actors in different sectors of the economy, and their use is increasing even in the context of the startup ecosystem, both on a regional and on a global scale. Although rankings meet the demand for measurability and comparability, they often provide an oversimplified picture of the status quo, which, in particular, overlooks the variability of the socio-economic conditions in which the quantified results are achieved. In this paper, we describe an approach based on constructing a network of world countries, in which links are determined by mutual similarity in terms of development indicators. Through the instrument of community detection, we perform an unsupervised partition of the considered set of countries, aimed at interpreting their performance in the StartupBlink rankings. We consider both the global ranking and the specific ones (quality, quantity, business). After verifying if community membership is predictive of the success of a country in the considered ranking, we rate country performances in terms of the expectation based on community peers. We are thus able to identify cases in which performance is better than expected, providing a benchmark for countries in similar conditions, and cases in which performance is below the expectation, highlighting the need to strengthen the innovation ecosystem.

The current guidelines recommend the sentinel lymph node biopsy to evaluate the lymph node involvement for breast cancer patients with clinically negative lymph nodes on clinical or radiological examination. Machine learning (ML) models have significantly improved the prediction of lymph nodes status based on clinical features, thus avoiding expensive, time-consuming and invasive procedures. However, the classification of sentinel lymph node status represents a typical example of an unbalanced classification problem. In this work, we developed a ML framework to explore the effects of unbalanced populations on the performance and stability of feature ranking for sentinel lymph node status classification in breast cancer. Our results indicate state-of-the-art AUC (Area under the Receiver Operating Characteristic curve) values on a hold-out set (67%) while providing particularly stable features related to tumor size, histological subtype and estrogen receptor expression, which should therefore be considered as potential biomarkers.

Predicting brain age has become one of the most attractive challenges in computational neuroscience due to the role of the predicted age as an effective biomarker for different brain diseases and conditions. A great variety of machine learning (ML) approaches and deep learning (DL) techniques have been proposed to predict age from brain magnetic resonance imaging scans. If on one hand, DL models could improve performance and reduce model bias compared to other less complex ML methods, on the other hand, they are typically black boxes as do not provide an in-depth understanding of the underlying mechanisms. Explainable Artificial Intelligence (XAI) methods have been recently introduced to provide interpretable decisions of ML and DL algorithms both at local and global level. In this work, we present an explainable DL framework to predict the age of a healthy cohort of subjects from ABIDE I database by using the morphological features extracted from their MRI scans. We embed the two local XAI methods SHAP and LIME to explain the outcomes of the DL models, determine the contribution of each brain morphological descriptor to the final predicted age of each subject and investigate the reliability of the two methods. Our findings indicate that the SHAP method can provide more reliable explanations for the morphological aging mechanisms and be exploited to identify personalized age-related imaging biomarker.

In recent years, several studies have demonstrated that machine learning and deep learning systems can be very useful to accurately predict brain age. In this work, we propose a novel approach based on complex networks using 1016 T1-weighted MRI brain scans (in the age range 7−64years). We introduce a structural connectivity model of the human brain: MRI scans are divided in rectangular boxes and Pearson’s correlation is measured among them in order to obtain a complex network model. Brain connectivity is then characterized through few and easy-to-interpret centrality measures; finally, brain age is predicted by feeding a compact deep neural network. The proposed approach is accurate, robust and computationally efficient, despite the large and heterogeneous dataset used. Age prediction accuracy, in terms of correlation between predicted and actual age r=0.89and Mean Absolute Error MAE =2.19years, compares favorably with results from state-of-the-art approaches. On an independent test set including 262 subjects, whose scans were acquired with different scanners and protocols we found MAE =2.52. The only imaging analysis steps required in the proposed framework are brain extraction and linear registration, hence robust results are obtained with a low computational cost. In addition, the network model provides a novel insight on aging patterns within the brain and specific information about anatomical districts displaying relevant changes with aging.

