Machine-Learning-Aided Prediction of Brain Metastases Development in Non-Small-Cell Lung Cancers

PURPOSE

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.

METHODS

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.

RESULTS

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).

CONCLUSION

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.

Computational methods and translational applications for targeted next-generation sequencing platforms

During the past decade, next-generation sequencing (NGS) technologies have become widely adopted in cancer research and clinical care. Common applications within the clinical setting include patient stratification into relevant molecular subtypes, identification of biomarkers of response and resistance to targeted and systemic therapies, assessment of heritable cancer risk based on known pathogenic variants, and longitudinal monitoring of treatment response. The need for efficient downstream processing and reliable interpretation of sequencing data has led to the development of novel algorithms and computational pipelines, as well as structured knowledge bases that link genomic alterations to currently available drugs and ongoing clinical trials. Cancer centers around the world use different types of targeted solid-tissue and blood based NGS assays to analyze the genomic and transcriptomic profile of patients as part of their routine clinical care. Recently, cross-institutional collaborations have led to the creation of large pooled datasets that can offer valuable insights into the genomics of rare cancers.