Lasse Hansen

Lasse Hansen

PhD Student in Machine Learning for Healthcare

Aarhus University


I am a PhD student at the Department of Clinical Medicine at Aarhus University studying how to use machine learning to improve patient outcomes in psychiatry.

I mainly work on the PSYCOP project where we create prediction models from data from electronic health records (EHR) to improve patients outcomes. My focus is on representation learning from multi-modal data and figuring out how best to model the complex sequential nature of the EHR.

I’m a large advocate for open-source software and have released the state-of-the-art pretrained speech model for Danish, a Python package for extracting metrics from text, and am a part of the Danish foundation models project.


  • Machine Learning and AI
  • Psychiatric Disorders
  • Effective Altruism


  • PhD student, 2021 - 2024

    Aarhus University

  • Msc in Cognitive Science, 2019 - 2022

    Aarhus University

  • Bachelor Semester Abroad, 2019

    University of Otago

  • BSc in Cognitive Science, 2016 - 2019

    Aarhus University





Machine Learning

Natural Language Processing

Acoustic analysis



Data Science Intern

Hoffmann-La Roche

Aug 2020 – Dec 2020 Basel, Switzerland
Research internship. Conducted a project on using transfer learning from emotional speech databases to predict the presence and severity of depression from interviews with Danish speakers. Supervised by Yan-Ping Zhang (Roche), Detlef Wolf (Roche), and Riccardo Fusaroli (Aarhus University).

Junior Developer

Center for Humanities Computing Aarhus (CHCAA)

Jun 2019 – Jan 2021 Aarhus, Denmark
Assisted and provided consultancy for researchers primarily from the humanities in analysing their data. Mainly NLP related tasks.

Study Mentor

Aarhus University, Denmark

Mar 2018 – Dec 2018 Aarhus, Denmark
Provided statistics and general university-life assistance.

Student Data Scientist

TV2 Østjylland

Jun 2017 – Aug 2018 Aarhus, Denmark
Created dashboards for visualization of KPIs and analysed data from e.g. Google Analytics.