IWBBIO 2017 special session
Aims & Scope
Decision making in healthcare at clinical environments is often made on the basis of multiple parameters and in the context of patient presentation, which includes the setting and the specific conditions related to the reason for admission and the procedures involved. The data used in clinical decision-making may originate from manifold sources and at multiple scales: devices in and around the patient, laboratory, blood tests, omics analyses, medical images, and ancillary information available both prior to and during the hospitalization.
Arguably, one of the most data dependent clinical environments is the intensive care unit (ICU). The ICU environment cares for acutely ill patients. Many patients within the ICU environments, and particularly surgical intensive care units (SICU), are technologically dependent on the life-sustaining devices that surround them. Some of these patients are indeed dependent for their very survival on technologies such as infusion pumps, mechanical ventilators, catheters and so on. Beyond treatment, assessment of prognosis in Critical Care and patient stratification combining different data sources is extremely important in a patient-centric environment.
With the advent and quick uptake of omics technologies in Critical Care, the use of data-based approaches for assistance in diagnosis and prognosis becomes paramount. New approaches to data analysis are thus required, and some of the most interesting ones are currently stemming from the fields of Computational Intelligence (CI) and Machine Learning (ML). This session is particularly interested in the proposal of novel CI and ML approaches and in the discussion of the challenges for the application of the existing ones to problems in Critical Care.
Topics that are of interest to this session include (but are not necessarily limited to):
· Novel applications of existing CI and ML and advanced statistical methods in Critical Care.
· Novel CI and ML techniques for Critical Care.
· CI and ML-based methods to improve model interpretability in a Critical Care context, including data/model visualization techniques.
· Novel CI and ML techniques for dealing with non-structured and heterogeneous data formats in Critical Care.
Alfredo Vellido, PhD.
Dept. of Computer Science, Universitat Politècnica de Catalunya, BarcelonaTECH (UPC), Barcelona, Spain.
Vicent Ribas, PhD.eHealth department, EURECAT Technology Centre of Catalonia, Barcelona, Spain
Preliminary dates & Submission Site:
Submission of papers/abstracts by authors (
EXTENDED ) January 4th,