Morphological changes in the brain over the lifespan have been successfully described by using structural magnetic resonance imaging (MRI) in conjunction with machine learning (ML) algorithms. International challenges and scientific initiatives to share open access imaging datasets also contributed significantly to the advance in brain structure characterization and brain age prediction methods. In this work, we present the results of the predictive model based on deep neural networks (DNN) proposed during the Predictive Analytic Competition 2019 for brain age prediction of 2638 healthy individuals. We used FreeSurfer software to extract some morphological descriptors from the raw MRI scans of the subjects collected from 17 sites. We compared the proposed DNN architecture with other ML algorithms commonly used in the literature (RF, SVR, Lasso). Our results highlight that the DNN models achieved the best performance with MAE = 4.6 on the hold-out test, outperforming the other ML strategies. We also propose a complete ML framework to perform a robust statistical evaluation of feature importance for the clinical interpretability of the results.

A startup ecosystem is a dynamic environment in which several actors, such as investors, venture capitalists, angels, and facilitators, are the protagonists of a complex interplay. Most of these interactions involve the flow of capital whose size and direction help to map the intricate system of relationships. This quantity is also considered a good proxy of economic success. Given the complexity of such systems, it would be more desirable to supplement this information with other informative features, and a natural choice is to adopt mathematical measures. In this work, we will specifically consider network centrality measures, borrowed by network theory. In particular, using the largest publicly available dataset for startups, the Crunchbase dataset, we show how centrality measures highlight the importance of particular players, such as angels and accelerators, whose role could be underestimated by focusing on collected funds only. We also provide a quantitative criterion to establish which firms should be considered strategic and rank them. Finally, as funding is a widespread measure for success in economic settings, we investigate to which extent this measure is in agreement with network metrics; the model accurately forecasts which firms will receive the highest funding in future years.

Network connectivity has been thoroughly investigated in several domains, including physics, neuroscience, and social sciences. This work tackles the possibility of characterizing the topological properties of real-world networks from a quantum-inspired perspective. Starting from the normalized Laplacian of a network, we use a well-defined procedure, based on the dressing transformations, to derive a 1-dimensional Schrödinger-like equation characterized by the same eigenvalues. We investigate the shape and properties of the potential appearing in this equation in simulated small-world and scale-free network ensembles, using measures of fractality. Besides, we employ the proposed framework to compare real-world networks with the Erdős-Rényi, Watts-Strogatz and Barabási-Albert benchmark models. Reconstructed potentials allow to assess to which extent real-world networks approach these models, providing further insight on their formation mechanisms and connectivity properties.

Abstract Background Hippocampal atrophy is a supportive feature for the diagnosis of probable Alzheimer’s disease (AD). However, even for an expert neuroradiologist, tracing the hippocampus and measuring its volume is a time consuming and extremely challenging task. Accordingly, the development of reliable fully-automated segmentation algorithms is of paramount importance. Materials and methods The present study evaluates (i) the precision and the robustness of the novel Hippocampal Unified Multi-Atlas Network (HUMAN) segmentation algorithm and (ii) its clinical reliability for AD diagnosis. For these purposes, we used a mixed cohort of 456 subjects and their T1 weighted magnetic resonance imaging (MRI) brain scans. The cohort included 145 controls (CTRL), 217 mild cognitive impairment (MCI) subjects and 94 AD patients from Alzheimer’s Disease Neuroimaging Initiative (ADNI). For each subject the baseline, repeat, 12 and 24 month follow-up scans were available. Results HUMAN provides hippocampal volumes with a 3% precision; volume measurements effectively reveal AD, with an area under the curve (AUC) AUC1 = 0.08 ± 0.02. Segmented volumes can also reveal the subtler effects present in MCI subjects, AUC2 = 0.76 ± 0.05. The algorithm is stable and reproducible over time, even for 24 month follow-up scans. Conclusions The experimental results demonstrate HUMAN is a precise segmentation algorithm, besides hippocampal volumes, provided by HUMAN, can effectively support the diagnosis of Alzheimer’s disease and become a useful tool for other neuroimaging applications.

