Seasonality, mediation and comparison (SMAC) methods to identify influences on lung function decline
Emrah Gecili,
Anushka Palipana,
Cole Brokamp,
Rui Huang,
Eleni-Rosalina Andrinopoulou,
Teresa Pestian,
Erika Rasnick,
Ruth H. Keogh,
Yizhao Ni,
John P. Clancy,
Patrick Ryan,
Rhonda D. Szczesniak
Affiliations
Emrah Gecili
Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH 45229, United States
Anushka Palipana
Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH 45229, United States; Division of Statistics and Data Science, Department of Mathematics, University of Cincinnati, 155B McMicken Hall, Cincinnati, OH, United States
Cole Brokamp
Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH 45229, United States; Department of Pediatrics, University of Cincinnati, 3333 Burnet Ave, Cincinnati, OH, United States
Rui Huang
Division of Statistics and Data Science, Department of Mathematics, University of Cincinnati, 155B McMicken Hall, Cincinnati, OH, United States
Eleni-Rosalina Andrinopoulou
Department of Biostatistics, Erasmus Medical Center, Dr. Molewaterplein 40, 3015 GD, Rotterdam, Netherlands
Teresa Pestian
Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH 45229, United States
Erika Rasnick
Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH 45229, United States
Ruth H. Keogh
London School of Hygiene and Tropical Medicine, Keppel Street, London WC1E 7HT United Kingdom
Yizhao Ni
Department of Pediatrics, University of Cincinnati, 3333 Burnet Ave, Cincinnati, OH, United States; Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH, United States
John P. Clancy
Department of Pediatrics, University of Cincinnati, 3333 Burnet Ave, Cincinnati, OH, United States; Cystic Fibrosis Foundation, 4550 Montgomery Ave, Bethesda, MD, United States; Division of Pulmonary Medicine, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH, United States
Patrick Ryan
Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH 45229, United States; Department of Pediatrics, University of Cincinnati, 3333 Burnet Ave, Cincinnati, OH, United States
Rhonda D. Szczesniak
Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH 45229, United States; Department of Pediatrics, University of Cincinnati, 3333 Burnet Ave, Cincinnati, OH, United States; Division of Pulmonary Medicine, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH, United States; Corresponding author at: Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, Cincinnati, OH 45229, United States.
This study develops a comprehensive method to assess seasonal influences on a longitudinal marker and compare estimates between cohorts. The method extends existing approaches by (i) combining a sine-cosine model of seasonality with a specialized covariance function for modeling longitudinal correlation; (ii) performing mediation analysis on a seasonality model. An example dataset and R code are provided. The bundle of methods is referred to as seasonality, mediation and comparison (SMAC). The case study described utilizes lung function as the marker observed on a cystic fibrosis cohort but SMAC can be used to evaluate other markers and in other disease contexts. Key aspects of customization are as follows. • This study introduces a novel seasonality model to fit trajectories of lung function decline and demonstrates how to compare this model to a conventional model in this context. • Steps required for mediation analyses in the seasonality model are shown. • The necessary calculations to compare seasonality models between cohorts, based on estimation coefficients, are derived in the study.
