Career

Project title: Performance evaluation, prediction and optimization of medical applications on emerging computing infrastructures

Publication date: Jan 4^th 2022

Closing date: Jan 31^st 2022

Level of education: Master's degree

Hours: 40 hours per week

Salary indication: up to 8000 PLN gross monthly

Supervisors:

Sano: dr. Maciej Malawski  (Extreme Scale data and Computing Research Group Leader)

Project start: January 2022 (as soon as a Candidate is selected

Computational medicine applications increasingly rely on artificial intelligence and machine learning. For this reason, AI/ML workloads become more important for Sano and in many computing centers. On the other hand, new hardware and software architectures are emerging: GPUs, IPU, TPU, Quantum (QPU). Examples are new machines at Cyfronet, Lumi, Juelich supercomputing centers and other collaborating institutions. Moreover, there are new computing models including containers or serverless clouds, which often need to use multi-cloud scenarios. This heterogeneity of infrastructures requires careful decisions about resource allocation and management.

The goal of the project will be to conduct performance analysis of application workloads coming from biomedical domain on selected computing infrastructures. This will allow to understand the trade-offs between cost, performance, accuracy, scalability, resource utilization, application turnaround times and other metrics. The gathered performance data will be used to build machine learning models for predicting the performance of applications and to optimize their execution with respect to selected criteria.

We are looking for an experienced:

 Scientific Programmer – Personal Health Research Group

You will help turn scientific vision into tangible solutions for clinicians and biologists. Output of your high-quality code will be published in popular journals, and will propel new healthcare products. You will work with industrial researchers to bring Sano’s technology to hospitals and patients. 

You will join the team dedicated to behavioural science and data analytics on population health data and other types of data (e.g. wearables) to identify health risks, trends, inefficiencies, vulnerable populations, patient subgroups and investigate potential population-wide interventions.

As a member of a team at a rapidly developing institute, you will have important impact on how Sano will evolve, and how it will go about meeting its strategic objectives in the long run. If you enjoy creating things, helping organisations and people grow, and contributing to workplace culture while accepting that some elements are in flux, and adaptation to an evolving environment is important, then you are the kind of person we would like to talk to.

We expect a full-time, long-term commitment to ensure continuity within the team (taking software developed by/with a PhD/MSc student, and handing it over to another student);

We are looking for an experienced:

 Scientific Programmer – Modelling and Simulation Research Group

You will help turn scientific vision into tangible solutions for clinicians and biologists. Output of your high-quality code will be published in leading journals and will propel new healthcare products. You will work with industrial researchers to bring Sano’s science and technology to hospitals and patients. 

You will join the team dedicated to development of models and mechanisms to model and simulate physiological processes relevant to diagnosis and therapy as well as applications in the area of in silico clinical trials.

As a member of a team at a rapidly developing institute, you will have important impact on how Sano will evolve, and how it will go about meeting its strategic objectives in the long run. If you enjoy creating things, helping organisations and people grow, and contributing to workplace culture while accepting that some elements are in flux, and adaptation to an evolving environment is important, then you are the kind of person we would like to talk to.

We expect a full-time, long-term commitment to ensure continuity within the team (e.g. taking software developed by/with a PhD/MSc student, and handing it over to another student);

Project title: Data abstractions as the foundation of machine self-learning from different data sources

Publication date: 22.10.2021

Closing date: 31.12.2021

Level of education: Master's degree

Hours: 40 hours per week

Salary indication: up to 8000 PLN gross monthly

Supervisors:

Sano: Dr. Jose Sousa (Research Group Leader – Personal Health Data Science)

Project start: January 2022 (depending on candidate’s availability)

Data is at the forefront of any process of decision making, as if there was any doubt, the actual pandemic made it clear. Data collection happens every day with individual contribution from browsing keywords to the sharing of images and feelings. This created a promised that if you collect enough data to generate big data, machines will be able to model the world and provide unique insights. However, the reality is not perfect and collecting “all the data” to describe a problem is impossible within a chaotic reality. One of the most promising approaches to the development of personalized medicine became siloed in machine learning applied to single diseases because of the difficulty on accessing and integrating data sources. This is closed related and defines the evolution of the actual approaches on machine learning.

Within this PhD, algorithms will be built to develop data abstraction in the local systems and upload them to the machine self-learning environment. This would allow the integration of different data sources in a way not done until now allowing the evolution of machine learning.

The project will be carried out in cooperation in computer scientists and machine learning from Sano and its partners and data sources providers such as polish hospitals and develop collaborations to explore data repositories in the UK and in Europe.

Project title: Machine self-learning from self-reported data using knowledge graphs

Publication date: 19.11.2021

Closing date: 31.12.2021

Level of education: PhD

Hours: 40 hours per week

Salary indication: up to 12000 PLN gross monthly

Supervisor:

Sano: Dr. Jose Sousa (Research Group Leader)

Project period: 2 years (e.g. January 2022 - January 2024)

Humans’ behaviour is at the centre of the capability of Personal Health Data Science to impact evidence-based outcomes with self-reported data as a fundamental asset for that evidence. However, its use within machine learning processes is challenging, because self-reported data is noisy, volatile, and diverse while actual machine learning algorithms need clean, classified, and homogenous data, preferably in a silo, and within a single dimension approach.