Heavy metals are a dangerous source of pollution due to their toxicity, permanence in the environment and chemical nature. It is well known that long-term exposure to heavy metals is related to several chronic degenerative diseases (cardiovascular diseases, neoplasms, neurodegenerative syndromes, etc.). In this work, we propose a machine learning framework to evaluate the severity of cardiovascular diseases (CVD) from Human scalp hair analysis (HSHA) tests and genetic analysis and identify a small group of these clinical features mostly associated with the CVD risk. Using a private dataset provided by the DD Clinic foundation in Caserta, Italy, we cross-validated the classification performance of a Random Forests model with 90 subjects affected by CVD. The proposed model reached an AUC of 0.78 ± 0.01 on a three class classification problem. The robustness of the predictions was assessed by comparison with different cross-validation schemes and two state-of-the-art classifiers, such as Artificial Neural Network and General Linear Model. Thus, is the first work that studies, through a machine learning approach, the tight link between CVD severity, heavy metal concentrations and SNPs. Then, the selected features appear highly correlated with the CVD phenotype, and they could represent targets for future CVD therapies.

Recent works have extensively investigated the possibility to predict brain aging from T1-weighted MRI brain scans. The main purposes of these studies are the investigation of subject-specific aging mechanisms and the development of accurate models for age prediction. Deviations between predicted and chronological age are known to occur in several neurodegenerative diseases; as a consequence, reaching higher levels of age prediction accuracy is of paramount importance to develop diagnostic tools. In this work, we propose a novel complex network model for brain based on segmenting T1-weighted MRI scans in rectangular boxes, called patches, and measuring pairwise similarities using Pearson's correlation to define a subject-specific network. We fed a deep neural network with nodal metrics, evaluating both the intensity and the uniformity of connections, to predict subjects' ages. Our model reaches high accuracies which compare favorably with state-of-the-art approaches. We observe that the complex relationships involved in this brain description cannot be accurately modeled with standard machine learning approaches, such as Ridge and Lasso regression, Random Forest, and Support Vector Machines, instead a deep neural network has to be used.

Alzheimer's disease (AD) is the most common type of dementia and affects millions of people worldwide. Since complex diseases are often the result of combinations of gene interactions, microarray data and gene co-expression analysis can provide tools for addressing complexity. Our study aimed to find groups of interacting genes that are relevant in the development of AD. In this perspective, we implemented a method proposed in a previous work to detect gene communities linked to AD. Our strategy combined co-expression network analysis with the study of Shannon entropy of the betweenness. We analyzed the publicly available GSE1297 dataset, achieved from the GEO database in NCBI, containing hippocampal gene expression of 9 control and 22 AD human subjects. Co-expressed genes were clustered into different communities. Two communities of interest (composed by 72 and 39 genes) were found by calculating the correlation coefficient between communities and clinical features. The detected communities resulted stable, replicated on two independent datasets and mostly enriched in pathways closely associated with neuro-degenative diseases. A comparison between our findings and other module detection techniques showed that the detected communities were more related to AD phenotype. Lastly, the hub genes within the two communities of interest were identified by means of a centrality analysis and a bootstrap procedure. The communities of the hub genes presented even stronger correlation with clinical features. These findings and further explorations on the detected genes could shed light on the genetic aspects related with physiological aspects of Alzheimer's disease.

Currently the whole world is affected by the COVID-19 disease. Italy was the first country to be seriously affected in Europe, where the first COVID-19 outbreak was localized in the Lombardy region. The further spreading of the cases led to the lockdown of the most affected regions in northern Italy and then the entire country. In this work we investigated an epidemic spread scenario in the Lombardy region by using the origin–destination matrix with information about the commuting flows among 1450 urban areas within the region. We performed a large-scale simulation-based modeling of the epidemic spread over the networks related to three main motivations, i.e., work, study and occasional transfers to quantify the potential contribution of each category of travellers to the spread of the epidemic process. Our findings outline that the three networks are characterised by different weight dynamic growth rates and that the network “work” has a critical role in the diffusion phenomenon showing the greatest contribution to the epidemic spread.

