Emulator-based Bayesian calibration of the CISNET colorectal cancer models.

Autor:	Pineda-Antunez C; The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, University of Washington, Seattle, WA, United States., Seguin C; Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, United States., van Duuren LA; Department of Public Health, Erasmus MC Medical Center Rotterdam, The Netherlands., Knudsen AB; Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, United States., Davidi B; Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, United States., de Lima PN; RAND Corporation, Santa Monica, CA, United States., Rutter C; Fred Hutchinson Cancer Research Center, Hutchinson Institute for Cancer Outcomes Research, Biostatistics Program, Public Health Sciences Division, Seattle WA., Kuntz KM; Division of Health Policy & Management, University of Minnesota School of Public Health, Minneapolis, MN, United States., Lansdorp-Vogelaar I; Department of Public Health, Erasmus MC Medical Center Rotterdam, The Netherlands., Collier N; Decision and Infrastructure Sciences Division, Argonne National Laboratory, Lemont, IL, United States.; Consortium for Advanced Science and Engineering, University of Chicago, Chicago, IL, United States., Ozik J; Decision and Infrastructure Sciences Division, Argonne National Laboratory, Lemont, IL, United States.; Consortium for Advanced Science and Engineering, University of Chicago, Chicago, IL, United States., Alarid-Escudero F; Department of Health Policy, School of Medicine, Stanford University, CA, US.; Center for Health Policy, Freeman Spogli Institute, Stanford University, CA, US.
Jazyk:	angličtina
Zdroj:	MedRxiv : the preprint server for health sciences [medRxiv] 2024 Feb 05. Date of Electronic Publication: 2024 Feb 05.
DOI:	10.1101/2023.02.27.23286525
Abstrakt:	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. In this work, we present a step-by-step guide to constructing emulators for calibrating three realistic CRC individual-level models using a Bayesian approach. Competing Interests: Declarations: All authors have read and approved the manuscript and agree with its submission to MDM. The authors have no conflicts of interest to declare.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu