Matteo Valerio

Matteo Valerio

Data Scientist

IRCCS Sacro Cuore Don Calabria Hospital

Oncology Department

Biography

I have been working in the field of Medical Informatics since 2011, when I started working on information systems and technologies for managing health data, developing applications for the collection and statistical analysis of clinical data, mainly in the oncology field.

Since 2012, I have been working steadily in the Department of Oncology at the IRCCS Sacro Cuore Don Calabria Hospital, where my activity has evolved over time thanks to the knowledge acquired through academic courses and certifications that have allowed me to connect multidisciplinary skills useful for forming my background in data science.

Currently, my activity involves managing clinical data related to the oncology field, aggregating the various sources of information that characterize its interdisciplinary nature and developing software applications for their analysis.

In the field of clinical research, I am responsible for creating electronic CRFs for data collection and conducting statistical analysis related to the definition of regression models, survival analysis, and the application of clustering and classification techniques in order to identify relationships between data.

My passion and curiosity for new technologies related to data science drives me to stay updated, especially in the area of Artificial Intelligence applied to clinical research.

For the Oncology Department, I also manage several software applications useful for medical and nursing clinical activities.

Interests
  • Machine Learning
  • Deep Learning
  • Data Science
  • Biostatistics
Education
  • II degree Master in Machine Learning and Big Data in Precision Medicine and Biomedical Research, 2020

    University of Padova

  • I degree Master in Computer processing of biomedical data in medicine, 2010

    University of Verona

  • MSc in Electronic Engineering, 2007

    University of Padova

Skills

R Programming

Data Analysis, Statistics, ETL,
Graphics, Machine Learning

Python Programming

Data Analysis, ETL, Graphics,
Machine Learning, Deep Learning

Reproducible Research

R Markdown, Jupyter Notebook, STATA scripts

Artificial Intelligence

Machine Learning and Deep Learning (Supervised/Unsupervised)

Biostatistics

Regression, Survival analysis,
Parametric/Non-Parametric tests

Continuous Integration

Git, GitHub

Databases

Oracle, MySQL, SQLite, SQL Server
SQL and PL/SQL language

eCRF

Development of web apps with
Oracle APEX and REDCap

Interactive Dashboards

Extracting insights from data
with QlikView and Plotly

Graphics

Photoshop, GIMP

Photography

Passionate and amateur
(Portfolio)

Accomplish­ments

Coursera
Sequence Models
See certificate
Coursera
Convolutional Neural Networks
See certificate
Coursera
Structuring Machine Learning Projects
See certificate
Coursera
Improving Deep Neural Networks:
Hyperparameter tuning, Regularization and Optimization
See certificate
Coursera
Neural Network and Deep Learning
See certificate
Coursera
AI for Medicine Specialization

Courses Included:

See certificate

Projects

pybioportal
A Python package to easily retrieve data from cBioPortal
pybioportal

Recent Publications

Follow-up of breast cancer: why is it necessary to start a Consensus in 2024?
In Italy, breast cancer is the most frequently diagnosed cancer in women, with 55,900 new cases in 2023 (over 90% in the early stages). …
Neoadjuvant Systemic Therapy in Early Breast Cancer: Results of a Prospective Observational Multicenter BRIDE Study
To evaluate the rate of early breast cancer (EBC) patients treated with neoadjuvant systemic therapy (NAT) in Italy, criteria of …
The Impact of NUTRItional Status at First Medical Oncology Visit on Clinical Outcomes: The NUTRIONCO Study
Malnutrition affects up to 75% of cancer patients and results from a combination of anorexia and metabolic dysregulation. Metabolic and …

Contact