A5052334999- Data Mining Algorithms and Applications
- Neural Networks and Applications
- Sentiment Analysis and Opinion Mining
- Bayesian Methods and Mixture Models
- Statistical Methods and Inference
- Data Management and Algorithms
- Stock Market Forecasting Methods
- Complex Systems and Time Series Analysis
- Machine Learning and Data Classification
- Blockchain Technology Applications and Security
- Management, Economics, and Public Policy
- Advanced Text Analysis Techniques
- Pharmacogenetics and Drug Metabolism
- Face and Expression Recognition
- Bayesian Modeling and Causal Inference
- Imbalanced Data Classification Techniques
- Health Systems, Economic Evaluations, Quality of Life
- Treatment of Major Depression
- Statistical Methods and Bayesian Inference
- Digital Marketing and Social Media
- Advanced Statistical Methods and Models
- Sensory Analysis and Statistical Methods
- Diverse academic and cultural studies
- Multi-Criteria Decision Making
- Fuzzy Logic and Control Systems
University of Cagliari
2016-2025
Institute of Genetic and Biomedical Research
2024
National Research Council
2024
National Academies of Sciences, Engineering, and Medicine
2024
Università degli studi di Cassino e del Lazio Meridionale
2004-2011
Leiden University
2010
University of Naples Federico II
2000-2002
Abstract Additive models and tree-based regression are two main classes of statistical used to predict the scores on a continuous response variable. It is known that additive become very complex in presence higher order interaction effects, whereas some models, such as CART, have problems capturing linear effects predictors. To overcome these drawbacks, trunk model has been proposed: multiple with parsimonious amount effects. The can be represented by small tree: trunk. This article proposes...
We present an overview of the main methodological features and goals pharmacoeconomic models that are classified in three major categories: regression models, decision trees Markov models. In particular, we focus on define a semi-Markov model cost utility vaccine for dengue fever discussing key components interpretation its results. Next, identify some criticalities rule arising from possible incorrect outcomes. Specifically, difference between median mean ICER handling willingness-to-pay...
Non-destructive, fast, and accurate methods of dating are highly desirable for many heritage objects. Here, we present critically evaluate the use near-infrared (NIR) spectroscopic data combined with three supervised machine learning to predict publication year paper books dated between 1851 2000. These provide different accuracies; however, demonstrate that underlying processes refer common spectral features. Regardless method used, most informative wavelength ranges can be associated C-H...
Eye tracking provides a quantitative measure of eye movements during different activities. We report the results from bibliometric analysis to investigate trends in research applied study medical conditions. conducted search on Web Science Core Collection (WoS) database and analyzed dataset 2456 retrieved articles using VOSviewer Bibliometrix R package. The most represented area was psychiatry (503, 20.5%) followed by neuroscience (465, 18.9%) psychology developmental (337, 13.7%). annual...
Abstract The Threshold-based Naïve Bayes (Tb-NB) classifier is introduced as a (simple) improved version of the original classifier. Tb-NB extracts sentiment from Natural Language text corpus and allows user not only to predict how much sentence positive (negative) but also quantify with numeric value. It based on estimation single threshold value that concurs define decision rule classifies into opinion its content. One main advantage deriving possibility utilize results input post-hoc...
Response to antidepressants (ADs) is highly variable and partly genetically driven, but the utility of pharmacogenetic testing in guiding ADs treatment still controversial. We conducted a retrospective, naturalistic study explore CYP2C6 CYP2C19 genotyping sample 156 patients diagnosed with major depressive disorder from South Sardinia (Italy). Clinical data, including history medication regimens, adverse reactions, response ADs, were collected over last five years preceding recruitment....
Major depressive disorder (MDD) is a common and severe psychiatric that has enormous economical societal costs. As pharmacogenetics one of the key tools precision psychiatry, we analyze cost-utility test screening CYP2C19 CYP2D6 for patients suffering from major try to understand main drivers influence cost-utility.We developed two pharmacoeconomic nonhomogeneous Markov models cost-utility, an Italian perspective, pharmacogenetic testing genetic characterize metabolizing profiles cytochrome...
