Gheorghe awarded Alberta Machine Intelligence Institute Scholarship

Our very own, Gheorghe Lisca, was awarded a highly competitive scholarship from the Alberta Machine Intelligence Institute with the Alberta University in Edmonton, Canada.

Gheorghe will visit AMII and present his work on Deep Reinforcement Learning for Plausible Motion Synthesis in Biomechanics in the research group of “the father” of Reinforcement Learning, Prof. Richard Sutton. The scholarship covers the travelling to and the accommodation in Edmonton during the AMII AI Week workshop 24 – 27th of May.

Well done Gheorghe!


PRECISION: Profile Extraction from Clinical Insights for Smart Individualized Oncology



Over the past decades, early diagnosis, new drugs and more personalised treatment have led to impressive increases in survival rates of cancer patients. Yet, chemotherapy-induced peripheral neuropathy (CIPN), one of the most disabling side effects of commonly used chemotherapeutic drugs, is a severe problem in oncology leading to dose reduction, treatment delay or discontinuation. CIPN causes long-lasting disturbances of daily functioning and quality of life in a considerable proportion of patients. With an increasing number of cancer survivors, more attention is being paid to persistent sequelae of tumour treatment and supportive measures used as adjuncts to mainstream cancer care to control symptoms and enhance well-being.

CIPN describes the damage to the peripheral nervous system incurred by a patient who has received a chemotherapeutic agent that is known to be neurotoxic. Independent of the mechanisms of action, the targeted impact of such agents is on axonal transmission with consequences leading up to neuronal apoptosis.

Computational Oncology Approach

The incidence of peripheral neuropathy differs significantly across chemotherapeutic agents. The prevalence and severity of CIPN are dependent upon several factors relating to both drug pharmacokinetics (e.g., PK, cumulative dose and treatment duration) and pharmacodynamics (e.g., PD, mechanisms of toxicity and patient characteristics). Typically, in vitro and in vivo tests are performed to investigate drug toxicity. In comparison to such experimental approaches, computational methods, including machine learning and structural alerts, have shown great advantages since they are green, fast, cheap, accurate, and most importantly they could be done before the patient receive the therapy. Although such approaches exploit patient-specific risk factors that have been associated with the susceptibility for developing CIPN.

We are aware of no publicly available, validated in silico system to predict the development of CIPN in individual patients. The goal of this project is to develop a clinical decision-support system to predict CIPN development. Using simulation, mechanistic modelling, and machine learning we will develop and validate predictive models to quantify the risk of developing CIPN and deploy a standalone clinical decision-making system that will improve cancer treatment and survivorship care planning.













The project proposes a new digital intervention to support clinical oncologists in designing CIPN-aware cancer therapies. Understanding low-level tumor biology and patient genetics can provide unique insights that were previously impossible, to identify genetic predictors of CIPN. Correlating such information with models of tumor growth and patient’s clinical peculiarities, the system can isolate the most relevant cancer response patterns to adjust therapy parameters. The overall goal of the project is to fuse the insights gained at each of these levels in order to build a decision support system that predicts the development of CIPN in a particular patient. The system will learn the governing drug PK/PD differential equations directly from patient data by combining key pharmacological principles with neural ordinary differential equations refined through simulations for improved temporal prediction metrics. Furthermore, by incorporating key PK/PD concepts into its architecture, the system can generalize and enable the simulations of patient responses to untested dosing regimens. These emphasize the potential such a system holds for automated predictive analytics of patient drug response. The end result of the project will be a simple app that will collect physician inputted patient clinical parameters and eventually health records and will provide, given the therapy drug choice a prediction of the severity of CIPN before the chemotherapy regimen. Additionally, the physician and patient will get interpretable insights and a clear explanation of how each of the factors affects the prognosis. The entire processing and data aggregation and learning will happen in the cloud using GDPR-aware data handling.
















The project is based on large-scale data fusion that provides a multi-faceted profile of the patient, drugs, tumor and how they interact. This will finally support personalized intervention and adaptive therapies that maximise efficacy and minimize toxicity.

