Personal tools
You are here: Home Events ANC Workshop Partha Lal/Emilia Wysocka Chairing: Sahar Primordian

ANC Workshop Partha Lal/Emilia Wysocka Chairing: Sahar Primordian

— filed under:

Partha Lal Title: Realtime Artifact Removal from Physiological Data in Intensive Care Units Emilia Wysocka Title: Towards a semi-automated framework for creating rule-based models of neuropsychiatric diseases

What
  • ANC Workshop Talk
When Jan 20, 2015
from 11:00 AM to 12:00 PM
Where Room 4.31/4.33
Add event to calendar vCal
iCal

Partha Lal


Title:   Realtime Artifact Removal from Physiological Data in Intensive Care Units

Abstract:

Physiological time series data is produced in large quantities in a medical intensive care setting.  This data can be useful in auditing patient care and evaluating new treatment plans.  It could also be used to detecting adverse clinical events.  Unfortunately the data contains artifactual events which need to be accounted for before any of that is possible.
In prior work the Factorial Switching Linear Dynamical System (FSLDS) has been applied in neonatal ICU, both for detecting artifacts (e.g. probe disconnections) and clinical events (bradycardia).  I shall describe a simple practical application of the FLSDS to a different ICU patient population.  New data has been collected in adult neuro ICU and manually annotated.  FSLDS models have been learned and evaluated for some of the events.
A difference with prior work is that here we work in realtime, rather than on retrospective data --- this brings its own problems, some of which will be discussed.

 

 

Emilia Wysocka


Title:  Towards a semi-automated framework for creating rule-based models of neuropsychiatric diseases

Abstract :

Systems level approaches are often used to help understand the pathogenesis of complex neuropsychiatric disorders. Commonly,mechanistic modeliing of the underlying dysfunction occurs at the level of critical signalling pathways which are popular targets for drug development. However, even with an abundance of information about these pathways, traditional equation-based models have become inadequate where the size, combinatorial complexity of reactions and the variety of post-translational modi cations is large. These issues are being addressed by new methods of rule-based modelling, embodied by languages such as BioNetGen and Kappa. Although these approaches have allowed for a massive expansion in size and complexity of the models that can be built their construction remains prohibitively labour intensive, seriously limiting their application. The aim of our project is to develop a tailored framework for the semi-automated construction of rule-based models designed to facilitate theprocess of model creation. We are aiming towards the integration and automation of access to primary data such as posttranslational modi_cation sites, protein and domain interactions and translate these data into the library of snippets encoded in rule-based language. To identify necessary stages for the framework, we based our approach on the real-world example, which is the aim of reconstruction of dynamic models of biochemical pathways and protein complexes relevant to Attention De cit Hyperactivity Disorder (ADHD). Many of these are shared with other neurological diseases including Autism and Parkinsons disease. Our targets are derived from static models constructed from protein-protein interaction (PPI) networks, pathway analysis and in the next steps will be followed on homology relations, expression data and gene partitions inferred by cluster analysis and mining of experimental literature for kinetic parameters and initial states. We plan also to adopt a modular approach to model construction, which is already encapsulated in rule-based languages (e.g. context-free molecular species) and is independent of the choice of simulation tools used.

1