Szymon Wilk

Szymon Wilk
Poznan University of Technology · Institute of Computing Science

About

143
Publications
18,838
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,089
Citations

Publications

Publications (143)
Chapter
Automated machine learning (AutoML) has made life easier for data analysts or scientists by providing quick insights into data by building machine learning (ML) models. AutoML techniques are applied to vast areas from image processing, speech recognition, natural language processing reinforcement learning, and more. However, there is still room for...
Chapter
Treatment of patients with multimorbidity is one of the greatest challenges for clinical decision support. While evidence-based management of specific diseases is supported by clinical practice guidelines, concurrent application of multiple guidelines requires checking for possible adverse interactions between interventions and mitigating them, bef...
Preprint
Full-text available
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 a...
Article
Full-text available
Current research on imbalanced data recognises that class imbalance is aggravated by other data intrinsic characteristics, among which class overlap stands out as one of the most harmful. The combination of these two problems creates a new and difficult scenario for classification tasks and has been discussed in several research works over the past...
Article
Multimorbidity, the coexistence of two or more health conditions, has become more prevalent as mortality rates in many countries have declined and their populations have aged. Multimorbidity presents significant difficulties for Clinical Decision Support Systems (CDSS), particularly in cases where recommendations from relevant clinical guidelines o...
Chapter
Adherence to therapy is one of the major determinants of therapy success, while non-adherence leads to worsening of patient condition and increased healthcare costs. The aim of our work is to evaluate therapies recommended by a clinical practice guideline in order to select a therapy that is most suited for a patient’s adherence profile and account...
Preprint
Full-text available
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...
Article
Full-text available
The adoption of the advanced data analytics methods has been limited in industries governed by strict data reuse regulations, such as healthcare. Barriers to data access and sharing have affected numerous research and development initiatives in healthcare resulting in major delays, extensive use of resources for data access and findings originating...
Article
Full-text available
We propose a methodological framework to support the development of personalized courses that improve patients’ understanding of their condition and prescribed treatment. Inspired by Intelligent Tutoring Systems (ITSs), the framework uses an eLearning ontology to express domain and learner models and to create a course. We combine the ontology with...
Chapter
The complexity of patient care is growing due to an ageing population. As chronic illnesses become more common, the incidence of multi-morbidity increases. Generating disease management plans for multi-morbid patients requires the integration of multiple evidence-based interventions, represented as clinical practice guidelines (CPGs), that are desi...
Chapter
The CAPABLE project aims to improve the wellbeing of cancer patients managed at home via a coaching system recommending personalized evidence-based health behavioral change interventions and supporting patients compliance. Focusing on managing stress via deep breathing intervention, we hypothesise that the patients are more likely to perform sugges...
Chapter
The CAncer PAtient Better Life Experience (CAPABLE) project combines the most advanced technologies for data and knowledge management with a socio-psychological approach, to develop a coaching system for improving the quality of life of cancer patients managed at home. The team includes complementary expertise in data- and knowledge-driven AI, data...
Chapter
Full-text available
The CAPABLE project has been funded by the EU Horizon 2020 Programme over the years 2020-24 to support home care. A system is being designed and implemented supporting remote monitoring and virtual coaching for cancer patients. The system is based on a distributed modular architecture involving many components encapsulating various knowledge. The C...
Article
Full-text available
Introduction Thanks to improvement of care, cancer has become a chronic condition. But due to the toxicity of treatment, the importance of supporting the quality of life (QoL) of cancer patients increases. Monitoring and managing QoL relies on data collected by the patient in his/her home environment, its integration, and its analysis, which suppor...
Article
Full-text available
The paper describes a computer tool dedicated to the comprehensive analysis of lung changes in computed tomography (CT) images. The correlation between the dose delivered during radiotherapy and pulmonary fibrosis is offered as an example analysis. The input data, in DICOM (Digital Imaging and Communications in Medicine) format, is provided from CT...
Article
As the population ages, patients’ complexity and the scope of their care is increasing. Over 60% of the population is 65 years of age or older and suffers from multi-morbidity, which is associated with two times as many patient-physician encounters. Yet clinical practice guidelines (CPGs) are developed to treat a single disease. To reconcile these...
