Trustworthy AI for healthcare Lab

Trustworthy AI requirements established by the HLEG of EU In the field of healthcare, Artificial Intelligence (AI) is currently promising support for healthcare professionals in their decision-making process of disease pattern detection or predicting risk situations for patients. However, when these AI systems’ outputs affect the patient’s life, their adoption in clinical routine encounters barriers related to the trustworthiness of the outputs.

The trustworthiness aspect of AI solutions has become a relevant value to be considered by any stakeholders related to AI solutions lifecycle. According to this importance, the European Commission delivered the Ethics guidelines for trustworthy AI where different requirements are stated. In a nutshell, the Trustworthy AI requirements established by the HLEG of EU (link) are depicted in the image.

In the context of tackling the Trustworthy AI requirements in AI applications, the Z-inspection® initiative ( ) proposes a framework to assess AI solutions in different phases of their lifecycle based on the Ethics Guidelines for Trustworthy AI  by the European Commission High-Level Expert Group on Artificial Intelligence.


Goals of the lab

The Trustworthy AI for Healthcare Laboratory at Tampere University is composed of a group of researchers that pursue to leverage the importance of Trustworthy AI in academic and civil society to enhance the AI solutions aimed at healthcare and improve their uptake by the different healthcare stakeholders. The Lab is affiliated with the Z-inspection ® initiative.

The goals of the lab are listed as follows:

  • Design, develop and evaluate decision-support models for different healthcare fields that foster Trustworthy AI principles, making emphasis on explainable AI and the risk of bias.
  • Raise the awareness of Trustworthy AI in the health data science community of TUNI.
  • Support research activities and project proposals of TUNI researchers in the area of health data science who are interested in complying with Trustworthy AI requirements.
  • Disseminate the Z-inspection process in TUNI’s education programs as well as in different research activities to achieve design, development, and validation of AI solutions in healthcare aligned with the principles of Trustworthy AI.
  • Build a research community around the topic of Trustworthy AI in Healthcare where researchers from Tampere, Finland, and abroad can share their expertise and effort toward different research and education activities.

Activities of the Lab

Members of the lab are involved in different activities aligned with the goals of the Lab, a (non-exhaustive) list as follows:

  • Lenatti, Marta, Moreno-Sánchez Pedro A., Edoardo M. Polo, Maximiliano Mollura, Riccardo Barbieri, and Alessia Paglialonga. “Evaluation of Machine Learning Algorithms and Explainability Techniques to Detect Hearing Loss From a Speech-in-Noise Screening Test.” American Journal of Audiology 31, no. 3S (September 21, 2022): 961–79. (link)
  • Allahabadi, Himanshi, Julia Amann, Isabelle Balot, Andrea Beretta, Charles Binkley, Jonas Bozenhard, Frédérick Bruneault, et al. “Assessing Trustworthy AI in Times of COVID-19. Deep Learning for Predicting a Multi-Regional Score Conveying the Degree of Lung Compromise in COVID-19 Patients.” IEEE Transactions on Technology and Society, 2022, 1–1. (link)
  • Zicari, Roberto V., Sheraz Ahmed, Julia Amann, Stephan Alexander Braun, John Brodersen, Frédérick Bruneault, James Brusseau, et al. “Co-Design of a Trustworthy AI System in Healthcare: Deep Learning Based Skin Lesion Classifier.” Frontiers in Human Dynamics 3 (2021). (link)
  • PerCard project (link)
  • Explainable AI lecture in Decision Support for Health course (BBT.HTI.509) at Tampere University
  • Z-Inspection® is listed in the new OECD Catalogue of AI Tools & Metrics


  • Pedro A. Moreno-Sanchez, PhD (Lead researcher)
  • Mark van Gils, Prof. (researcher)
  • Roberto Zicari, Prof. (advisor)


To know more about the lab, do not hesitate to contact us: