Estimating the risk of brain metastasis for patients newly diagnosed with cancer

Joseph A Miccio ¹, Zizhong Tian ², Sean S Mahase ¹

¹Department of Radiation Oncology, Penn State Cancer Institute, Hershey, PA, USA.
²Division of Biostatistics and Bioinformatics, Department of Public Health Sciences, Penn State College of Medicine, Hershey, PA, USA.
³Department of Radiation Oncology, University Hospitals Seidman Cancer Center, Case Western Reserve School of Medicine, Cleveland, OH, USA.
⁴Department of Neurosurgery, Penn State Cancer Institute, Hershey, PA, USA.
⁵Department of Neurosurgery, University of Virginia School of Medicine, Charlottesville, VA, USA.
⁶Department of Radiation Oncology, Mayo Clinic, Rochester, MN, USA.
⁷Department of Radiation Oncology, Mayo Clinic, Jacksonville, FL, USA.
⁸Department of Radiation Oncology, The Ohio State University James Comprehensive Cancer Center, Columbus, OH, USA.
⁹Department of Population and Quantitative Health Sciences, Case Western Reserve University School of Medicine, Cleveland, OH, USA.
¹⁰Department of Radiation Oncology, University Hospitals Seidman Cancer Center, Case Western Reserve School of Medicine, Cleveland, OH, USA. Nicholas.Zaorsky@UHhospitals.org.

⁰Department of Radiation Oncology, Penn State Cancer Institute, Hershey, PA, USA.

Communications Medicine +

|

February 22, 2024

View abstract on PubMed

Summary

Accurate models predict brain metastasis risk at diagnosis for common cancers. These tools, including nomograms and a web tool, can help clinicians decide on brain MRI screening for newly diagnosed patients.

Area Of Science

Oncology
Radiology
Biostatistics

Background

Brain metastases (BM) significantly impact cancer patient prognosis and management.
Limited resources exist for estimating BM risk in newly diagnosed patients.
Current guidelines for brain MRI screening are often insufficient.

Purpose Of The Study

To develop and validate predictive models for brain metastasis (BM) risk at the time of initial cancer diagnosis.
To identify key variables associated with BM at diagnosis for common brain-metastasizing cancers.
To create accessible tools (nomograms, web tool) for clinical use.

Main Methods

Utilized data from 4,828,305 patients across six cancer types (breast, melanoma, kidney, CRC, SCLC, NSCLC) from the National Cancer Database (2010-2018).
Developed multivariable logistic regression (LR) models to predict BM risk.
Evaluated model performance using Area Under the Receiver Operating Characteristic Curve (AUC) and random-split validation.

Main Results

BM prevalence at diagnosis varied by cancer type, ranging from 0.3% (breast, CRC) to 16.0% (SCLC).
Developed LR models demonstrated high predictive accuracy, with average AUCs ranging from 0.6180 (SCLC) to 0.9534 (breast cancer).
Created cancer-specific nomograms and a web tool for risk prediction.

Conclusions

Accurate predictive models for brain metastasis risk at diagnosis were successfully developed for multiple cancer types.
The developed nomograms and web tool can assist clinicians in determining the need for brain MRI screening at initial cancer diagnosis.
These tools aim to improve timely detection and management of brain metastases.

Related Concept Videos

Metastasis

Metastasis is the spread of cancer cells from the original site to distant locations in the body. Cancer cells can spread via blood vessels (hematogenous) as well as lymph vessels in the body.
Epithelial-to-Mesenchymal Transition
The epithelial-to-mesenchymal transition or EMT is a developmental process commonly observed in wound healing, embryogenesis, and cancer metastasis. EMT is induced by transforming growth factor-beta (TGF-β) or receptor tyrosine kinase (RTK) ligands, which further...