TY - JOUR
AU - Visonà, Giovanni
AU - Spiller, Lisa M
AU - Hahn, Sophia
AU - Hattingen, Elke
AU - Vogl, Thomas J
AU - Schweikert, Gabriele
AU - Bankov, Katrin
AU - Demes, Melanie
AU - Reis, Henning
AU - Wild, Peter
AU - Zeiner, Pia S
AU - Acker, Fabian
AU - Sebastian, Martin
AU - Wenger, Katharina J
TI - Machine-Learning-Aided Prediction of Brain Metastases Development in Non-Small-Cell Lung Cancers.
JO - Clinical lung cancer
VL - 24
IS - 8
SN - 1525-7304
CY - Dallas, Tex.
PB - Cancer Information Group
M1 - DKFZ-2023-01847
SP - e311-e322
PY - 2023
N1 - 2023 Dec;24(8):e311-e322
AB - Non-small-cell lung cancer (NSCLC) shows a high incidence of brain metastases (BM). Early detection is crucial to improve clinical prospects. We trained and validated classifier models to identify patients with a high risk of developing BM, as they could potentially benefit from surveillance brain MRI.Consecutive patients with an initial diagnosis of NSCLC from January 2011 to April 2019 and an in-house chest-CT scan (staging) were retrospectively recruited at a German lung cancer center. Brain imaging was performed at initial diagnosis and in case of neurological symptoms (follow-up). Subjects lost to follow-up or still alive without BM at the data cut-off point (12/2020) were excluded. Covariates included clinical and/or 3D-radiomics-features of the primary tumor from staging chest-CT. Four machine learning models for prediction (80/20 training) were compared. Gini Importance and SHAP were used as measures of importance; sensitivity, specificity, area under the precision-recall curve, and Matthew's Correlation Coefficient as evaluation metrics.Three hundred and ninety-five patients compromised the clinical cohort. Predictive models based on clinical features offered the best performance (tuned to maximize recall: sensitivity∼70
KW - Interpretable machine learning (Other)
KW - NSCLC (Other)
KW - Predictive models (Other)
KW - Radiomics (Other)
KW - Secondary brain cancer (Other)
LB - PUB:(DE-HGF)16
C6 - pmid:37689579
DO - DOI:10.1016/j.cllc.2023.08.002
UR - https://inrepo02.dkfz.de/record/282721
ER -