1
|
Pineda-Antunez C, Seguin C, van Duuren LA, Knudsen AB, Davidi B, de Lima PN, Rutter C, Kuntz KM, Lansdorp-Vogelaar I, Collier N, Ozik J, Alarid-Escudero F. Emulator-Based Bayesian Calibration of the CISNET Colorectal Cancer Models. Med Decis Making 2024; 44:543-553. [PMID: 38858832 PMCID: PMC11281870 DOI: 10.1177/0272989x241255618] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/12/2024]
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.
Collapse
Affiliation(s)
- Carlos Pineda-Antunez
- The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, University of Washington, Seattle, WA, United States
| | - Claudia Seguin
- Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, United States
| | - 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, United States
| | - Barak Davidi
- Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, United States
| | | | - Carolyn Rutter
- Fred Hutchinson Cancer Research Center, Hutchinson Institute for Cancer Outcomes Research, Biostatistics Program, Public Health Sciences Division, Seattle WA
| | - Karen M. Kuntz
- Division of Health Policy & Management, University of Minnesota School of Public Health, Minneapolis, MN, United States
| | | | - Nicholson Collier
- 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
| | - Jonathan Ozik
- 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
| | - Fernando Alarid-Escudero
- Department of Health Policy, School of Medicine, Stanford University, CA, US
- Center for Health Policy, Freeman Spogli Institute, Stanford University, CA, US
| |
Collapse
|
2
|
Pineda-Antunez C, Seguin C, van Duuren LA, Knudsen AB, Davidi B, de Lima PN, Rutter C, Kuntz KM, Lansdorp-Vogelaar I, Collier N, Ozik J, Alarid-Escudero F. Emulator-based Bayesian calibration of the CISNET colorectal cancer models. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2023.02.27.23286525. [PMID: 36909607 PMCID: PMC10002763 DOI: 10.1101/2023.02.27.23286525] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
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. 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.
Collapse
Affiliation(s)
- Carlos Pineda-Antunez
- The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, University of Washington, Seattle, WA, United States
| | - Claudia Seguin
- Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, United States
| | - 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, United States
| | - Barak Davidi
- Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, United States
| | | | - Carolyn Rutter
- Fred Hutchinson Cancer Research Center, Hutchinson Institute for Cancer Outcomes Research, Biostatistics Program, Public Health Sciences Division, Seattle WA
| | - Karen M. Kuntz
- Division of Health Policy & Management, University of Minnesota School of Public Health, Minneapolis, MN, United States
| | | | - Nicholson Collier
- 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
| | - Jonathan Ozik
- 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
| | - Fernando Alarid-Escudero
- Department of Health Policy, School of Medicine, Stanford University, CA, US
- Center for Health Policy, Freeman Spogli Institute, Stanford University, CA, US
| |
Collapse
|
3
|
Richard DM, Lipsitch M. What's next: using infectious disease mathematical modelling to address health disparities. Int J Epidemiol 2024; 53:dyad180. [PMID: 38145617 PMCID: PMC10859128 DOI: 10.1093/ije/dyad180] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2023] [Accepted: 12/14/2023] [Indexed: 12/27/2023] Open
Affiliation(s)
- Danielle M Richard
- Center for Forecasting and Outbreak Analytics, Centers for Disease Control and Prevention, Atlanta, GA, USA
| | - Marc Lipsitch
- Center for Forecasting and Outbreak Analytics, Centers for Disease Control and Prevention, Atlanta, GA, USA
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA
| |
Collapse
|
4
|
Malloy GSP, Puglisi LB, Bucklen KB, Harvey TD, Wang EA, Brandeau ML. Predicting COVID-19 Outbreaks in Correctional Facilities Using Machine Learning. MDM Policy Pract 2024; 9:23814683231222469. [PMID: 38293655 PMCID: PMC10826393 DOI: 10.1177/23814683231222469] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Accepted: 10/05/2023] [Indexed: 02/01/2024] Open
Abstract
Introduction. The risk of infectious disease transmission, including COVID-19, is disproportionately high in correctional facilities due to close living conditions, relatively low levels of vaccination, and reduced access to testing and treatment. While much progress has been made on describing and mitigating COVID-19 and other infectious disease risk in jails and prisons, there are open questions about which data can best predict future outbreaks. Methods. We used facility data and demographic and health data collected from 24 prison facilities in the Pennsylvania Department of Corrections from March 2020 to May 2021 to determine which sources of data best predict a coming COVID-19 outbreak in a prison facility. We used machine learning methods to cluster the prisons into groups based on similar facility-level characteristics, including size, rurality, and demographics of incarcerated people. We developed logistic regression classification models to predict for each cluster, before and after vaccine availability, whether there would be no cases, an outbreak defined as 2 or more cases, or a large outbreak, defined as 10 or more cases in the next 