Emulator-Based Bayesian Calibration of the CISNET Colorectal Cancer Models

Carlos Pineda-Antunez, Claudia Seguin, Luuk A. van Duuren, Amy B. Knudsen, Barak Davidi, Pedro Nascimento de Lima, Carolyn Rutter, Karen M. Kuntz, Iris Lansdorp-Vogelaar, Nicholson Collier, Jonathan Ozik and Fernando Alarid-Escudero
Additional contact information
Carlos Pineda-Antunez: The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, University of Washington, Seattle, WA, USA
Claudia Seguin: Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, USA
Luuk A. van Duuren: Department of Public Health, Erasmus MC Medical Center, Rotterdam, The Netherlands
Amy B. Knudsen: Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, USA
Barak Davidi: Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, USA
Pedro Nascimento de Lima: RAND Corporation, Arlington, VA, USA
Carolyn Rutter: Fred Hutchinson Cancer Research Center, Hutchinson Institute for Cancer Outcomes Research, Biostatistics Program, Public Health Sciences Division, Seattle, WA, USA
Karen M. Kuntz: Division of Health Policy & Management, University of Minnesota School of Public Health, Minneapolis, MN, USA
Iris Lansdorp-Vogelaar: Department of Public Health, Erasmus MC Medical Center, Rotterdam, The Netherlands
Nicholson Collier: Decision and Infrastructure Sciences Division, Argonne National Laboratory, Lemont, IL, USA
Jonathan Ozik: Decision and Infrastructure Sciences Division, Argonne National Laboratory, Lemont, IL, USA
Fernando Alarid-Escudero: Department of Health Policy, School of Medicine, Stanford University, CA, USA

Medical Decision Making, 2024, vol. 44, issue 5, 543-553

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 (ANNs) 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 4 hidden layers and 360 hidden nodes, MISCAN-Colon had 4 hidden layers and 114 hidden nodes, and CRC-SPIN had 1 hidden layer and 140 hidden nodes. The total time for training and calibrating the emulators was 7.3, 4.0, and 0.66 h 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, such as the CISNET CRC models. In this work, we present a step-by-step guide to constructing emulators for calibrating 3 realistic CRC individual-level models using a Bayesian approach. Highlights We use artificial neural networks (ANNs) to build emulators that surrogate complex individual-based models to reduce the computational burden in the Bayesian calibration process. ANNs showed good performance in emulating the CISNET-CRC microsimulation models, despite having many input parameters and outputs. 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. This work aims to support health decision scientists who want to quantify the uncertainty of calibrated parameters of computationally intensive simulation models under a Bayesian framework.

Keywords: artificial neural networks; Bayesian calibration; colorectal cancer model; emulator; machine learning (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/0272989X241255618 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:medema:v:44:y:2024:i:5:p:543-553

DOI: 10.1177/0272989X241255618

Access Statistics for this article

More articles in Medical Decision Making
Bibliographic data for series maintained by SAGE Publications ().