arXiv subjects

Szymon Wilk

Publications and source records attributed to Szymon Wilk.

6 recordsLinked to original sources

arXiv2024

Defining Effective Engagement For Enhancing Cancer Patients' Well-being with Mobile Digital Behavior Change Interventions

Digital Behavior Change Interventions (DBCIs) are supporting development of new health behaviors. Evaluating their effectiveness is crucial for their improvement and understanding of success factors. However, comprehensive guidance for developers, particularly in small-scale studies with ethical constraints, is limited. Building on the CAPABLE project, this study aims to define effective engagement with DBCIs for supporting cancer patients in enhancing their quality of life. We identify metrics for measuring engagement, explore the interest of both patients and clinicians in DBCIs, and propose hypotheses for assessing the impact of DBCIs in such contexts. Our findings suggest that clinician prescriptions significantly increase sustained engagement with mobile DBCIs. In addition, while one weekly engagement with a DBCI is sufficient to maintain well-being, transitioning from extrinsic to intrinsic motivation may require a higher level of engagement.

cs.HC↗

arXiv2024

A Hybrid Execution Environment for Computer-Interpretable Guidelines in PROforma

In this paper, we share our experience of developing a hybrid execution environment for computer-interpretable guidelines (CIGs) in PROforma. The proposed environment is part of the CAPABLE system which provides coaching for cancer patients and decision support for physicians. It extends a standard PROforma execution engine - Deontics Engine (DE) - with additional components that act as wrappers around DE, allow handling of non-standard tasks, and facilitate integration with the rest of the CAPABLE system. This yields a hybrid environment in which the standard engine and specialized components must be interfaced together by some intervening layer. In the CAPABLE system this has been achieved by defining a set of specialized meta-properties which are attached to data and tasks in the PROforma CIGs to specify the interface between engine and components.

cs.SE↗

arXiv2023

Can Large Language Models Augment a Biomedical Ontology with missing Concepts and Relations?

Ontologies play a crucial role in organizing and representing knowledge. However, even current ontologies do not encompass all relevant concepts and relationships. Here, we explore the potential of large language models (LLM) to expand an existing ontology in a semi-automated fashion. We demonstrate our approach on the biomedical ontology SNOMED-CT utilizing semantic relation types from the widely used UMLS semantic network. We propose a method that uses conversational interactions with an LLM to analyze clinical practice guidelines (CPGs) and detect the relationships among the new medical concepts that are not present in SNOMED-CT. Our initial experimentation with the conversational prompts yielded promising preliminary results given a manually generated gold standard, directing our future potential improvements.

cs.CL↗

arXiv2023

Personalising Digital Health Behaviour Change Interventions using Machine Learning and Domain Knowledge

We are developing a virtual coaching system that helps patients adhere to behavior change interventions (BCI). Our proposed system predicts whether a patient will perform the targeted behaviour and uses counterfactual examples with feature control to guide personalisation of BCI. We use simulated patient data with varying levels of receptivity to intervention to arrive at the study design which would enable evaluation of our system.

cs.LG↗

arXiv2022

What do you need to consider when designing mobile health intervention?

Designing theory-driven digital health interventions is a challenging task that needs support. We created a guide for the incomers in the field on how to design digital health interventions with case studies from the Cancer Better Life Experience (CAPABLE) European project. The guide explains how behaviour change theories can inform customisation and personalisation of the intervention. The proposed SATO (ideaS expAnded wiTh bciO) design workflow is based on the IDEAS (Integrate, Design, Assess, and Share) framework and is aligned with the Behaviour Change Intervention Ontology (BCIO). We provide a checklist of the activities that should be performed during intervention planning as well as app design templates which bundle together relevant behaviour change techniques. In the process of creating this guide, we found the necessity to extend the BCIO to support the scenarios of multiple clinical goals in the same application. The extension utilizes existing classes and properties where possible.

cs.CY↗

arXiv2021

Tree-based local explanations of machine learning model predictions, AraucanaXAI

Increasingly complex learning methods such as boosting, bagging and deep learning have made ML models more accurate, but harder to understand and interpret. A tradeoff between performance and intelligibility is often to be faced, especially in high-stakes applications like medicine. In the present article we propose a novel methodological approach for generating explanations of the predictions of a generic ML model, given a specific instance for which the prediction has been made, that can tackle both classification and regression tasks. Advantages of the proposed XAI approach include improved fidelity to the original model, the ability to deal with non-linear decision boundaries, and native support to both classification and regression problems

cs.LG↗