A5069995691- Data Mining Algorithms and Applications
- Biomedical Text Mining and Ontologies
- Bioinformatics and Genomic Networks
- Semantic Web and Ontologies
- Time Series Analysis and Forecasting
- Machine Learning in Healthcare
- Diabetes Management and Research
- Electronic Health Records Systems
- Artificial Intelligence in Healthcare
- Gene expression and cancer classification
- Business Process Modeling and Analysis
- Data Quality and Management
- Digital Mental Health Interventions
- Data Management and Algorithms
- Mobile Health and mHealth Applications
- Gene Regulatory Network Analysis
- Reproductive Biology and Fertility
- Rough Sets and Fuzzy Logic
- Advanced Database Systems and Queries
- Clinical practice guidelines implementation
- Pluripotent Stem Cells Research
- Systemic Lupus Erythematosus Research
- Health Systems, Economic Evaluations, Quality of Life
- Renal and related cancers
- Diabetes, Cardiovascular Risks, and Lipoproteins
University of Pavia
2015-2024
Italian Institute of Technology
2024
Hasselt University
2022
Karolinska Institutet
2022
Pontificia Universidad Católica de Chile
2022
Research Foundation - Flanders
2022
Universitat Politècnica de València
2022
University of Applied Sciences Upper Austria
2022
Consorzio di Bioingegneria e Informatica Medica
2022
Fondazione Salvatore Maugeri
2015-2020
One of the areas where Artificial Intelligence is having more impact machine learning, which develops algorithms able to learn patterns and decision rules from data. Machine learning have been embedded into data mining pipelines, can combine them with classical statistical strategies, extract knowledge Within EU-funded MOSAIC project, a pipeline has used derive set predictive models type 2 diabetes mellitus (T2DM) complications based on electronic health record nearly one thousand patients....
Process mining techniques can be used to analyse business processes using the data logged during their execution. These are leveraged in a wide range of domains, including healthcare, where it focuses mainly on analysis diagnostic, treatment, and organisational processes. Despite huge amount generated hospitals by staff machinery involved healthcare processes, there is no evidence systematic uptake process beyond targeted case studies research context. When developing distinguishing...
Objectives To evaluate changes in demographic, clinical and histological presentation, prognosis of lupus nephritis (LN) over time. Patients methods We studied a multicentre cohort 499 patients diagnosed with LN from 1970 to 2016. The 46-year follow-up was subdivided into three periods (P): P1 1970–1985, P2 1986–2001 P3 2002–2016, accordingly grouped based on the year diagnosis. Predictors patient renal survival were investigated by univariate multivariate proportional hazards Cox regression...
Short-term predictive endpoints of chronic kidney disease (CKD) are needed in lupus nephritis (LN). We tested response to therapy at 1 year.We considered patients with LN who underwent renal biopsy followed by induction between January 1970 and December 2016. was assessed using the International Society Nephrology/Renal Pathology (2003) criteria National Institute Health (NIH) activity chronicity index. The outcome CKD. Response defined according EULAR/European League Against...
IntroductionThe aim of this retrospective study on biopsy-proven lupus nephritis (LN) patients is to assess the probability sustained clinical remission (sCR) and investigate sCR effects disease flares impaired kidney function (IKF).MethodssCR was defined as clinical-SLEDAI-2K=0 eGFR>60ml/min/1.73m2 lasting≥1 year; IKF: eGFR<60ml/min/1.73m2 for>3 months. We analysed achieving maintaining sCR, yearly risk flare. Cox models were used identify predictors IKF with variables time-depending...
Abstract Predictive data mining in clinical medicine deals with learning models to predict patients' health. The can be devoted support clinicians diagnostic, therapeutic, or monitoring tasks. Data methods are usually applied contexts analyze retrospective data, thus giving healthcare professionals the opportunity exploit large amounts of routinely collected during their day‐by‐day activity. Moreover, nowadays take advantage techniques deal huge amount research results obtained by molecular...
To describe the development, as part of European Union MOSAIC (Models and Simulation Techniques for Discovering Diabetes Influence Factors) project, a dashboard-based system management type 2 diabetes assess its impact on clinical practice.The dashboard is based predictive modeling, longitudinal data analytics, reuse integration from hospitals public health repositories. Data are merged into an i2b2 warehouse, which feeds set advanced temporal analytic models, including abstractions,...
<b><i>Objectives:</i></b> This study included a cohort of advanced renal cell carcinoma patients treated with sunitinib. Since resistance to sunitinib may be mediated through angiogenic cytokines other than VEGF, we measured the circulating levels three pro-angiogenic cytokines: basic fibroblast growth factor (bFGF), hepatocyte (HGF), and interleukin (IL)-6. <b><i>Methods:</i></b> Cytokines were at baseline on first day each treatment cycle...
In the age of Evidence-Based Medicine, Clinical Guidelines (CGs) are recognized to be an indispensable tool support physicians in their daily clinical practice. Medical Informatics is expected play a relevant role facilitating diffusion and adoption CGs. However, past pioneering approaches, often fragmented many disciplines, did not lead solutions that actually exploited hospitals. Process Mining for Healthcare (PM4HC) emerging discipline gaining interest healthcare experts, seems able deal...
Anti-IgE treatment represents a major breakthrough in the therapeutic management of severe allergic asthma. To date, omalizumab is only biological drug currently licensed as add-on therapy children aged > 6 years with moderate-to-severe and asthma uncontrolled after high dose inhaled corticosteroids plus long-acting beta2-agonist. The clinical efficacy safety pediatric population has been extensively documented specific trials consistently expanded from real-life studies. Our aim to describe...
Abstract Background The maternal contribution of transcripts and proteins supplied to the zygote is crucial for progression from a gametic an embryonic control preimplantation development. Here we compared transcriptional profiles two types mouse MII oocytes, one which developmentally competent (MII SN oocyte), other that ceases development at 2-cell stage NSN with aim identifying genes gene expression networks whose misregulated would contribute reduced developmental competence. Results We...
Aims: In type 2 diabetes, we aimed at clarifying the role of glycated haemoglobin variability and other risk factors in development main micro-vascular complications: peripheral neuropathy, nephropathy retinopathy. Methods: a single-centre cohort 900 patients, was evaluated as intra-individual standard deviation, adjusted deviation coefficient variation serially measured 2-year period before randomly selected index visit. We devised four models considering different aspects evolution....
Abstract Summary: TimeClust is a user-friendly software package to cluster genes according their temporal expression profiles. It can be conveniently used analyze data obtained from DNA microarray time-course experiments. implements two original algorithms specifically designed for clustering short time series together with hierarchical and self-organizing maps. Availability: executable files Windows LINUX platforms downloaded free of charge non-profit institutions the following web site:...
Oct4 is a key factor of an expanded transcriptional network (Oct4-TN) that governs pluripotency and self-renewal in embryonic stem cells (ESCs) the inner cell mass from which ESCs are derived. A pending question whether establishment Oct4-TN initiates during oogenesis or after fertilisation. To this regard, recent evidence has shown controls poorly known central to acquisition mouse egg developmental competence. The aim study was investigate identity extension maternal Oct4-TN, as much its...
Big data technologies are nowadays providing health care with powerful instruments to gather and analyze large volumes of heterogeneous collected for different purposes, including clinical care, administration research. This makes possible design IT infrastructures that favor the implementation so-called "Learning Healthcare System Cycle", where healthcare practice research part a unique synergic process. In this paper we highlight how "Big Data enabled" integrated collections may support...