New Journal Article accepted in Frontiers in Artificial Intelligence

Our lab’s collaboration with the Life Sciences Department at TU Munich and the Interdisciplinary Breast Center at the Helios Klinikum Munich West resulted in a new research article published in the prestigious Frontiers in Artificial Intelligence – Medicine and Public Health (Mathematical and Computational Oncology).

The work on Data-driven Discovery of Mathematical and Physical Relations in Oncology Data using Human-understandable Machine Learning introduces a new framework for mathematical and computational oncology tools that exploit network approaches for the mathematical modeling, analysis, and prediction of cancer development and therapy design. Well done!

The preprint is available at: 

New journal article accepted in MDPI Symmetry

Our lab’s collaboration with IBM Research Zurich and the Computer Science Department at the University of Surrey resulted in a new perspective article published in the prestigious MDPI Symmetry under Networks in Cancer: From Symmetry Breaking to Targeted Therapy.

This perspective article gathers the latest developments in mathematical and computational oncology tools that exploit network approaches for the mathematical modelling, analysis, and simulation of cancer development and therapy design. Well done!

The full article is available at: 

New journal article accepted in IEEE Sensors

Our latest work on Learning Insights from a Single Motion Sensor for Accurate and Explainable Soccer Goalkeeper Kinematics has been accepted for publication in the prestigious IEEE Sensors Journal.


This work is part of PERSEUS Project (Platform for Enhanced virtual Reality in Sport Exercise Understanding and Simulation, No. ZF4017410SS9) funded by the Central Innovation Program for Small and Medium-sized Enterprises (ZIM) from the German Federal Ministry for Economic Affairs and Energy (BMWi).


The preprint is available at:

Well done team and collaborators!

ETH – AKII Lab Seminar: Biomechanics and Rehabilitation

On Thursday, the 8th of April 2021, 10:00, AKII Lab hosts a seminar on Biomechanics and Rehabilitation with a great invited talk from a world expert in Robotic Rehabilitation, Dr. Fabian Just


Usability innovations in rehabilitation robotics



In the last 20 years, robotic devices are increasingly used for rehabilitation training of neurological patients. Robots can increase the intensity through adaptive and gamified training while relieving the therapist from hard physical work. Nevertheless, therapists and patients are not able to feel each other and the therapist has only limited possibilities to adapt to the training (i.e. computer interface).
In this talk, I will show the current state of the art in robotic rehabilitation and present novel approaches to increase the usability of rehabilitation robots.



Dr. Fabian Just was a postdoctoral researcher at ETH Zurich and focused on controls, machine learning, and rehabilitation robotics. He developed the fifth version of ARMin, an arm rehabilitation robot specifically designed with intelligent control strategies to enhance the capabilities of therapists.
Fabian received an M.Sc. degree in electrical and computer engineering from Purdue University (IN, USA) in 2013 as well as an M.Sc. degree in automatic control from Ruhr-University Bochum (Germany) in 2014. From 2014 to 2015 he worked at the institute of automation and computer control at Ruhr-University Bochum as a research and teaching assistant.


Just right after, our very own, Mr. Gheorghe Lisca will talk about Leveraging biomechanics assessment with Machine Learning.



The movement of the human body is the result of proper coordination between the three systems: skeletal, muscular, and nervous. The study of human movement pathologies must consider all of them. In vivo studies are limited by the required direct measurements which are difficult to perform and have small sizes. In silico studies show great potential for exploratory studies. This talk will summarize the state of the art in the simulation of the human body neuromusculoskeletal model, and discuss a few research directions for the control of this model.



Gheorghe Lisca is a Ph.D. candidate at THI and AKII Lab researching techniques for the control of the biomechanical models of the human body. In his previous academic activity, he researched Artificial Intelligence for service and social robots at the Technical University of Munich and the University of Bremen in Germany. His entrepreneurial experience includes two co-founded startups and multiple feasibility studies.

Gheorghe received his M.Sc. in Artificial Intelligence and Computer Vision and B.Eng in Computer Science from the Technical University of Cluj-Napoca, Romania.



Loading new posts...
No more posts