Abstract Background Sars-Cov-2 is a novel corona virus associated with significant morbidity and mortality. Remdesivir Dexamethasone are two treatments that have shown to be effective against the disease. However, cost-effectiveness analysis of still lacking. Objective The cost-utility Remdesivir, simultaneous use drugs respect standard care for treatment Covid-19 hospitalized patients evaluated, together effect compared base model but based on alernative assumptions. Methods A decision tree...
Epidemiological research has shown relevant differences between sexes in clinical manifestations, severity, and progression of cardiovascular metabolic disorders. To date, the mechanisms underlying these remain unknown. Given rising incidence such diseases, gender-specific on established emerging risk factors, as dysfunction glycaemic and/or lipid metabolism, sex hormones gut microbiome, is paramount importance. The relationships hormones, host metabolism are largely unknown even...
Abstract The iterative Threshold-based Naïve Bayes (iTb-NB) classifier is introduced as a (simple) improved version of the previously non-iterative (Tb-NB) classifier. iTb-NB starts from Natural Language text-corpus and allows user to quantify with numeric value sentiment (positive or negative) specific test. Differently Tb-NB, an algorithm aimed at estimating multiple threshold values that concur refine Tb-NB’s decision rules when classifying text into positive (negative) based on its...
We analyse, using a mixture of statistical models and natural language process techniques, what happened in social media from June 2019 onwards to understand the relationships between Cryptocurrencies' prices media, focusing on rise Bitcoin Ethereum prices. In particular, we identify model relationship cryptocurrencies market price changes, sentiment topic discussion occurrences Hawkes' Model. find that some topics precedes certain types movements. Specifically, discussions concerning...
Aim of this paper is to investigate the extent impact Airbnb phenomenon on tourism indicators in general and, particular, sustainable (STI). We conjecture that, notwithstanding correctness STIs construction, these measure partially, since are computed using data recorded by official statistics organisation that do not include information about flows. demonstrate offer a new point view analysis terms sustainability. Results provide evidence substantial presence guests Italy and consequent...
Abstract Statistical and machine learning methods have become paramount in order to handle large size claims data as part of health care fraud detection frameworks. Among these, predictive such regression classification algorithms are widely used with labeled data. However, the imbalanced nature skewness distributions result challenges practical applications. This paper presents use various pre‐processing on claim payment populations overpayment scenarios different characteristics. It can...
Abstract During the recent Coronavirus disease 2019 (COVID-19) outbreak, microblogging service Twitter has been widely used to share opinions and reactions events. Italy was one of first European countries be severely affected by outbreak establish lockdown stay-at-home orders, potentially leading country reputation damage. We resort sentiment analysis investigate changes in about reported on before after COVID-19 outbreak. Using different lexicons-based methods, we find a breakpoint...
Summary Data editing is the process by which data that are collected in some way (a statistical survey for example) examined errors and corrected with help of software. Edits, logical conditions should be satisfied data, specified subject-matter experts a procedure could tedious lead to mistakes practical implications. To render edit specification more efficient we provide new step—the definition so-called abstract model survey—which describes structure phenomenon studied survey. The...
The Bradley-Terry Regression Trunk (BTRT) model combines the log-linear model, including subject-specific covariates, with a particular tree-based so-called regression trunk. It aims to consider simultaneously main effects and interaction of covariates on data expressed as paired comparisons. We apply this financial rankings then transformed into Tax revenues differentiated by category represent statistical units analysis (i.e., taxes income, social security contributions, property, goods...
We develop a general framework to apply the Kelly criterion stock market data, and consequently, portfolio optimization. Under few conditions, using Monte Carlo simulations with different scenarios we prove that beats any other approach in many aspects. In particular, it maximizes expected growth rate median of terminal wealth. also show that, under normal distribution returns, has best performance long run. Next, optimize no leverage short selling conditions this lays mean-variance...