Emulator-based Bayesian calibration of the CISNET colorectal cancer models
Authors:
- Carlos Pineda-AntunezCPCarlos Pineda-Antunez
- Claudia SeguinCSClaudia Seguin
- Luuk A van DuurenLDLuuk A van Duuren
- Barak DavidiBDBarak Davidi
- Pedro Nascimento de LimaPLPedro Nascimento de Lima
- Carolyn RutterCRCarolyn Rutter
- Karen M. KuntzKKKaren M. Kuntz
- Iris Lansdorp-VogelaarILIris Lansdorp-Vogelaar
- Nicholson CollierNCNicholson Collier
- Jonathan OzikJOJonathan Ozik
- Fernando Alarid-EscuderoFAFernando Alarid-Escudero
Preprint
Abstract
Purpose To calibrate Cancer Intervention and Surveillance Modeling Network (CISNET) ‘s SimCRC, MISCAN-Colon, and CRC-SPIN simulation models of the natural history colorectal cancer (CRC) with an emulator-based Bayesian algorithm and internally validate the model-predicted outcomes to calibration targets. Methods We used Latin hypercube sampling to sample up to 50,000 parameter sets for each CISNET-CRC model and generated the corresponding outputs. We trained multilayer perceptron artificial neural networks (ANN) as emulators using the input and output samples for each CISNET-CRC model. We selected ANN structures with corresponding hyperparameters (i.e., number of hidden layers, nodes, activation functions, epochs, and optimizer) that minimize the predicted mean square error on the validation sample. We implemented the ANN emulators in a probabilistic programming language and calibrated the input parameters with Hamiltonian Monte Carlo-based algorithms to obtain the joint posterior distributions of the CISNET-CRC models’ parameters. We internally validated each calibrated emulator by comparing the model-predicted posterior outputs against the calibration targets. Results The optimal ANN for SimCRC had four hidden layers and 360 hidden nodes, MISCAN-Colon had 4 hidden layers and 114 hidden nodes, and CRC-SPIN had one hidden layer and 140 hidden nodes. The total time for training and calibrating the emulators was 7.3, 4.0, and 0.66 hours for SimCRC, MISCAN-Colon, and CRC-SPIN, respectively. The mean of the model-predicted outputs fell within the 95% confidence intervals of the calibration targets in 98 of 110 for SimCRC, 65 of 93 for MISCAN, and 31 of 41 targets for CRC-SPIN. Conclusions Using ANN emulators is a practical solution to reduce the computational burden and complexity for Bayesian calibration of individual-level simulation models used for policy analysis, like the CISNET CRC models.Keywords
All Related Versions
- Published version: Medical Decision Making, 44 (5), 543.
This publication has 29 references indexed in Scilit:
- Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantificationJournal of Computational Physics, 2018
- Bayesian Methods for Calibrating Health Policy Models: A TutorialPharmacoEconomics, 2017
- Introduction2015
- Adaptive sequential sampling for surrogate model generation with artificial neural networksComputers & Chemical Engineering, 2014
- SkyNet: an efficient and robust neural network training tool for machine learning in astronomyMonthly Notices of the Royal Astronomical Society, 2014
- Modeling Good Research Practices—Overview: A Report of the ISPOR-SMDM Modeling Good Research Practices Task Force-1Value in Health, 2012
- Clarifying Differences in Natural History between Models of ScreeningMedical Decision Making, 2011
- Bayesian Calibration of Microsimulation ModelsJournal of the American Statistical Association, 2009
- Computing Normalizing Constants for Finite Mixture Models via Incremental Mixture Importance Sampling (IMIS)Journal of Computational and Graphical Statistics, 2006
- General Methods for Monitoring Convergence of Iterative SimulationsJournal of Computational and Graphical Statistics, 1998