In recent years personalized medicine reached an increasing importance, especially in the design of oncological therapies. In particular, the development of patients’ profiling strategies suggests the possibility of promising rewards. In this work, we present an explainable artificial intelligence (XAI) framework based on an adaptive dimensional reduction which (i) outlines the most important clinical features for oncological patients’ profiling and (ii), based on these features, determines the profile, i.e., the cluster a patient belongs to. For these purposes, we collected a cohort of 267 breast cancer patients. The adopted dimensional reduction method determines the relevant subspace where distances among patients are used by a hierarchical clustering procedure to identify the corresponding optimal categories. Our results demonstrate how the molecular subtype is the most important feature for clustering. Then, we assessed the robustness of current therapies and guidelines; our findings show a striking correspondence between available patients’ profiles determined in an unsupervised way and either molecular subtypes or therapies chosen according to guidelines, which guarantees the interpretability characterizing explainable approaches to machine learning techniques. Accordingly, our work suggests the possibility to design data-driven therapies to emphasize the differences observed among the patients.

The COVID-19 pandemic has amplified the urgency of the developments in computer-assisted medicine and, in particular, the need for automated tools supporting the clinical diagnosis and assessment of respiratory symptoms. This need was already clear to the scientific community, which launched an international challenge in 2017 at the International Conference on Biomedical Health Informatics (ICBHI) for the implementation of accurate algorithms for the classification of respiratory sound. In this work, we present a framework for respiratory sound classification based on two different kinds of features: (i) short-term features which summarize sound properties on a time scale of tenths of a second and (ii) long-term features which assess sounds properties on a time scale of seconds. Using the publicly available dataset provided by ICBHI, we cross-validated the classification performance of a neural network model over 6895 respiratory cycles and 126 subjects. The proposed model reached an accuracy of 85%±3% and an precision of 80%±8%, which compare well with the body of literature. The robustness of the predictions was assessed by comparison with state-of-the-art machine learning tools, such as the support vector machine, Random Forest and deep neural networks. The model presented here is therefore suitable for large-scale applications and for adoption in clinical practice. Finally, an interesting observation is that both short-term and long-term features are necessary for accurate classification, which could be the subject of future studies related to its clinical interpretation.

Remote sensing images find application in several different domains, such as land cover or land usage observation, environmental monitoring, and urbanization. This latter field has recently witnessed an interesting development with the use of remote sensing for infrastructural monitoring. In this work, we present an analysis of Sentinel-1 images, which were used to monitor the Italian provinces of Bologna and Modena located at the Emilia Region Apennines foothill. The goal of this study was the development of a machine learning-based detection system to monitor the deterioration of public aqueduct infrastructures based on Persistent Scatterer Interferometry (PSI). We evaluated the land deformation over a temporal range of five years; these series feed a k-means clustering algorithm to separate the pixels of the region according to different deformation patterns. Furthermore, we defined the critical areas as those areas where different patterns collided or overlapped. The proposed approach provides an informative tool for the structural health monitoring of underground infrastructures.

Modeling disease progression through the cognitive scores has become an attractive challenge in the field of computational neuroscience due to its importance for early diagnosis of Alzheimer’s disease (AD). Several scores such as Alzheimer’s Disease Assessment Scale cognitive total score, Mini Mental State Exam score and Rey Auditory Verbal Learning Test provide a quantitative assessment of the cognitive conditions of the patients and are commonly used as objective criteria for clinical diagnosis of dementia and mild cognitive impairment (MCI). On the other hand, connectivity patterns extracted from diffusion tensor imaging (DTI) have been successfully used to classify AD and MCI subjects with machine learning algorithms proving their potential application in the clinical setting. In this work, we carried out a pilot study to investigate the strength of association between DTI structural connectivity of a mixed ADNI cohort and cognitive spectrum in AD. We developed a machine learning framework to find a generalized cognitive score that summarizes the different functional domains reflected by each cognitive clinical index and to identify the connectivity biomarkers more significantly associated with the score. The results indicate that the efficiency and the centrality of some regions can effectively track cognitive impairment in AD showing a significant correlation with the generalized cognitive score (R = 0.7).