Chapter
Full-text available
In healthcare domains, dealing with missing data is crucial since absent observations compromise the reliability of decision support models. K-nearest neighbours imputation has proven beneficial since it takes advantage of the similarity between patients to replace missing values. Nevertheless, its performance largely depends on the distance functi...
Preprint
Full-text available
Introduction - Thanks to improvement of care, cancer has become a chronic condition. But due to the toxicity of treatment, the importance of supporting the quality of life (QoL) of cancer patients increases. Monitoring and managing QoL relies on data collected by the patient in his/her home environment, its integration, and its analysis, which supp...
Article
Full-text available
When deciding about surgical treatment options, an important aspect of the decision-making process is the potential risk of complications. A risk assessment performed by a spinal surgeon is based on their knowledge of the best available evidence and on their own clinical experience. The objective of this work is to demonstrate the differences in th...
Technical Report
Full-text available
The 2020 International Workshop on Health Intelligences is held in conjunction with AAAI-20 on Feb 7, 2020, in New York City, NY USA.
Article
Background and purpose: Teamwork has become a modus operandi in healthcare and delivery of patient care by an interdisciplinary healthcare team (IHT) is now a prevailing modality of care. We argue that a formal and automated support framework is needed for an IHT to properly leverage information technology resources. Such a framework should allow...
Article
Full-text available
Objectives: Machine learning models have been used to predict mortality among patients requiring rapid response team activation. The goal of our study was to assess the impact of adding laboratory values into the model. Design: A gradient boosted decision tree model was derived and internally validated to predict a primary outcome of in-hospital...
Article
Full-text available
A prominent characteristic of clinical data is their heterogeneity - such data include structured examination records and laboratory results, unstructured clinical notes, raw and tagged images, and genomic data. This heterogeneity poses a formidable challenge while constructing diagnostic and therapeutic decision models that are currently based on...
Technical Report
The third AAAI Health Intelligence workshop, held in conjunction with the 33rd AAAI Conference on Artificial Intelligence (AAAI-19) on Jan 27 - Feb 1, 2019, at the Hilton Hawaiian Village in Honolulu, Hawaii, USA, addresses various aspects of using AI for improving population and personalized healthcare and is structured in two tracks focusing on p...
Book
This book constitutes the refereed proceedings of the 17th Conference on Artificial Intelligence in Medicine, AIME 2019, held in Poznan, Poland, in June 2019. The 22 revised full and 31 short papers presented were carefully reviewed and selected from 134 submissions. The papers are organized in the following topical sections: deep learning; simulat...
Article
Full-text available
Regardless of potential benefits and better outcomes, adoption of shared decision-making between a patient and providers involved in his/her care is still in its infancy. This paper intends to fill this gap by formalizing shared decision-making, situating it as part of team-based care delivery, and incorporating workflow concepts allowing for ident...
Conference Paper
Full-text available
Regardless of potential benefits and better outcomes, adoption of shared decision-making between a patient and providers involved in his/her care is still in its infancy. This paper intends to fill this gap by formalizing shared decision-making, situating it as part of team-based care delivery, and incorporating workflow concepts allowing for ident...
Article
Full-text available
Poor patient compliance to therapy results in a worsening condition that often increases healthcare costs. In the MobiGuide project, we developed an evidence-based clinical decision-support system that delivered personalized reminders and recommendations to patients, helping to achieve higher therapy compliance. Yet compliance could still be improv...
Conference Paper
Progress in medical imaging and computer vision has enabled us to rely on machines for the detection or diagnosis of many diseases, including eye-related problems. One of them is wet age-related macular degeneration (wet AMD) which is a type of age-related macular degeneration. Wet AMD causes the detachment of retinal pigment epithelium layer (RPE)...
Book
This workshop will address various aspects of using AI for improving population and personalized healthcare and is structured in two tracks focusing on population (W3PHI) and personalized health (HIAI). Following the success of AAAI-W3PHI 2014-16, AAAI-HIAI 2013-16, and the first joint workshop at AAAI-17 (W3PHIAI-17), this workshop aims to bring t...
