A5040369618- Electronic Health Records Systems
- Clinical practice guidelines implementation
- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Machine Learning in Healthcare
- Rough Sets and Fuzzy Logic
- Imbalanced Data Classification Techniques
- Chronic Disease Management Strategies
- Digital Mental Health Interventions
- Machine Learning and Data Classification
- Business Process Modeling and Analysis
- Mobile Health and mHealth Applications
- Data Mining Algorithms and Applications
- Artificial Intelligence in Healthcare
- Context-Aware Activity Recognition Systems
- Multi-Agent Systems and Negotiation
- Health Systems, Economic Evaluations, Quality of Life
- Diabetes Treatment and Management
- Explainable Artificial Intelligence (XAI)
- Cancer survivorship and care
- Statistical and Computational Modeling
- Anomaly Detection Techniques and Applications
- COVID-19 and Mental Health
- Topic Modeling
- Healthcare Technology and Patient Monitoring
Poznań University of Technology
2015-2024
University of Pavia
2021
University of Ottawa
2008-2020
Wilfrid Laurier University
2009-2020
Institute of Computer Science
2017
Children's Hospital of Eastern Ontario
2009
City, University of London
2009
Increasingly complex learning methods such as boosting, bagging and deep have made ML models more accurate, but harder to interpret explain, culminating in black-box machine models. Model developers users alike are often presented with a trade-off between performance intelligibility, especially high-stakes applications like medicine. In the present article we propose novel methodological approach for generating explanations predictions of generic model, given specific instance which...
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 (indexing retrieving medical evidence we posit that the use PICO allows organizing aligned with MD's decision model. describe study where students...
Summary Background: Asthma exacerbations are one of the most common medical reasons for children to be brought hospital emergency department (ED). Various prediction models have been proposed support diagnosis and evaluation their severity. Objectives: First, evaluate constructed from data using machine learning techniques select best performing model. Second, compare predictions selected model with Pediatric Respiratory Assessment Measure (PRAM) score, made by ED physicians. Design: A...
The adoption of the advanced data analytics methods has been limited in industries governed by strict reuse regulations, such as healthcare. Barriers to access and sharing have affected numerous research development initiatives healthcare resulting major delays, extensive use resources for findings originating from datasets that are too small be generalizable. Federated machine learning presents a solution problems health projects facing providing way complying with regulatory requirements...
Our objective was to design and develop a mobile clinical decision support system for emergency triage of different acute pain presentations. The should interact with existing hospital information systems, run on computing devices (handheld computers) be suitable operation in weak-connectivity conditions (with unstable connections between clients server).The MET (Mobile Emergency Triage) designed following an extended client-server architecture. client component, responsible support, is...
Summary Objectives: The objective of this research was to design a clinical decision support system (CDSS) that supports heterogeneous problems and runs on multiple computing platforms. Meeting required novel create an extendable easy maintain CDSS for point care support. proposed solution evaluated in proof concept implementation. Methods: Based our earlier with the mobile emergency triage we used ontology-driven represent essential components CDSS. Models were derived from ontology they...
The purpose of this study was to create a task-based support architecture for developing clinical decision systems (CDSSs) that assist physicians in making decisions at the point-of-care emergency department (ED). backbone proposed established by workflow model patient-physician encounter.The designed according an agent-oriented paradigm. Specifically, we used O-MaSE (Organization-based Multi-agent System Engineering) method allows iterative translation functional requirements into...