In recent years, a number of different procedures have been proposed for segmentation of remote sensing images, basing on spectral information. Model-based and machine learning strategies have been investigated in several studies. This work presents a comprehensive overview and an unbiased comparison of the most adopted segmentation strategies: Support Vector Machines (SVM), Random Forests, Neural networks, Sen2Cor, FMask and MAJA. We used a training set for learning and two different independent sets for testing. The comparison accounted for 135 images acquired from 54 different worldwide sites. We observed that machine learning segmentations are extremely reliable when the training and test are homogeneous. SVM performed slightly better than other methods. In particular, when using heterogeneous test data, SVM remained the most accurate segmentation method while state-of-the-art model-based methods such as MAJA and FMask obtained better sensitivity and precision, respectively. Therefore, even if each method has its specific advantages and drawbacks, SVM resulted in a competitive option for remote sensing applications.

Characterizing both neurodevelopmental and aging brain structural trajectories is important for understanding normal biological processes and atypical patterns that are related to pathological phenomena. Initiatives to share open access morphological data contributed significantly to the advance in brain structure characterization. Indeed, such initiatives allow large brain morphology multi-site datasets to be shared, which increases the statistical sensitivity of the outcomes. However, using neuroimaging data from multi-site studies requires harmonizing data across the site to avoid bias. In this work we evaluated three different harmonization techniques on the Autism Brain Imaging Data Exchange (ABIDE) dataset for age prediction analysis in two groups of subjects (i.e., controls and autism spectrum disorder). We extracted the morphological features from T1-weighted images of a mixed cohort of 654 subjects acquired from 17 sites to predict the biological age of the subjects using three machine learning regression models. A machine learning framework was developed to quantify the effects of the different harmonization strategies on the final performance of the models and on the set of morphological features that are relevant to the age prediction problem in both the presence and absence of pathology. The results show that, even if two harmonization strategies exhibit similar accuracy of predictive models, a greater mismatch occurs between the sets of most age-related predictive regions for the Autism Spectrum Disorder (ASD) subjects. Thus, we propose to use a stability index to extract meaningful features for a robust clinical validation of the outcomes of multiple harmonization strategies.

Functional connectivity analysis aims at assessing the strength of functional coupling between the signal responses in distinct brain areas. Usually, functional magnetic resonance imaging (fMRI) time series connections are estimated through zero-lag correlation metrics that quantify the statistical similarity between pairs of regions or spectral measures that assess synchronization at a frequency band of interest. Here, we explored the application of a new metric to assess the functional synchronization in phase space between fMRI time series in a resting state. We applied a complete topological analysis to the resulting connectivity matrix to uncover both the macro-scale organization of the brain and detect the most important nodes. The synchronization metric is also compared with Pearson’s correlation coefficient and spectral coherence to highlight similarities and differences between the topologies of the three functional networks. We found that the individual topological organization of the resulting synchronization-based connectivity networks shows a finer modular organization than that identified with the other two metrics and a low overlap with the modular partitions of the other two networks suggesting that the derived topological information is not redundant and could be potentially integrated to provide a multi-scale description of functional connectivity.

Signal processing and machine learning techniques are changing the clinical practice based on medical imaging from many perspectives. A major topic is related to (i) the development of computer aided diagnosis systems to provide clinicians with novel, non-invasive and low-cost support-tools, and (ii) to the development of new methodologies for the analysis of biomedical data for finding new disease biomarkers. Advancements have been recently achieved in the context of Alzheimer’s disease (AD) diagnosis through the use of diffusion weighted imaging (DWI) data. When combined with tractography algorithms, this imaging modality enables the reconstruction of the physical connections of the brain that can be subsequently investigated through a complex network-based approach. A graph metric particularly suited to describe the disruption of the brain connectivity due to AD is communicability. In this work, we develop a machine learning framework for the classification and feature importance analysis of AD based on communicability at the whole brain level. We fairly compare the performance of three state-of-the-art classification models, namely support vector machines, random forests and artificial neural networks, on the connectivity networks of a balanced cohort of healthy control subjects and AD patients from the ADNI database. Moreover, we clinically validate the information content of the communicability metric by performing a feature importance analysis. Both performance comparison and feature importance analysis provide evidence of the robustness of the method. The results obtained confirm that the whole brain structural communicability alterations due to AD are a valuable biomarker for the characterization and investigation of pathological conditions.