Article
Full-text available
Interdisciplinary healthcare teams (IHTs) are involved in clinical processes composed of tasks requiring specific capabilities from different disciplines, often executed at different times. Although some hospitals use Business Process Management (BPM) suites to support their clinical activities, these tools are often unable to support the dynamic a...
Article
Full-text available
The AAAI-17 workshop program included 17 workshops covering a wide range of topics in AI. Workshops were held Sunday and Monday, February 4-5, 2017 at the Hilton San Francisco Union Square in San Francisco, California, USA. This report contains summaries of 12 of the workshops, and brief abstracts of the remaining 5.
Conference Paper
Clinical data is characterized not only by its constantly increasing volume but also by its diversity. Information collected in clinical information systems such as electronic health records is highly heterogeneous and it includes structured laboratory and examination reports, unstructured clinical notes, images, and more often genetic data. This h...
Conference Paper
Full-text available
Computer-interpretable implementations of clinical guidelines (CIGs) add knowledge that is outside the scope of the original guideline. This knowledge can customize CIGs to patients’ psycho-social context or address comorbidities that are common in the local population, potentially increasing standardization of care and patient compliance. We devel...
Conference Paper
In this paper we propose a new algorithm called SPIDER3 for selective preprocessing of multi-class imbalanced data sets. While it borrows selected ideas (i.e., combination of relabeling and local resampling) from its predecessor – SPIDER2, it introduces several important extensions. Unlike SPIDER2, it is able to handle directly multi-class problems...
Technical Report
The First Joint AAAI Workshop on Health Intelligence (W3PHIAI 2017) was held in San Francisco, California, on February 4-5, 2017. This workshop follows the success of AAAI-W3PHI 2014 in Québec City, Québec, Canada, AAAI-W3PHI 2015 in Austin, Texas, USA, AAAI-W3PHI 2016 in Phonix, Arizona, USA and HIAI 2013-2016 held in conjunction with the twenty-s...
Technical Report
The First Joint AAAI Workshop on Health Intelligence (W3PHIAI 2017) was held in San Francisco, California, on February 4-5, 2017. This workshop follows the success of AAAI-W3PHI 2014 in Québec City, Québec, Canada, AAAI-W3PHI 2015 in Austin, Texas, USA, AAAI-W3PHI 2016 in Phonix, Arizona, USA and HIAI 2013-2016 held in conjunction with the twenty-s...
Article
Full-text available
In this paper we describe results of an experimental study where we checked the impact of various difficulty factors in imbalanced data sets on the performance of selected classifiers applied alone or combined with several preprocessing methods. In the study we used artificial data sets in order to systematically check factors such as dimensionalit...
Article
In this work we propose a comprehensive framework based on first-order logic (FOL) for mitigating (identifying and addressing) interactions between multiple clinical practice guidelines (CPGs) applied to a multi-morbid patient while also considering patient preferences related to the prescribed treatment. With this framework we respond to two funda...
Article
Full-text available
Background: A significant challenge associated with practicing evidence-based medicine is to provide physicians with relevant clinical information when it is needed. At the same time it appears that the notion of relevance is subjective and its perception is affected by a number of contextual factors. Objectives: To assess to what extent physici...
Chapter
In this paper we describe an experimental study where we analyzed data difficulty factors encountered in imbalanced clinical data sets and examined how selected data preprocessing methods were able to address these factors. We considered five data sets describing various pediatric acute conditions. In all these data sets the minority class was spar...
Article
Full-text available
In healthcare organizations, clinical workflows are executed by interdisciplinary healthcare teams (IHTs) that operate in ways that are difficult to manage. Responding to a need to support such teams, we designed and developed the MET4 multi-agent system that allows IHTs to manage patients according to presentation-specific clinical workflows. In t...
Article
Full-text available
The increasing prevalence of multimorbidity is a challenge for physicians who have to manage a constantly growing number of patients with simultaneous diseases. Adding to this challenge is the need to incorporate patient preferences as key components of the care process, thanks in part to the emergence of personalized and participatory medicine. In...
