Post-imaging pulmonary nodule mathematical prediction models: are they clinically relevant?

Johanna Uthoff; Nicholas Koehn; Jared Larson; Samantha K N Dilger; Emily Hammond; Ann Schwartz; Brian Mullan; Rolando Sanchez; Richard M Hoffman; Jessica C Sieren; COPDGene Investigators

doi:10.1007/s00330-019-06168-x

Back

Post-imaging pulmonary nodule mathematical prediction models: are they clinically relevant?

Journal article

Peer reviewed

Post-imaging pulmonary nodule mathematical prediction models: are they clinically relevant?

Johanna Uthoff, Nicholas Koehn, Jared Larson, Samantha K N Dilger, Emily Hammond, Ann Schwartz, Brian Mullan, Rolando Sanchez, Richard M Hoffman, Jessica C Sieren, …

European radiology, Vol.29(10), pp.5367-5377

10/2019

DOI: 10.1007/s00330-019-06168-x

PMCID: PMC6717521

PMID: 30937590

View Online

Abstract

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. A common cohort of 317 individuals with computed tomography-detected, solid nodules (80 malignant, 237 benign) were used to evaluate the MPM performance. We created a web-based application for this study that allows others to easily calibrate thresholds and analyze the performance of MPMs on their local cohort. Thirty patients with repeated imaging were tested for improved performance longitudinally. Using calibrated thresholds, Mayo Clinic and Brock University (BU) MPMs performed the best (AUC = 0.63, 0.61) compared to the Veteran's Affairs (0.51) and Peking University (0.55). Only BU had consensus with the original MPM threshold; the other calibrated thresholds improved MPM accuracy. No significant improvements in accuracy were found longitudinally between time points. Calibration to a common cohort can select the best-performing MPM for your institution. Without calibration, BU has the most stable performance in solid nodules ≥ 8 mm but has only moderate potential to refine subjects into appropriate workup. Application of MPM is recommended only at initial evaluation as no increase in accuracy was achieved over time. • Post-imaging lung cancer risk mathematical predication models (MPMs) perform poorly on local populations without calibration. • An application is provided to facilitate calibration to new study cohorts: the Mayo Clinic model, the U.S. Department of Veteran's Affairs model, the Brock University model, and the Peking University model. • No significant improvement in risk prediction occurred in nodules with repeated imaging sessions, indicating the potential value of risk prediction application is limited to the initial evaluation.

Models, Theoretical

Lung - pathology

Humans

Middle Aged

Tomography, X-Ray Computed - methods

Lung Neoplasms - pathology

Male

Precancerous Conditions - diagnostic imaging

Solitary Pulmonary Nodule - diagnostic imaging

Aged, 80 and over

Adult

Female

Lung Neoplasms - diagnostic imaging

Precancerous Conditions - pathology

Aged

Cohort Studies

Solitary Pulmonary Nodule - pathology

Details

Title: Subtitle: Post-imaging pulmonary nodule mathematical prediction models: are they clinically relevant?
Creators: Johanna Uthoff - Department of Biomedical Engineering, University of Iowa, 5601 Seamans Center, Iowa City, IA, 52242, USA
Nicholas Koehn - Department of Radiology, University of Iowa, 200 Hawkins Drive cc704 GH, Iowa City, IA, 52242, USA
Jared Larson - Department of Radiology, University of Iowa, 200 Hawkins Drive cc704 GH, Iowa City, IA, 52242, USA
Samantha K N Dilger - Department of Biomedical Engineering, University of Iowa, 5601 Seamans Center, Iowa City, IA, 52242, USA
Emily Hammond - Department of Biomedical Engineering, University of Iowa, 5601 Seamans Center, Iowa City, IA, 52242, USA
Ann Schwartz - Karmanos Cancer Institute, Wayne State University, 4100 John R St, Detroit, MI, 48201, USA
Brian Mullan - Department of Radiology, University of Iowa, 200 Hawkins Drive cc704 GH, Iowa City, IA, 52242, USA
Rolando Sanchez - Department of Internal Medicine, University of Iowa, 200 Hawkins Drive, Iowa City, IA, 52242, USA
Richard M Hoffman - Department of Internal Medicine, University of Iowa, 200 Hawkins Drive, Iowa City, IA, 52242, USA
Jessica C Sieren - Department of Biomedical Engineering, University of Iowa, 5601 Seamans Center, Iowa City, IA, 52242, USA. jessica-sieren@uiowa.edu
COPDGene Investigators
Resource Type: Journal article
Publication Details: European radiology, Vol.29(10), pp.5367-5377
DOI: 10.1007/s00330-019-06168-x
PMID: 30937590
PMCID: PMC6717521
NLM abbreviation: Eur Radiol
ISSN: 0938-7994
eISSN: 1432-1084
Grant note: P30 ES005605 / NIEHS NIH HHS U01 HL089897 / NHLBI NIH HHS R01 HL089856 / NHLBI NIH HHS HHSN261201300011I / NIH HHS R01 CA141769 / NCI NIH HHS IGR-77-004-34 / American Cancer Society P30 CA086862 / NCI NIH HHS U01 HL089856 / NHLBI NIH HHS R01CA141769 / NIH HHS S10 OD018526 / NIH HHS P30CA022453 / NIH HHS P30 CA022453 / NCI NIH HHS R01 HL089897 / NHLBI NIH HHS U01-HL089897 / NHLBI NIH HHS U01HL089856 / NHLBI NIH HHS
Language: English
Date published: 10/2019
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Pulmonary, Critical Care, and Occupational Medicine; Epidemiology; General Internal Medicine; Internal Medicine
Record Identifier: 9984094544202771

Metrics

25 Record Views

8 Times Cited - Web of Science