Literature DB >> 30248276

Nonidentifiability in Model Calibration and Implications for Medical Decision Making.

Fernando Alarid-Escudero1, Richard F MacLehose2, Yadira Peralta3, Karen M Kuntz1, Eva A Enns1.   

Abstract

BACKGROUND: Calibration is the process of estimating parameters of a mathematical model by matching model outputs to calibration targets. In the presence of nonidentifiability, multiple parameter sets solve the calibration problem, which may have important implications for decision making. We evaluate the implications of nonidentifiability on the optimal strategy and provide methods to check for nonidentifiability.
METHODS: We illustrate nonidentifiability by calibrating a 3-state Markov model of cancer relative survival (RS). We performed 2 different calibration exercises: 1) only including RS as a calibration target and 2) adding the ratio between the 2 nondeath states over time as an additional target. We used the Nelder-Mead (NM) algorithm to identify parameter sets that best matched the calibration targets. We used collinearity and likelihood profile analyses to check for nonidentifiability. We then estimated the benefit of a hypothetical treatment in terms of life expectancy gains using different, but equally good-fitting, parameter sets. We also applied collinearity analysis to a realistic model of the natural history of colorectal cancer.
RESULTS: When only RS is used as the calibration target, 2 different parameter sets yield similar maximum likelihood values. The high collinearity index and the bimodal likelihood profile on both parameters demonstrated the presence of nonidentifiability. These different, equally good-fitting parameter sets produce different estimates of the treatment effectiveness (0.67 v. 0.31 years), which could influence the optimal decision. By incorporating the additional target, the model becomes identifiable with a collinearity index of 3.5 and a unimodal likelihood profile.
CONCLUSIONS: In the presence of nonidentifiability, equally likely parameter estimates might yield different conclusions. Checking for the existence of nonidentifiability and its implications should be incorporated into standard model calibration procedures.

Entities:  

Keywords:  calibration; decision-analytic models; estimation; likelihood function; nonidentifiability

Mesh:

Year:  2018        PMID: 30248276      PMCID: PMC6156799          DOI: 10.1177/0272989X18792283

Source DB:  PubMed          Journal:  Med Decis Making        ISSN: 0272-989X            Impact factor:   2.583


  35 in total

1.  Incorporating calibrated model parameters into sensitivity analyses: deterministic and probabilistic approaches.

Authors:  Douglas C A Taylor; Vivek Pawar; Denise T Kruzikas; Kristen E Gilmore; Myrlene Sanon; Milton C Weinstein
Journal:  Pharmacoeconomics       Date:  2012-02-01       Impact factor: 4.981

2.  The relative survival rate: a statistical methodology.

Authors:  F EDERER; L M AXTELL; S J CUTLER
Journal:  Natl Cancer Inst Monogr       Date:  1961-09

Review 3.  A review and critique of modelling in prioritising and designing screening programmes.

Authors:  J Karnon; E Goyder; P Tappenden; S McPhie; I Towers; J Brazier; J Madan
Journal:  Health Technol Assess       Date:  2007-12       Impact factor: 4.014

4.  Structural and practical identifiability analysis of partially observed dynamical models by exploiting the profile likelihood.

Authors:  A Raue; C Kreutz; T Maiwald; J Bachmann; M Schilling; U Klingmüller; J Timmer
Journal:  Bioinformatics       Date:  2009-06-08       Impact factor: 6.937

Review 5.  A perspective on cancer cell metastasis.

Authors:  Christine L Chaffer; Robert A Weinberg
Journal:  Science       Date:  2011-03-25       Impact factor: 47.728

6.  Exploring the unknown and the unknowable with simulation models.

Authors:  Louise B Russell
Journal:  Med Decis Making       Date:  2011 Jul-Aug       Impact factor: 2.583

Review 7.  Profile likelihood in systems biology.

Authors:  Clemens Kreutz; Andreas Raue; Daniel Kaschek; Jens Timmer
Journal:  FEBS J       Date:  2013-05-09       Impact factor: 5.542

8.  Cost-effectiveness analysis of colorectal cancer screening with stool DNA testing in intermediate-incidence countries.

Authors:  Grace Hui-Min Wu; Yi-Ming Wang; Amy Ming-Fang Yen; Jau-Min Wong; Hsin-Chih Lai; Jane Warwick; Tony Hsiu-Hsi Chen
Journal:  BMC Cancer       Date:  2006-05-24       Impact factor: 4.430

9.  Model transparency and validation: a report of the ISPOR-SMDM Modeling Good Research Practices Task Force-7.

Authors:  David M Eddy; William Hollingworth; J Jaime Caro; Joel Tsevat; Kathryn M McDonald; John B Wong
Journal:  Med Decis Making       Date:  2012 Sep-Oct       Impact factor: 2.583

10.  Bias modelling in evidence synthesis.

Authors:  Rebecca M Turner; David J Spiegelhalter; Gordon C S Smith; Simon G Thompson
Journal:  J R Stat Soc Ser A Stat Soc       Date:  2009-01       Impact factor: 2.483

View more
  8 in total

1.  Revisiting assumptions about age-based mixing representations in mathematical models of sexually transmitted infections.

Authors:  C W Easterly; F Alarid-Escudero; E A Enns; S Kulasingam
Journal:  Vaccine       Date:  2018-08-06       Impact factor: 3.641

2.  CDX2 Biomarker Testing and Adjuvant Therapy for Stage II Colon Cancer: An Exploratory Cost-Effectiveness Analysis.

Authors:  Fernando Alarid-Escudero; Deborah Schrag; Karen M Kuntz
Journal:  Value Health       Date:  2021-11-02       Impact factor: 5.725

3.  Calibrating Natural History of Cancer Models in the Presence of Data Incompatibility: Problems and Solutions.

Authors:  Olena Mandrik; Chloe Thomas; Sophie Whyte; James Chilcott
Journal:  Pharmacoeconomics       Date:  2022-01-07       Impact factor: 4.558

4.  Characterization and Valuation of the Uncertainty of Calibrated Parameters in Microsimulation Decision Models.

Authors:  Fernando Alarid-Escudero; Amy B Knudsen; Jonathan Ozik; Nicholson Collier; Karen M Kuntz
Journal:  Front Physiol       Date:  2022-05-09       Impact factor: 4.755

5.  Calculating the Expected Value of Sample Information in Practice: Considerations from 3 Case Studies.

Authors:  Anna Heath; Natalia Kunst; Christopher Jackson; Mark Strong; Fernando Alarid-Escudero; Jeremy D Goldhaber-Fiebert; Gianluca Baio; Nicolas A Menzies; Hawre Jalal
Journal:  Med Decis Making       Date:  2020-04-16       Impact factor: 2.583

6.  Multiobjective Calibration of Disease Simulation Models Using Gaussian Processes.

Authors:  Aditya Sai; Carolina Vivas-Valencia; Thomas F Imperiale; Nan Kong
Journal:  Med Decis Making       Date:  2019-08-02       Impact factor: 2.583

7.  A Need for Change! A Coding Framework for Improving Transparency in Decision Modeling.

Authors:  Fernando Alarid-Escudero; Eline M Krijkamp; Petros Pechlivanoglou; Hawre Jalal; Szu-Yu Zoe Kao; Alan Yang; Eva A Enns
Journal:  Pharmacoeconomics       Date:  2019-11       Impact factor: 4.981

8.  Optimal timing and effectiveness of COVID-19 outbreak responses in China: a modelling study.

Authors:  Anthony Zhenhuan Zhang; Eva A Enns
Journal:  BMC Public Health       Date:  2022-04-07       Impact factor: 3.295

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.