Analysis and quantification of brain structural changes, using Magnetic Resonance Imaging (MRI), are increasingly used to define novel biomarkers of brain pathologies, such as Alzheimer's disease (AD). Several studies have suggested that brain topological organization can reveal early signs of AD. Here, we propose a novel brain model which captures both intra- and inter-subject information within a multiplex network approach. This model localizes brain atrophy effects and summarizes them with a diagnostic score. On an independent test set, our multiplex-based score segregates (i) normal controls (NC) from AD patients with a 0.86±0.01 accuracy and (ii) NC from mild cognitive impairment (MCI) subjects that will convert to AD (cMCI) with an accuracy of 0.84±0.01. The model shows that illness effects are maximally detected by parceling the brain in equal volumes of 3, 000 mm3 (“patches”), without any a priori segmentation based on anatomical features. The multiplex approach shows great sensitivity in detecting anomalous changes in the brain; the robustness of the obtained results is assessed using both voxel-based morphometry and FreeSurfer morphological features. Because of its generality this method can provide a reliable tool for clinical trials and a disease signature of many neurodegenerative pathologies.

Research on brain disorders with a strong genetic component and complex heritability, such as schizophrenia, has led to the development of brain transcriptomics. This field seeks to gain a deeper understanding of gene expression, a key factor in exploring further research issues. Our study focused on how genes are associated amongst each other. In this perspective, we have developed a novel data-driven strategy for characterizing genetic modules, i.e., clusters of strongly interacting genes. The aim was to uncover a pivotal community of genes linked to a target gene for schizophrenia. Our approach combined network topological properties with information theory to highlight the presence of a pivotal community, for a specific gene, and to simultaneously assess the information content of partitions with the Shannon's entropy based on betweenness. We analyzed the publicly available BrainCloud dataset containing post-mortem gene expression data and focused on the Dopamine D2 receptor, encoded by the DRD2 gene. We used four different community detection algorithms to evaluate the consistence of our approach. A pivotal DRD2 community emerged for all the procedures applied, with a considerable reduction in size, compared to the initial network. The stability of the results was confirmed by a Dice index ≥80% within a range of tested parameters. The detected community was also the most informative, as it represented an optimization of the Shannon entropy. Lastly, we verified the strength of connection of the DRD2 community, which was stronger than any other randomly selected community and even more so than the Weighted Gene Co-expression Network Analysis module, commonly considered the standard approach for such studies. This finding substantiates the conclusion that the detected community represents a more connected and informative cluster of genes for the DRD2 community, and therefore better elucidates the behavior of this module of strongly related DRD2 genes. Because this gene plays a relevant role in Schizophrenia, this finding of a more specific DRD2 community will improve the understanding of the genetic factors related with this disorder.

In this paper, we investigate the connectivity alterations of the subcortical brain network due to Alzheimer’s disease (AD). Mostly, the literature investigated AD connectivity abnormalities at the whole brain level or at the cortex level, while very few studies focused on the sub-network composed only by the subcortical regions, especially using diffusion-weighted imaging (DWI) data. In this work, we examine a mixed cohort including 46 healthy controls (HC) and 40 AD patients from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) data set. We reconstruct the brain connectome through the use of state of the art tractography algorithms and we propose a method based on graph communicability to enhance the information content of subcortical brain regions in discriminating AD. We develop a classification framework, achieving 77% of area under the receiver operating characteristic (ROC) curve in the binary discrimination AD vs. HC only using a 12 × 12 subcortical features matrix. We find some interesting AD-related connectivity patterns highlighting that subcortical regions tend to increase their communicability through cortical regions to compensate the physical connectivity reduction between them due to AD. This study also suggests that AD connectivity alterations mostly regard the inter-connectivity between subcortical and cortical regions rather than the intra-subcortical connectivity.