% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Vison:282721,
author = {G. Visonà and L. M. Spiller and S. Hahn and E.
Hattingen$^*$ and T. J. Vogl$^*$ and G. Schweikert and K.
Bankov and M. Demes$^*$ and H. Reis$^*$ and P. Wild$^*$ and
P. S. Zeiner$^*$ and F. Acker$^*$ and M. Sebastian$^*$ and
K. J. Wenger$^*$},
title = {{M}achine-{L}earning-{A}ided {P}rediction of {B}rain
{M}etastases {D}evelopment in {N}on-{S}mall-{C}ell {L}ung
{C}ancers.},
journal = {Clinical lung cancer},
volume = {24},
number = {8},
issn = {1525-7304},
address = {Dallas, Tex.},
publisher = {Cancer Information Group},
reportid = {DKFZ-2023-01847},
pages = {e311-e322},
year = {2023},
note = {2023 Dec;24(8):e311-e322},
abstract = {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:
$sensitivity∼70\%,$ $specificity∼60\%).$ Radiomics
features failed to provide sufficient information, likely
due to the heterogeneity of imaging data. Adenocarcinoma
histology, lymph node invasion, and histological tumor grade
were positively correlated with the prediction of BM, age,
and squamous cell carcinoma histology were negatively
correlated. A subgroup discovery analysis identified 2
candidate patient subpopulations appearing to present a
higher risk of BM (female patients + adenocarcinoma
histology, adenocarcinoma patients + no other distant
metastases).Analysis of the importance of input features
suggests that the models are learning the relevant
relationships between clinical features/development of BM. A
higher number of samples is to be prioritized to improve
performance. Employed prospectively at initial diagnosis,
such models can help select high-risk subgroups for
surveillance brain MRI.},
keywords = {Interpretable machine learning (Other) / NSCLC (Other) /
Predictive models (Other) / Radiomics (Other) / Secondary
brain cancer (Other)},
cin = {FM01},
ddc = {610},
cid = {I:(DE-He78)FM01-20160331},
pnm = {899 - ohne Topic (POF4-899)},
pid = {G:(DE-HGF)POF4-899},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:37689579},
doi = {10.1016/j.cllc.2023.08.002},
url = {https://inrepo02.dkfz.de/record/282721},
}