Match!

Construction of longitudinal prediction targets using semisupervised learning

Published on Sep 1, 2018in Statistical Methods in Medical Research2.39
· DOI :10.1177/0962280216684163
Booil Jo31
Estimated H-index: 31
(Stanford University),
Robert L. Findling71
Estimated H-index: 71
(Johns Hopkins University)
+ 8 AuthorsSarah M. Horwitz45
Estimated H-index: 45
(NYU: New York University)
Cite
Abstract
In establishing prognostic models, often aided by machine learning methods, much effort is concentrated in identifying good predictors. However, the same level of rigor is often absent in improving the outcome side of the models. In this study, we focus on this rather neglected aspect of model development. We are particularly interested in the use of longitudinal information as a way of improving the outcome side of prognostic models. This involves optimally characterizing individuals’ outcome status, classifying them, and validating the formulated prediction targets. None of these tasks are straightforward, which may explain why longitudinal prediction targets are not commonly used in practice despite their compelling benefits. As a way of improving this situation, we explore the joint use of empirical model fitting, clinical insights, and cross-validation based on how well formulated targets are predicted by clinically relevant baseline characteristics (antecedent validators). The idea here is that all ...
  • References (25)
  • Citations (3)
Cite
References25
Newest
#1Chen Pin Wang (University of Texas Health Science Center at San Antonio)H-Index: 17
#2Booil Jo (Stanford University)H-Index: 31
Last.C. Hendricks Brown (NU: Northwestern University)H-Index: 46
view all 3 authors...
#1Robert L. Findling (Johns Hopkins University)H-Index: 71
#2Booil Jo (Stanford University)H-Index: 31
Last.David Axelson (University of Pittsburgh)H-Index: 59
view all 10 authors...
#1Gareth M. JamesH-Index: 23
#2Daniela WittenH-Index: 31
Last.Robert TibshiraniH-Index: 124
view all 4 authors...
#1Laura B. Dunn (UCSF: University of California, San Francisco)H-Index: 36
#2Bruce A. Cooper (UCSF: University of California, San Francisco)H-Index: 48
Last.Christine Miaskowski (UCSF: University of California, San Francisco)H-Index: 70
view all 10 authors...
#1Robert L. Findling (Case Western Reserve University)H-Index: 71
#2Eric A. Youngstrom (UNC: University of North Carolina at Chapel Hill)H-Index: 59
Last.Christine Demeter (Case Western Reserve University)H-Index: 25
view all 10 authors...
#1Sarah McCue Horwitz (Stanford University)H-Index: 23
#2Christine Demeter (Case Western Reserve University)H-Index: 25
Last.Robert A. Kowatch (Cincinnati Children's Hospital Medical Center)H-Index: 34
view all 10 authors...
#1Hanno Petras (UMD: University of Maryland, College Park)H-Index: 20
#2Katherine E. Masyn (UC Davis: University of California, Davis)H-Index: 23
#1Niklaus Stulz (UPenn: University of Pennsylvania)H-Index: 13
#2Michael E. Thase (UPenn: University of Pennsylvania)H-Index: 112
Last.Paul Crits-Christoph (UPenn: University of Pennsylvania)H-Index: 58
view all 5 authors...
View next paperBuilding and Interpreting Risk Models from Imbalanced Clinical Data