About
Jakub is a Research Engineer at the IT Innovation Centre, within the Department of Electronics and Computer Science (ECS) at the University of Southampton.
With over four years of experience in applied research across healthcare, technology, and agriculture, he specialises in data-driven approaches using Artificial Intelligence (AI) and Machine Learning (ML). His primary focus is on Health Informatics, and his impactful work has led to a nomination for the Engineers in Society Award by the Institute of Engineering and Technology (IET).
Jakub’s research contributes to numerous high-profile projects. He leverages Large Language Models (LLMs) and Natural Language Processing (NLP) for clinical applications, including medical coding automation and data harmonisation (MELDB, AIM-NLP). Additionally, he develops AI-driven risk models and decision-support frameworks for conditions such as hypertension (MEMBAH), type-1 diabetes (COTADs), COPD (mySmartCOPD), and oesophageal cancer. Beyond healthcare, his AI expertise also extends to optimising agricultural sustainability through the FertilizerAI project.
You can update this in Pure (opens in a new tab). Select ‘Edit profile’. Under the heading and then ‘Curriculum and research description’, select ‘Add profile information’. In the dropdown menu, select - ‘About’.
Write about yourself in the third person. Aim for 100 to 150 words covering the main points about who you are and what you currently do. Clear, simple language is best. You can include specialist or technical terms.
You’ll be able to add details about your research, publications, career and academic history to other sections of your staff profile.
Research
Research interests
- Natural Language Processing (NLP) and Large Language Models (LLMs) for Healthcare
- Artificial Intelligence (AI) in Health Informatics and Clinical Decision Support
- Data Harmonisation and Automated Medical Phenotyping
Current research
Jakub's current research sits at the intersection of health informatics, natural language processing and machine learning, with a focus on turning routinely collected health data into meaningful insight for people living with multiple long-term conditions (MLTCs).
Natural Language Processing for Clinical Research
Jakub focuses on applying natural language processing (NLP) and pretrained language models to solve one of the biggest bottlenecks in observational health research: harmonising inconsistent clinical data across studies.
As health datasets grow in volume and diversity, comparing findings across cohorts requires aligning variables that are labelled and structured differently between studies. This work develops a semantics-aware, language-model-based approach to automate and scale this harmonisation process, making multi-cohort and multi-study clinical research faster and more reproducible.
- Pretrained language models for semantics-aware data harmonisation of observational clinical studies in the era of big data BMC Medical Informatics and Decision Making, 2025
Multimorbidity and the Lived Experience of Multiple Long-Term Conditions
Jakub investigates how multimorbidity (living with two or more long-term health conditions) is experienced, measured, and reported across health and social care systems in the UK.
Much of my research addresses a core problem in multimorbidity science: routine electronic health records (EHRs) capture diagnoses and contacts, but often fail to capture the lived burden of managing multiple conditions simultaneously. This theme includes work establishing large-scale data resources for this purpose, such as the SAIL MELD-B e-cohorts, which link population-scale linked data to study "burdensomeness" in both adults and children alongside analyses of variation in social care need reporting among GP practices, and methodological work using informatics techniques to cluster and profile the "burden space" of people under 65 with multiple conditions. A related paper examines why the human impact of MLTC frequently gets "lost in translation" between patient experience and what is recorded in routine data.
- Variations in social care need reporting amongst GP practices in England: a retrospective cohort study in people with multimorbidity BMC Primary Care, 2025
- An informatics approach to profiling patient experiences using electronic health records: constructing and clustering the burden space of individuals under 65 with multiple long-term conditions Working paper, 2025
- Capturing the human impact of living with multiple long-term conditions in routine electronic health records – lost in translation? Journal of Multimorbidity and Comorbidity, 2025
- Cohort profile: the creation of the SAIL MELD-B e-cohort (SMC) and SAIL MELD-B children and young adult e-cohort (SMYC) BMJ Open, 2025
Machine Learning and Co-Design for Diabetes Management
Jakub applies machine learning to type 1 diabetes management and explores how patients, family carers, and clinicians can be meaningfully involved in designing the ML tools built to support them.
Work here spans both technical and participatory methods: developing machine learning models to predict glucose levels from continuous glucose monitoring (CGM) data, and using computational notebooks as a co-design tool to engage young adults with diabetes, their carers, and clinicians directly in shaping how these predictive models are built and used.
- Computational notebooks as co-design tools: engaging young adults living with diabetes, family carers, and clinicians with machine learning models CHI'23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
- Machine learning based prediction of glucose levels in Type 1 diabetes patients with the use of continuous glucose monitoring data Working paper, 2023
You can update the information for this section in Pure (opens in a new tab).
Research groups
Any research groups you belong to will automatically appear on your profile. Speak to your line manager if these are incorrect. Please do not raise a ticket in Ask HR.
Research interests
Add up to 5 research interests. The first 3 will appear in your staff profile next to your name. The full list will appear on your research page. Keep these brief and focus on the keywords people may use when searching for your work. Use a different line for each one.
In Pure (opens in a new tab), select ‘Edit profile’. Under the heading 'Curriculum and research description', select 'Add profile information'. In the dropdown menu, select 'Research interests: use separate lines'.
Current research
Update this in Pure (opens in a new tab). Select ‘Edit profile’ and then ‘Curriculum and research description - Current research’.
Describe your current research in 100 to 200 words. Write in the third person. Include broad key terms to help people discover your work, for example, “sustainability” or “fashion textiles”.
Research projects
Research Council funded projects will automatically appear here. The active project name is taken from the finance system.
Publications
Public outputs that list you as an author will appear here, once they’re validated by the ePrints Team. If you’re missing any outputs that you’ve added to Pure, they may be waiting for validation.
Supervision
A list of your current and past PhD students.
This section will only display on your public profile if content has been added.
Contact your Faculty Operating Service team to update PhD students you supervise and any you’ve previously supervised. Making this information available will help potential PhD applicants to find you.
Teaching
A short description of your teaching interests and responsibilities.
This section will only display on your public profile if you’ve added content.
You can update your teaching description in Pure (opens in a new tab). Select ‘Edit profile’. Under the heading and then ‘Curriculum and research description’ , select ‘Add profile information’. In the dropdown menu, select – ‘Teaching Interests’. Describe your teaching interests and your current responsibilities. Aim for 200 words maximum.
Courses and modules
Contact the Curriculum and Quality Assurance (CQA) team for your faculty to update this section.
External roles and responsibilities
These are the public-facing activities you’d like people to know about.
This section will only display on your public profile if you’ve added content.
You can update your external roles and responsibilities in Pure (opens in a new tab). Select ‘+ Add content’ and then ‘Activity’, your ‘Personal’ tab and then ‘Activities’. Choose which activities you want to show on your public profile.
You can hide activities from your public profile. Set the visibility as 'Backend' to only show this information within Pure, or 'Confidential' to make it visible only to you.
Biography
A chance to go into more detail about your work and interests.
This section will only display on your public profile if you’ve added content.
You can update your biography section in Pure (opens in a new tab). Select your ‘Personal’ tab then ‘Edit profile’. Under the heading, and ‘Curriculum and research description’, select ‘Add profile information’. In the dropdown menu, select - ‘Biography’. Aim for no more than 400 words.
This section will only appear if you enter the information into Pure (opens in a new tab).
Prizes
You can update this section in Pure (opens in a new tab). Select ‘+Add content’ and then ‘Prize’. using the ‘Prizes’ section.
You can choose to hide prizes from your public profile. Set the visibility as ‘Backend’ to only show this information within Pure, or ‘Confidential’ to make it visible only to you.