Conference Paper
The increasing prevalence of multimorbidity is a challenge for physicians who have to manage a constantly growing number of patients with simultaneous diseases. Adding to this challenge is the need to incorporate patient preferences as key components of the care process, thanks in part to the emergence of personalized and participatory medicine. In...
Article
We propose a novel approach to the problem of the classification with test costs understood as costs of obtaining attribute values of classified examples. Many existing approaches construct classifiers in order to control the tradeoff between test costs and the prediction accuracy (or misclassification costs). The aim of the proposed method is to r...
Article
The use of business workflow models in healthcare is limited because of insufficient capture of complexities associated with behavior of interdisciplinary healthcare teams that execute healthcare workflows. In this paper we present a novel framework that builds on the well-founded business workflow model formalism and related infrastructures and in...
Article
Full-text available
In the paper we describe a sequential classification scheme that iteratively explores levels of abstraction in the description of examples. These levels of abstraction represent attribute values of increasing precision. Specifically, we assume attribute values constitute an ontology (i.e., attribute value ontology) reflecting a domain-specific back...
Article
Full-text available
Clinical practice guidelines (CPGs) implement evidence-based medicine designed to help generate a therapy for a patient suffering from a single disease. When applied to a comorbid patient, the concurrent combination of treatment steps from multiple CPGs is susceptible to adverse interactions in the resulting combined therapy (i.e., a therapy establ...
Article
Full-text available
Participatory medicine refers to the equal participation of patients and interdisciplinary healthcare team (IHT) members as part of care delivery. Facilitating workflow execution is a significant challenge for participatory medicine because of the need to integrate IHT members into a common workflow. A further challenge is that patient preferences...
Conference Paper
Full-text available
This paper describes MET4, a multi-agent system that supports interdisciplinary healthcare teams (IHTs) in executing patient care workflows. Using the concept of capability, the system facilitates the maintenance of an IHT and assignment of workflow tasks to the most appropriate team members. Moreover, following the principles of participatory medi...
Conference Paper
Clinical practice guidelines (CPGs) were originally designed to help with evidence-based management of a single disease and such a single disease focus has impacted research on CPG computerization. This computerization is mostly concerned with supporting different representation formats and identifying potential inconsistencies in the definitions o...
Article
Background: Online medical knowledge repositories such as MEDLINE and The Cochrane Library are increasingly used by physicians to retrieve articles to aid with clinical decision making. The prevailing approach for organizing retrieved articles is in the form of a rank-ordered list, with the assumption that the higher an article is presented on a l...
Article
Objectives Despite many clinical decision support systems (CDSSs) being rated as highly usable, CDSSs have not been widely adopted in clinical practice. We posit that there are factors aside from usability that impact adoption of CDSSs; in particular we are interested in the role played by MDs intrinsic motivation to use computer-based support. Our...
Article
We consider a classification process, that the representation precision of new examples is interactively increased. We use an attribute value ontology (AVO) to represent examples at different levels of abstraction (levels of precision). This precision can be improved by conducting diagnostic tests. The selection of these diagnostic tests is general...
Article
Asthma exacerbations are one of the most common medical reasons for children to be brought to the hospital emergency department (ED). Various prediction models have been proposed to support diagnosis of exacerbations and evaluation of their severity. First, to evaluate prediction models constructed from data using machine learning techniques and to...
Article
Managing a patient with comorbid diseases according to multiple clinical practice guidelines (CPGs) may result in adverse interactions that need to be mitigated (identified and addressed) so a safe therapy can be devised. However, mitigation poses both clinical and methodological challenges. It requires extensive domain knowledge and calls for adva...
Article
Modern medicine is characterized by an "explosion" in clinical research information making practical application of Evidence-Based Medicine (EBM), problematic for many clinicians. We have developed a PICO-(evidence based search strategy focusing on Patient/Population, Intervention, Comparison and Outcome)-based framework for (indexing and retrievin...
Conference Paper
Full-text available
There is a pressing need in clinical practice to mitigate (iden-tify and address) adverse interactions that occur when a comorbid pa-tient is managed according to multiple concurrently applied disease-specific clinical practice guidelines (CPGs). In our previous work we described an automatic algorithm for mitigating pairs of CPGs. The algorithm co...