The challenge for machine learning is then to be able to use self-reported data to allow a better understanding of individual health in a process from population to the individual. To use this data, we will focus on developing machine self-learning algorithms that overcome the human need to classify data and to build this we are going to start from knowledge graphs produced using machine self-learning capable to describe diseases, such as diabetes, obesity, dementia, or aged related macular degeneration (AMD) and aim for the development of a machine self-learning approach to support personalized decision making.

This would allow the development of policies and frameworks fitted to change behavior which is a central element to reduce the burden of these diseases on the health care systems. With this project we will develop the machine self-learning algorithms to create personal evidence on individual multiple long-term conditions (MLTC) also known as multimorbidity’s.

This project will be carried out in cooperation with machine learning and AI scientists at SANO and its partners and by developing external collaborations with Krakow health providers and with UK and Portuguese Universities.

Project title: Citizen before patient and the creation of the personal evidence-based decision-making ecosystem – step 1

Publication date: 19.11.2021

Closing date: 31.12.2021

Level of education: PhD

Hours: 40 hours per week

Salary indication: up to 12000 PLN gross monthly

Supervisor:

Sano: Dr. Jose Sousa (Research Group Leader)

Project period: 2 years (e.g. January 2022 - January 2024)

The effects of risky behaviors, like smoking, obesity and drinking are reflected on the development of non-communicable disease. The World Health Organization (WHO) reports that the noncommunicable diseases (NCDs) kill 41 million people the equivalent to 71% of all deaths globally. Behavioral risk factors account for almost half of all deaths in Poland. Detection, screening, and treatment of NCDs, as well as palliative care, are key components of the response to NCDs.

Citizenship is described as one of the main factors to enhance human quality of life (QoL) and drive change, however in the health care sector the citizen empowerment is often disregarded. Due to its effects and impacts, the health decision making process relies on experts delivering solutions while not empowering individuals’ choice on its health path. It’s well known that no one likes to be forced, to stop smoking, change diet, and ultimately change behavior, as we are seeing in the actual pandemic.

However, when evidence is given, and a choice is provided individual citizenship becomes crowdsourcing to tackle big problems. No one wants to be a patient if it can have the evidence to choose not to be it with small nudges. From this concept and building on machine self-learning a personal health architecture of choice is needed to create evidence on the health path and provide nudge effects to empower individual change within an AI self-learning architecture of choice. With this project we are doing the first step.

This project will be carried out in cooperation with machine learning and AI scientists from Sano and its partners and experience from hospitals and industry, including a pharmaceutical company specialized in biomarkers testing.

Project title: The Role of Structural and Functional Heterogeneity in Digital Twin Hearts

Publication date:

Closing date:

Level of education required: Master's degree

Hours: 40 hours per week

Salary indication: up to PLN 8000 gross monthly

Supervisors:

Sano: Dr Zbigniew R. Struzik (Modelling and Simulation Research Group Leader)

Project start: April 2022

Degree Awarding Institution:

The primary question to be addressed in this project is whether electrophysiological heterogeneity at both structural and functional levels can be incorporated in digital cohort/twin models of the whole human heart. If so, how are we to approach this in Digital Twin models considering two particular examples of inhomogeneous conductance:

i)            that due to the arrangement of myocardial fibres;

ii)           that due to the Purkinje network.

The aim is to investigate the degree to which structural and functional heterogeneity of conductance at the tissue level affects organ (system) level cardiac dynamics. To this end, methodologies should be devised with the purpose of implementing such heterogeneity using realistic parameterized models and investigating the resultant system dynamics. The phase space of system behaviour is to be discerned and quantified, including specific sensitivity to key parameters in order to provide guidelines on how to incorporate heterogeneity at tissue level in the preparation of patient specific Digital Twin Hearts.

Automatic generation methods and software tools drawing on data available from atlases, ex vivo scanning data and possible imaging techniques anticipated to be available in the near future must be prepared. This is particularly important for identifying the parameters and parameter ranges capturing most controllability/sensitivity in the system, and is thus deemed absolutely essential for the success of the personalized Digital Twin Hearts.

Project title: The Role of Neurocardiac Interaction in Arrhythmic Digital Twin Hearts

Publication date:

Closing date:

Level of education required: Master's degree

Hours: 40 hours per week

Salary indication: up to PLN 8000 gross monthly

Supervisors:

Sano: Dr Zbigniew R. Struzik (Modelling and Simulation Research Group Leader)

Project start: April 2022

Degree Awarding Institution:

The primary question to be addressed in this project is whether neurocardiac interaction at both Autonomic Nervous System (ANS) level and Intrinsic Cardiac Nervous System (ICNS) level can be incorporated in digital cohort/twin models of the whole human heart, in particular those developing arrhythmias. If so, how are we to approach this in Digital Twin models, given sparse information about both the ANS and ICNS at an individual patient level.

Understanding the role that the ICNS plays in controlling cardiac function, and how it interacts with information between the central command centres of the ANS and integrates sensory information from the myocardium could prove crucial for prophylactic and corrective treatments of heart disease. In particular, clusters of cardiac ganglia neurons located on the surface of the heart, collectively termed ganglionated plexuses (GP), are known to be involved in arrhythmias. An array of imaging, modelling and simulation studies should be devised to address the question of whether Digital Twin Heart modelling can incorporate and will benefit from ANS and ICNS control insights. In particular, can we incorporate knowledge of the structure and function of the Intrinsic Nervous System to provide better modelling of arrhythmias? Further, can this knowledge be used to provide guidance in (optimal) ablation of the ganglionated plexuses?