ICT and Healthcare
Information Reliability

Author: Gianpiero Pescarmona
Date: 16/10/2012

Description

a new approach to Healthcare is now possible due the availability of:

  • more Data (Big Data, accessibility, sharing, privacy???)
      • Data Burden: how extract the relevant data? (causal models can supply hints?)
  • more sound Models
    • A top down model: from the disease to the optimal care
    • A bottom up model: from biochemical pathways to symptoms and symptoms collections (diseases)

Modelling Metabolism to improve Health Management

GP Publications

Definitions

  • Health (ability to cope with everyday environmental stress)
    • energy production (whole body)
      • Local conditions affecting energy production (organ specific)
        • Environment

Modelling by Agents

  • genetic
  • environmental

Structural Causal Models - SCM

Vensim Metabolic Pathways

Tutorial on How To Develop Stock-and-Flow Diagrams Using Vensim - System Dynamics Simulation Using Stock-and-Flow Diagrams

Vensim PLE Tutorial

Vensim Help

Generalized Structural Causal Models - GSCM

Generalized Structural Causal Models, 2018

  • In an SCM, each endogenous variable is associated with
    a structural equation that describes its causal dependence
    on other variables in the system, which induces a set of
    probability distributions over the space of endogenous
    variables. We generalize the notion of a structural equation
    to the concept of a causal constraint, which is a
    functional relation between variables that is invariant under
    a specified set of interventions. A generalized structural
    causal model is then a set of causal constraints in
    combination with a probability distribution on the exogenous
    variables.

What is new in causal inference - Judea Pearl

The seven tools of causal inference with reflections on machine learning, 2018

  • In this technical report Judea Pearl reflects on some of the limitations of machine learning systems that are based solely on statistical interpretation of data. To understand why? and to answer what if? questions, we need some kind of a causal model.

Examples

Metabolism_of_stromal_and_immune_cells_in_health_and_disease_2014

David Hammerstain

Google: Charlotte Kellogg Public Health

Ron S. Kenett, Israel : Applications of Bayesian Networks to Operational Risks, Healthcare, Biotechnology and Customer Surveys

AddThis Social Bookmark Button