TY - JOUR
T1 - The Thoracic Research Evaluation and Treatment 2.0 Model
T2 - A Lung Cancer Prediction Model for Indeterminate Nodules Referred for Specialist Evaluation
AU - Godfrey, Caroline M.
AU - Shipe, Maren E.
AU - Welty, Valerie F.
AU - Maiga, Amelia W.
AU - Aldrich, Melinda C.
AU - Montgomery, Chandler
AU - Crockett, Jerod
AU - Vaszar, Laszlo T.
AU - Regis, Shawn
AU - Isbell, James M.
AU - Rickman, Otis B.
AU - Pinkerman, Rhonda
AU - Lambright, Eric S.
AU - Nesbitt, Jonathan C.
AU - Maldonado, Fabien
AU - Blume, Jeffrey D.
AU - Deppen, Stephen A.
AU - Grogan, Eric L.
N1 - Publisher Copyright:
© 2023
PY - 2023/11
Y1 - 2023/11
N2 - Background: Appropriate risk stratification of indeterminate pulmonary nodules (IPNs) is necessary to direct diagnostic evaluation. Currently available models were developed in populations with lower cancer prevalence than that seen in thoracic surgery and pulmonology clinics and usually do not allow for missing data. We updated and expanded the Thoracic Research Evaluation and Treatment (TREAT) model into a more generalized, robust approach for lung cancer prediction in patients referred for specialty evaluation. Research Question: Can clinic-level differences in nodule evaluation be incorporated to improve lung cancer prediction accuracy in patients seeking immediate specialty evaluation compared with currently available models? Study Design and Methods: Clinical and radiographic data on patients with IPNs from six sites (N = 1,401) were collected retrospectively and divided into groups by clinical setting: pulmonary nodule clinic (n = 374; cancer prevalence, 42%), outpatient thoracic surgery clinic (n = 553; cancer prevalence, 73%), or inpatient surgical resection (n = 474; cancer prevalence, 90%). A new prediction model was developed using a missing data-driven pattern submodel approach. Discrimination and calibration were estimated with cross-validation and were compared with the original TREAT, Mayo Clinic, Herder, and Brock models. Reclassification was assessed with bias-corrected clinical net reclassification index and reclassification plots. Results: Two-thirds of patients had missing data; nodule growth and fluorodeoxyglucose-PET scan avidity were missing most frequently. The TREAT version 2.0 mean area under the receiver operating characteristic curve across missingness patterns was 0.85 compared with that of the original TREAT (0.80), Herder (0.73), Mayo Clinic (0.72), and Brock (0.68) models with improved calibration. The bias-corrected clinical net reclassification index was 0.23. Interpretation: The TREAT 2.0 model is more accurate and better calibrated for predicting lung cancer in high-risk IPNs than the Mayo, Herder, or Brock models. Nodule calculators such as TREAT 2.0 that account for varied lung cancer prevalence and that consider missing data may provide more accurate risk stratification for patients seeking evaluation at specialty nodule evaluation clinics.
AB - Background: Appropriate risk stratification of indeterminate pulmonary nodules (IPNs) is necessary to direct diagnostic evaluation. Currently available models were developed in populations with lower cancer prevalence than that seen in thoracic surgery and pulmonology clinics and usually do not allow for missing data. We updated and expanded the Thoracic Research Evaluation and Treatment (TREAT) model into a more generalized, robust approach for lung cancer prediction in patients referred for specialty evaluation. Research Question: Can clinic-level differences in nodule evaluation be incorporated to improve lung cancer prediction accuracy in patients seeking immediate specialty evaluation compared with currently available models? Study Design and Methods: Clinical and radiographic data on patients with IPNs from six sites (N = 1,401) were collected retrospectively and divided into groups by clinical setting: pulmonary nodule clinic (n = 374; cancer prevalence, 42%), outpatient thoracic surgery clinic (n = 553; cancer prevalence, 73%), or inpatient surgical resection (n = 474; cancer prevalence, 90%). A new prediction model was developed using a missing data-driven pattern submodel approach. Discrimination and calibration were estimated with cross-validation and were compared with the original TREAT, Mayo Clinic, Herder, and Brock models. Reclassification was assessed with bias-corrected clinical net reclassification index and reclassification plots. Results: Two-thirds of patients had missing data; nodule growth and fluorodeoxyglucose-PET scan avidity were missing most frequently. The TREAT version 2.0 mean area under the receiver operating characteristic curve across missingness patterns was 0.85 compared with that of the original TREAT (0.80), Herder (0.73), Mayo Clinic (0.72), and Brock (0.68) models with improved calibration. The bias-corrected clinical net reclassification index was 0.23. Interpretation: The TREAT 2.0 model is more accurate and better calibrated for predicting lung cancer in high-risk IPNs than the Mayo, Herder, or Brock models. Nodule calculators such as TREAT 2.0 that account for varied lung cancer prevalence and that consider missing data may provide more accurate risk stratification for patients seeking evaluation at specialty nodule evaluation clinics.
KW - lung cancer
KW - lung nodule
KW - prediction model
UR - http://www.scopus.com/inward/record.url?scp=85175184327&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85175184327&partnerID=8YFLogxK
U2 - 10.1016/j.chest.2023.06.009
DO - 10.1016/j.chest.2023.06.009
M3 - Article
C2 - 37421973
AN - SCOPUS:85175184327
SN - 0012-3692
VL - 164
SP - 1305
EP - 1314
JO - Chest
JF - Chest
IS - 5
ER -