GP-HD: Using Genetic Programming to Generate Dynamical Systems Models for Health Care

  title={GP-HD: Using Genetic Programming to Generate Dynamical Systems Models for Health Care},
  author={Mark Hoogendoorn and Ward van Breda and Jeroen Ruwaard},
  journal={2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI)},
The huge wealth of data in the health domain can be exploited to create models that predict development of health states over time. Temporal learning algorithms are well suited to learn relationships between health states and make predictions about their future developments. However, these algorithms: (1) either focus on learning one generic model for all patients, providing general insights but often with limited predictive performance, or (2) learn individualized models from which it is hard… 

Figures and Tables from this paper



Assessment of temporal predictive models for health care using a formal method

Learning to Diagnose with LSTM Recurrent Neural Networks

This first study to empirically evaluate the ability of LSTMs to recognize patterns in multivariate time series of clinical measurements considers multilabel classification of diagnoses, and establishes the effectiveness of a simple LSTM network for modeling clinical data.

A temporal pattern mining approach for classifying electronic health record data

The Minimal Predictive Temporal Patterns framework is presented to generate a small set of predictive and nonspurious patterns for the real-world clinical task of predicting patients who are at risk of developing heparin-induced thrombocytopenia.

Validation of a Computational Model for Mood and Social Integration

A computational model that can be used for analyzing and predicating the mood level of individuals by taking into account the social integration, the participation in social activities and the enjoyableness of those activities is presented.

The Racing Algorithm: Model Selection for Lazy Learners

This paper develops a technique called “racing” that tests the set of models in parallel, quickly discards those models that are clearly inferior and concentrates the computational effort on differentiating among the better models.

Network-Oriented Modeling: Addressing Complexity of Cognitive, Affective and Social Interactions

Network-oriented modeling allows high-level cognitive, affective and social models in the form of (cyclic) graphs to be constructed, which can be automatically transformed into executable simulation models, making it possible to address complex phenomena such as the integration of emotions within cognitive processes of all kinds.

An Agent-Based Generic Model for Human-Like Ambience

A reusable agent-based generic model is presented for a specific class of Ambient Intelligence applications: those cases addressing human wellbeing and functioning from a human-like understanding, thus providing an executable specification that can be used for prototyping.

Evolutionary Modeling of Systems of Ordinary Differential Equations with Genetic Programming

This paper describes an approach to the evolutionary modeling problem of ordinary differential equations including systems of ordinary differential equations and higher-order differential equations.