A5012783740- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Machine Learning in Healthcare
- Clinical practice guidelines implementation
- Business Process Modeling and Analysis
- Electronic Health Records Systems
- Artificial Intelligence in Healthcare
- Chronic Disease Management Strategies
- Sepsis Diagnosis and Treatment
- Data Mining Algorithms and Applications
- Rough Sets and Fuzzy Logic
- Service-Oriented Architecture and Web Services
- Multi-Agent Systems and Negotiation
- Diabetes Treatment and Management
- Context-Aware Activity Recognition Systems
- Big Data and Business Intelligence
- Web Data Mining and Analysis
- Healthcare Systems and Technology
- Health Systems, Economic Evaluations, Quality of Life
- Intensive Care Unit Cognitive Disorders
- Advanced Database Systems and Queries
- Healthcare Technology and Patient Monitoring
- Respiratory Support and Mechanisms
- Data Quality and Management
- Bayesian Modeling and Causal Inference
Universitat Rovira i Virgili
2013-2023
Institut d'Investigació Sanitària Pere Virgili
2023
Universidad Nacional Autónoma de México
2020
University of Maribor
2011
Universitat Politècnica de Catalunya
1998
Background: Acute respiratory distress syndrome (ARDS) is an intense inflammatory process of the lungs. Most ARDS patients require mechanical ventilation (MV). Few studies have investigated prediction MV duration over time. We aimed at characterizing best early scenario during first two days in intensive care unit (ICU) to predict after onset using supervised machine learning (ML) approaches. Methods: For model description, we extracted data from 3 ICU diagnosis included publicly available...
Abstract Background Usually, arterial oxygenation in patients with the acute respiratory distress syndrome (ARDS) improves substantially by increasing level of positive end-expiratory pressure (PEEP). Herein, we are proposing a novel variable [PaO 2 /(FiO xPEEP) or P/FP E ] for PEEP ≥ 5 to address Berlin’s definition gap ARDS severity using machine learning (ML) approaches. Methods We examined values delimiting boundaries mild, moderate, and severe ARDS. applied ML predict after onset over...
Procedural knowledge in medicine is embedded Clinical Practice Guidelines whose textual condition makes it difficult to share and reuse. Several languages for formal definition of clinical practice guidelines have been proposed overcome these difficulties. In order deal with the huge amount medical situations, use be extensive complex such a way that they, they are used represent, arduous understand manage by non-trained general practitioners. The SDA* model introduced as an alternative...
Background: Accurate planning of the duration stays at intensive care units is utmost importance for resource planning. Currently, discharge date used management calculated only admission time and called length stay. However, evolution treatment may be different from one patient to another, so a recalculation should performed, days discharge. The prediction during stay ICU with statistical data analysis methods has been poorly studied low-quality results. This study aims improve any in using...
We discuss in this paper how the results of discipline known as Knowledge Management could improve some types Environmental Systems. In particular we Decision Support Systems (EDSS). last decade, EDSS emerged a suitable software tool to support control decisiondmaking maximize performance system and minimize negative impact faults. appear necessity for users place guarantees on system's behavior but these methodologies are still underdexplored. paper, first approach put forward Methodology...
Abstract Natural language processing (NLP) has been used to process text pertaining patient records and narratives. However, most of the methods were developed for specific systems, so new research is necessary assess whether such can be easily retargeted applications goals, with same performance. In this paper, open‐source tools are reused as building blocks on which a system built. The aim our work evaluate applicability current NLP technology domain: automatic knowledge acquisition...