Mark Hoogendoorn
ABSTRACT
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 to derive generic concepts. In this paper, we present a middle ground, namely parameterized dynamical systems models that are generated from data using a Genetic Programming (GP) framework. A fitness function suitable for the health domain is exploited. An evaluation of the approach in the mental health domain shows that performance of the model generated by the GP is on par with a dynamical systems model developed based on domain knowledge, significantly outperforms a generic Long Term Short Term Memory (LSTM) model and in some cases also outperforms an individualized LSTM model.
- Altaf Hussain Abro and Michel CA Klein. 2016. Validation of a Computational Model for Mood and Social Integration. In International Conference on Social Informatics. Springer, 385–399.Google Scholar
Digital Library
- Iyad Batal, Hamed Valizadegan, Gregory F Cooper, and Milos Hauskrecht. 2013. A temporal pattern mining approach for classifying electronic health record data. ACM Transactions on Intelligent Systems and Technology (TIST) 4, 4(2013), 63.Google ScholarDigital Library
- Tibor Bosse, Mark Hoogendoorn, Michel CA Klein, and Jan Treur. 2007. An agent-based generic model for human-like ambience. In European Conference on Ambient Intelligence. Springer, 93–103.Google Scholar
- Tibor Bosse, Mark Hoogendoorn, Michel CA Klein, and Jan Treur. 2009. A generic architecture for human-aware ambient computing. In Agent-based ubiquitous computing. Springer, 35–61.Google Scholar
- Hongqing Cao, Lishan Kang, Yuping Chen, and Jingxian Yu. 2000. Evolutionary modeling of systems of ordinary differential equations with genetic programming. Genetic Programming and Evolvable Machines 1, 4 (2000), 309–337.Google ScholarDigital Library
- Darryl Daugherty, Tairi Roque-Urrea, John Urrea-Roque, Jessica Troyer, Stephen Wirkus, and Mason A Porter. 2009. Mathematical models of bipolar disorder. Communications in Nonlinear Science and Numerical Simulation 14, 7(2009), 2897–2908.Google ScholarCross Ref
- Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and TAMT Meyarivan. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation 6, 2(2002), 182–197.Google Scholar
- Agoston E Eiben and James E Smith. 2015. Introduction to evolutionary computing. Springer.Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.Google ScholarDigital Library
- Mark Hoogendoorn and Burkhardt Funk. 2017. Machine Learning for the Quantified Self: On the Art of Learning from Sensory Data. Springer.Google Scholar
- Robert LiKamWa, Yunxin Liu, Nicholas D Lane, and Lin Zhong. 2013. Moodscope: Building a mood sensor from smartphone usage patterns. In Proceeding of the 11th annual international conference on Mobile systems, applications, and services. ACM, 389–402.Google Scholar
- Zachary C Lipton, David C Kale, Charles Elkan, and Randall Wetzell. 2015. Learning to Diagnose with LSTM Recurrent Neural Networks. arXiv preprint arXiv:1511.03677(2015).Google Scholar
- Oded Maron and Andrew W Moore. 1997. The racing algorithm: Model selection for lazy learners. In Lazy learning. Springer, 193–225.Google Scholar
- Adam Mikus, Mark Hoogendoorn, Artur Rocha, Joao Gama, Jeroen Ruwaard, and Heleen Riper. 2018. Predicting short term mood developments among depressed patients using adherence and ecological momentary assessment data. Internet interventions 12 (2018), 105–110.Google Scholar
- Venet Osmani, Alban Maxhuni, Agnes Grünerbl, Paul Lukowicz, Christian Haring, and Oscar Mayora. 2013. Monitoring activity of patients with bipolar disorder using smart phones. In Proceedings of International Conference on Advances in Mobile Computing & Multimedia. ACM, 85.Google ScholarDigital Library
- Heleen Riper, Gerhard Andersson, Helen Christensen, Pim Cuijpers, Alfred Lange, and Gunther Eysenbach. 2010. Theme issue on e-mental health: a growing field in internet research. Journal of medical Internet research 12, 5 (2010).Google ScholarCross Ref
- Michael Schmidt and Hod Lipson. 2009. Distilling free-form natural laws from experimental data. Science 324, 5923 (2009), 81–85.Google Scholar
- Dorthe Kirkegaard Thomsen, Mimi Yung Mehlsen, Søren Christensen, and Robert Zachariae. 2003. Rumination-relationship with negative mood and sleep quality. Personality and Individual Differences 34, 7 (2003), 1293–1301.Google ScholarCross Ref
- Jan Treur. 2016. Network-Oriented Modeling and Its Conceptual Foundations. In Network-Oriented Modeling. Springer, 3–33.Google Scholar
- Ward van Breda, Mark Hoogendoorn, AE Eiben, and Matthias Berking. 2017. Assessment of temporal predictive models for health care using a formal method. Computers in biology and medicine 87 (2017), 347–357.Google Scholar
Index Terms
- GP-HD: Using Genetic Programming to Generate Dynamical Systems Models for Health Care
Recommendations
Using electronic health record systems in diabetes care: emerging practices
IHI '10: Proceedings of the 1st ACM International Health Informatics SymposiumWhile there has been considerable attention devoted to the deployment of electronic health record (EHR) systems, there has been far less attention given to their appropriation for use in clinical encounters --- particularly in the context of complex, ...
Current Issues in Health Care Informatics
Health care informatics has emerged as a diverse and important new field of study. The field can be very broadly defined as the science that addresses how best to use information to improve health care. The field includes the four areas of ...
Comments