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

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Recent developments in the field of sensor devices provide new possibilities to measure a variety of health related aspects in a precise and fine-grained manner. Subsequently, more empirical data will be generated than ever before. While this greatly improves the opportunities for creating accurate predictive models, other types of models besides the more traditional machine learning approaches can provide insights into temporal relationships in the data. Models that express temporal relationships between states in a mathematical manner are examples of such models. However, the evaluation methods traditionally used in the field of predictive modeling are not appropriate for those models, making it difficult to distinguish them in terms of validity. Appropriate assessment methodology is therefore necessary to drive the research of mathematical modeling forward. In this paper we investigate the applicability of such a formalized method. The method takes into account important model aspects, namely descriptive and predictive capability, parameter sensitivity and model complexity. As a case study the method is applied to a mathematical model in the domain of mental health, showing that the method generates useful insights into the behavior of the model.

Original languageEnglish
Pages (from-to)347-357
Number of pages11
JournalComputers in Biology and Medicine
Volume87
DOIs
Publication statusPublished - 1 Aug 2017

Fingerprint

Formal methods
Health care
Delivery of Health Care
Health
Mental Health
Theoretical Models
Equipment and Supplies
Learning systems
Research
Mathematical models
Sensors

Keywords

  • Depression
  • Health care
  • Mathematical modeling
  • Model evaluation
  • Multi-objective optimization
  • Predictive modeling
  • Regression

Cite this

@article{f2125db1e0094c21804f69255124248d,
title = "Assessment of temporal predictive models for health care using a formal method",
abstract = "Recent developments in the field of sensor devices provide new possibilities to measure a variety of health related aspects in a precise and fine-grained manner. Subsequently, more empirical data will be generated than ever before. While this greatly improves the opportunities for creating accurate predictive models, other types of models besides the more traditional machine learning approaches can provide insights into temporal relationships in the data. Models that express temporal relationships between states in a mathematical manner are examples of such models. However, the evaluation methods traditionally used in the field of predictive modeling are not appropriate for those models, making it difficult to distinguish them in terms of validity. Appropriate assessment methodology is therefore necessary to drive the research of mathematical modeling forward. In this paper we investigate the applicability of such a formalized method. The method takes into account important model aspects, namely descriptive and predictive capability, parameter sensitivity and model complexity. As a case study the method is applied to a mathematical model in the domain of mental health, showing that the method generates useful insights into the behavior of the model.",
keywords = "Depression, Health care, Mathematical modeling, Model evaluation, Multi-objective optimization, Predictive modeling, Regression",
author = "{van Breda}, Ward and Mark Hoogendoorn and Eiben, {A. E.} and Matthias Berking",
year = "2017",
month = "8",
day = "1",
doi = "10.1016/j.compbiomed.2017.06.014",
language = "English",
volume = "87",
pages = "347--357",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

Assessment of temporal predictive models for health care using a formal method. / van Breda, Ward; Hoogendoorn, Mark; Eiben, A. E.; Berking, Matthias.

In: Computers in Biology and Medicine, Vol. 87, 01.08.2017, p. 347-357.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Assessment of temporal predictive models for health care using a formal method

AU - van Breda, Ward

AU - Hoogendoorn, Mark

AU - Eiben, A. E.

AU - Berking, Matthias

PY - 2017/8/1

Y1 - 2017/8/1

N2 - Recent developments in the field of sensor devices provide new possibilities to measure a variety of health related aspects in a precise and fine-grained manner. Subsequently, more empirical data will be generated than ever before. While this greatly improves the opportunities for creating accurate predictive models, other types of models besides the more traditional machine learning approaches can provide insights into temporal relationships in the data. Models that express temporal relationships between states in a mathematical manner are examples of such models. However, the evaluation methods traditionally used in the field of predictive modeling are not appropriate for those models, making it difficult to distinguish them in terms of validity. Appropriate assessment methodology is therefore necessary to drive the research of mathematical modeling forward. In this paper we investigate the applicability of such a formalized method. The method takes into account important model aspects, namely descriptive and predictive capability, parameter sensitivity and model complexity. As a case study the method is applied to a mathematical model in the domain of mental health, showing that the method generates useful insights into the behavior of the model.

AB - Recent developments in the field of sensor devices provide new possibilities to measure a variety of health related aspects in a precise and fine-grained manner. Subsequently, more empirical data will be generated than ever before. While this greatly improves the opportunities for creating accurate predictive models, other types of models besides the more traditional machine learning approaches can provide insights into temporal relationships in the data. Models that express temporal relationships between states in a mathematical manner are examples of such models. However, the evaluation methods traditionally used in the field of predictive modeling are not appropriate for those models, making it difficult to distinguish them in terms of validity. Appropriate assessment methodology is therefore necessary to drive the research of mathematical modeling forward. In this paper we investigate the applicability of such a formalized method. The method takes into account important model aspects, namely descriptive and predictive capability, parameter sensitivity and model complexity. As a case study the method is applied to a mathematical model in the domain of mental health, showing that the method generates useful insights into the behavior of the model.

KW - Depression

KW - Health care

KW - Mathematical modeling

KW - Model evaluation

KW - Multi-objective optimization

KW - Predictive modeling

KW - Regression

UR - http://www.scopus.com/inward/record.url?scp=85021293772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021293772&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2017.06.014

DO - 10.1016/j.compbiomed.2017.06.014

M3 - Article

VL - 87

SP - 347

EP - 357

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -