%0 Journal Article
%A Visonà, Giovanni
%A Spiller, Lisa M
%A Hahn, Sophia
%A Hattingen, Elke
%A Vogl, Thomas J
%A Schweikert, Gabriele
%A Bankov, Katrin
%A Demes, Melanie
%A Reis, Henning
%A Wild, Peter
%A Zeiner, Pia S
%A Acker, Fabian
%A Sebastian, Martin
%A Wenger, Katharina J
%T Machine-Learning-Aided Prediction of Brain Metastases Development in Non-Small-Cell Lung Cancers.
%J Clinical lung cancer
%V 24
%N 8
%@ 1525-7304
%C Dallas, Tex.
%I Cancer Information Group
%M DKFZ-2023-01847
%P e311-e322
%D 2023
%Z 2023 Dec;24(8):e311-e322
%X 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
%K Interpretable machine learning (Other)
%K NSCLC (Other)
%K Predictive models (Other)
%K Radiomics (Other)
%K Secondary brain cancer (Other)
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:37689579
%R 10.1016/j.cllc.2023.08.002
%U https://inrepo02.dkfz.de/record/282721