1, 2, and 3 d. We compared these predictions to data on outbreaks that occurred. Results. Facilities were divided into 8 clusters of sizes varying from 1 to 7 facilities per cluster. We trained 60 logistic regressions; 20 had test sets with between 35% and 65% of days with outbreaks detected. Of these, 8 logistic regressions correctly predicted the occurrence of an outbreak more than 55% of the time. The most common predictive feature was incident cases among the incarcerated population from 2 to 32 d prior. Other predictive features included the number of tests administered from 1 to 33 d prior, total population, test positivity rate, and county deaths, hospitalizations, and incident cases. Cumulative cases, vaccination rates, and race, ethnicity, or age statistics for incarcerated populations were generally not predictive. Conclusions. County-level measures of COVID-19, facility population, and test positivity rate appear as potential promising predictors of COVID-19 outbreaks in correctional facilities, suggesting that correctional facilities should monitor community transmission in addition to facility transmission to inform future outbreak response decisions. These efforts should not be limited to COVID-19 but should include any large-scale infectious disease outbreak that may involve institution-community transmission. Highlights The risk of infectious disease transmission, including COVID-19, is disproportionately high in correctional facilities.We used machine learning methods with data collected from 24 prison facilities in the Pennsylvania Department of Corrections to determine which sources of data best predict a coming COVID-19 outbreak in a prison facility.Key predictors included county-level measures of COVID-19, facility population, and the test positivity rate in a facility.Fortifying correctional facilities with the ability to monitor local community rates of infection (e.g., though improved interagency collaboration and data sharing) along with continued testing of incarcerated people and staff can help correctional facilities better predict-and respond to-future infectious disease outbreaks.
Collapse
Affiliation(s)
| | - Lisa B. Puglisi
- SEICHE Center for Health and Justice, Department of Internal Medicine, School of Medicine, Yale University, New Haven, CT, USA
| | | | - Tyler D. Harvey
- SEICHE Center for Health and Justice, Department of Internal Medicine, School of Medicine, Yale University, New Haven, CT, USA
| | - Emily A. Wang
- SEICHE Center for Health and Justice, Department of Internal Medicine, School of Medicine, Yale University, New Haven, CT, USA
| | - Margaret L. Brandeau
- Department of Management Science and Engineering, School of Engineering, Stanford University, Stanford, CA, USA
| |
Collapse
|
5
|
Dubey P, Hoover CM, Lu P, Blumberg S, Porco TC, Parsons TL, Worden L. Rates of SARS-CoV-2 transmission between and into California state prisons. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.08.24.23294583. [PMID: 37662306 PMCID: PMC10473789 DOI: 10.1101/2023.08.24.23294583] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/05/2023]
Abstract
Correctional institutions are a crucial hotspot amplifying SARS-CoV-2 spread and disease disparity in the U.S. In the California state prison system, multiple massive outbreaks have been caused by transmission between prisons. Correctional staff are a likely vector for transmission into the prison system from surrounding communities. We used publicly available data to estimate the magnitude of flows to and between California state prisons, estimating rates of transmission from communities to prison staff and residents, among and between residents and staff within facilities, and between staff and residents of distinct facilities in the state's 34 prisons through March 22, 2021. We use a mechanistic model, the Hawkes process, reflecting the dynamics of SARS-CoV-2 transmission, for joint estimation of transmission rates. Using nested models for hypothesis testing, we compared the results to simplified models (i) without transmission between prisons, and (ii) with no distinction between prison staff and residents. We estimated that transmission between different facilities' staff is a significant cause of disease spread, and that staff are a vector of transmission between resident populations and outside communities. While increased screening and vaccination of correctional staff may help reduce introductions, large-scale decarceration remains crucially needed as more limited measures are not likely to prevent large-scale disease spread.
Collapse
Affiliation(s)
- Preeti Dubey
- Francis I. Proctor Foundation, University of California, San Francisco, Calif., USA
| | | | - Phoebe Lu
- Francis I. Proctor Foundation, University of California, San Francisco, Calif., USA
| | - Seth Blumberg
- Francis I. Proctor Foundation, University of California, San Francisco, Calif., USA
- Department of Medicine, Division of Hospital Medicine, University of California, San Francisco, Calif., USA
| | - Travis C. Porco
- Francis I. Proctor Foundation, University of California, San Francisco, Calif., USA
| | - Todd L. Parsons
- CNRS & Laboratoire de Probabilités, Statistique et Modélisation, Campus Pierre et Marie Curie, Sorbonne Université, Paris, France
| | - Lee Worden
- Francis I. Proctor Foundation, University of California, San Francisco, Calif., USA
| |
Collapse
|