TY - JOUR
T1 - Predicting clinical events using Bayesian multivariate linear mixed models with application to scleroderma
AU - Kim, Ji Soo
AU - Shah, Ami A.
AU - Hummers, Laura K.
AU - Zeger, Scott L.
N1 - Funding Information:
This work was supported in part by the Johns Hopkins inHealth initiative, the Scleroderma Research Foundation, the Nancy and Joachim Bechtle Precision Medicine Fund for Scleroderma, the Manugian Family Scholar, the Donald B. and Dorothy L. Stabler Foundation, the Chresanthe Staurulakis Memorial Fund, NIH P30 (1P30AR070254–01) and NIH/NIAMS R01 (AR073208). The funders support the Johns Hopkins Scleroderma Center Research Registry infrastructure for data management, biospecimen banking and autoantibody assays, and clinician, biostatistician and engineering effort.
Funding Information:
The authors thank Professor Antony Rosen, director of the Johns Hopkins inHealth Precision Medicine program, Fred Wigley director of the Johns Hopkins Scleroderma Center, Aalok Shah for supporting our use of the JH Precision Medicine Analytics Platform, and Adrianne Woods for database support.
Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - Background: Scleroderma is a serious chronic autoimmune disease in which a patient’s disease state manifests in several irregularly spaced longitudinal measures of lung, heart, skin, and other organ systems. Threshold crossings of pulmonary and cardiac measures indicate potentially life-threatening key clinical events including interstitial lung disease (ILD), cardiomyopathy, and pulmonary hypertension (PH). The statistical challenge is to accurately and precisely predict these events by using all of the clinical history for the patient at hand and for a reference population of patients. Methods: We use a Bayesian mixed model approach to simultaneously characterize each individual’s future trajectories for several biomarkers. We estimate this model using a large population of patients from the Johns Hopkins Scleroderma Center Research Registry. The joint probabilities of critical lung and heart events are then calculated as a byproduct of the mixed model. Results: The performance of this approach is substantially better than standard, more common alternatives. In order to predict an individual’s risks in a clinical setting, we also develop a cross-validated, sequential prediction (CVSP) algorithm. As additional data are observed during a patient’s visit, the algorithm sequentially produces updated predictions for the future longitudinal trajectories and for ILD, cardiomyopathy, and PH. The updated prediction distributions with little additional computing, for example within an electronic health record (EHR). Conclusions: This method that generates real-time personalized risk estimates has been implemented within the electronic health record system for clinical testing. To our knowledge, this work represents the first approach to compute personalized risk estimates for multiple scleroderma complications.
AB - Background: Scleroderma is a serious chronic autoimmune disease in which a patient’s disease state manifests in several irregularly spaced longitudinal measures of lung, heart, skin, and other organ systems. Threshold crossings of pulmonary and cardiac measures indicate potentially life-threatening key clinical events including interstitial lung disease (ILD), cardiomyopathy, and pulmonary hypertension (PH). The statistical challenge is to accurately and precisely predict these events by using all of the clinical history for the patient at hand and for a reference population of patients. Methods: We use a Bayesian mixed model approach to simultaneously characterize each individual’s future trajectories for several biomarkers. We estimate this model using a large population of patients from the Johns Hopkins Scleroderma Center Research Registry. The joint probabilities of critical lung and heart events are then calculated as a byproduct of the mixed model. Results: The performance of this approach is substantially better than standard, more common alternatives. In order to predict an individual’s risks in a clinical setting, we also develop a cross-validated, sequential prediction (CVSP) algorithm. As additional data are observed during a patient’s visit, the algorithm sequentially produces updated predictions for the future longitudinal trajectories and for ILD, cardiomyopathy, and PH. The updated prediction distributions with little additional computing, for example within an electronic health record (EHR). Conclusions: This method that generates real-time personalized risk estimates has been implemented within the electronic health record system for clinical testing. To our knowledge, this work represents the first approach to compute personalized risk estimates for multiple scleroderma complications.
KW - Bayesian hierarchical models
KW - Longitudinal profiles
KW - Multivariate mixed models
KW - Scleroderma
KW - Sequentially-updated prediction
UR - http://www.scopus.com/inward/record.url?scp=85119340134&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119340134&partnerID=8YFLogxK
U2 - 10.1186/s12874-021-01439-y
DO - 10.1186/s12874-021-01439-y
M3 - Article
C2 - 34773969
AN - SCOPUS:85119340134
SN - 1471-2288
VL - 21
JO - BMC Medical Research Methodology
JF - BMC Medical Research Methodology
IS - 1
M1 - 249
ER -