Open AccessPost-imaging pulmonary nodule mathematical prediction models: are they clinically relevant?
Author(s) -
Johanna Uthoff,
Nicholas Koehn,
Jared Larson,
Samantha K. N. Dilger,
Emily Hammond,
Ann G. Schwartz,
Brian F. Mullan,
Rolando Sanchez,
Richard M. Hoffman,
Jessica C. Sieren,
COPDGene Investigators
Publication year - 2019
Publication title -
european radiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.606
H-Index - 149
eISSN - 1432-1084
pISSN - 0938-7994
DOI - 10.1007/s00330-019-06168-x
Subject(s) - medicine , neuroradiology , lung cancer , calibration , cohort , nodule (geology) , radiology , interventional radiology , medical physics , nuclear medicine , statistics , paleontology , mathematics , neurology , psychiatry , biology
Post-imaging mathematical prediction models (MPMs) provide guidance for the management of solid pulmonary nodules by providing a lung cancer risk score from demographic and radiologists-indicated imaging characteristics. We hypothesized calibrating the MPM risk score threshold to a local study cohort would result in improved performance over the original recommended MPM thresholds. We compared the pre- and post-calibration performance of four MPM models and determined if improvement in MPM prediction occurs as nodules are imaged longitudinally.