CV

Contact Information

Name Alberto Marfoglia
Professional Title AI & Healthcare Data Engineer | PhD Candidate
Email a.marfoglia@hotmail.it

Professional Summary

PhD candidate in Computer Science and Engineering specializing in trustworthy AI, healthcare data engineering, and semantic interoperability. Experienced in designing and deploying real-world clinical data infrastructures, combining machine learning, knowledge graphs, HL7 FHIR, and Digital Twin technologies. Collaborates with hospitals, research institutes, and EU-connected healthcare initiatives.

Experience

  • 2025 - present

    Paris, France

    Visiting PhD Researcher
    Inria – HEKA Research Unit (INSERM – Université Paris Cité)
    • Developed graph-based clinical outcome prediction models (GCNs, KG learning)
    • Analyzed impact of clinical data standards (FHIR, OMOP, SPHN)
    • Collaborated with Nantes University Hospital (CHU de Nantes) within NEUROVASC project
    • Worked on explainable AI for healthcare decision support
  • 2025 - 2025

    Bologna, Italy

    ICT Research Consultant (AlmaHealthDB)
    University of Bologna
    • Engineered secure multi-user research infrastructure for AlmaHealthDB
    • AlmaHealthDB, connected healthcare data infrastructure (IRCCS network: Rizzoli, S. Orsola-Malpighi, Institute of Neurological Sciences)
    • Implemented GPU optimization, role-based access control, and secure data exchange
    • Supported interoperability with regional infrastructure (Lepida S.c.p.A.)
  • 2024 - 2025

    Remote

    Topic Coordinator
    Frontiers in Digital Health
    • Coordinated special issue on Digital Twins in healthcare
    • Managed peer-review and interdisciplinary editorial workflow
    • Defined scientific scope on AI, interoperability, and patient-centered systems
  • 2023 - 2023

    Bologna, Italy

    Research Fellow
    University of Bologna
    • Designed FHIR-based clinical data transformation pipeline (Heal Italia)
    • Developed ETL workflows for heterogeneous healthcare datasets
    • Contributed to data lake and backend infrastructure design
  • 2023 - 2023

    Fano, Italy

    GenAI Research Engineer
    MEBLabs
    • Developed RAG pipelines using LLMs and vector databases (FAISS)
    • Built semantic search systems with OpenAI API
    • Deployed AI prototypes on AWS cloud infrastructure
  • 2020 - 2021

    Cesena, Italy

    Research Scholarship Holder
    I-Tel S.r.l. / University of Bologna
    • Designed a microservice-based interoperability platform for healthcare systems
    • Implemented HL7, FHIR, and REST integration with legacy systems
    • Built a hexagonal architecture for healthcare data exchange

Education

  • 2023 - present

    Bologna, Italy

    PhD
    University of Bologna
    Computer Science and Engineering
    • Trustworthy AI, clinical data harmonization, Digital Twins
    • Knowledge graphs and graph learning for healthcare prediction
    • Best Workshop Paper Award (IEEE PerCom DIGITA 2025)
  • 2020 - 2023

    Cesena, Italy

    MSc
    University of Bologna
    Computer Science and Engineering
    • Thesis with Rizzoli Orthopaedic Institute (Bologna)
    • Healthcare interoperability and digital modeling
  • 2017 - 2020

    Cesena, Italy

    BSc
    University of Bologna
    Computer Science and Engineering
    • Pre-hospital trauma tracking system (clinical collaboration)
    • Early graduation with honors award

Projects

  • CONNECTED – Digital Twin Healthcare Platform
    • Knowledge graph-driven Digital Twin architecture for healthcare
    • Patient-centric APIs for clinical data integration and prediction
    • Applied to stroke-risk and clinical outcome prediction benchmarks
    • Publications in PerCom (2024–2025), Frontiers in Digital Health, FGCS
    • Best Workshop Paper (DIGITA 2025)
  • AlmaHealthDB
    • Distributed healthcare research infrastructure across IRCCS hospitals (Bologna)
    • Supports Rizzoli Orthopaedic Institute, S. Orsola-Malpighi, Neurological Sciences Institute
    • EU-connected ecosystem (METASTRA, CPW, regional health service integration)
  • FHIR Clinical Data Transformation Pipeline
    • ETL pipeline for converting heterogeneous clinical datasets into HL7 FHIR
    • Used in the MOTU dataset, the METASTRA project, and multi-center studies
    • SNOMED CT-based semantic mapping and validation

Publications

Skills

AI & Machine Learning: Graph Representation Learning, Knowledge Graphs, Explainable AI, NLP & LLMs
Healthcare Data: HL7 FHIR, OMOP, openEHR, SNOMED CT, LOINC, Clinical Data Harmonization
Semantic Technologies: RDF, OWL, SPARQL, Ontology Engineering, Protégé, Apache Jena
Software & Infrastructure: Python, Java, Scala, Kotlin, JavaScript, Docker, Git, CI/CD, GitLab, AWS, Linux, HPC, Microservices, Hexagonal Architecture

Languages

Italian : Native
English : C1
French : A2