2023 World Conference on Lung Cancer (Posters)-P2.03. Predicting Risk of Distant Brain Failure with Radiosurgery and Systemic Therapy in a Diverse NSCLC Brain Metastasis Population

P2.03. Predicting Risk of Distant Brain Failure with Radiosurgery and Systemic Therapy in a Diverse NSCLC Brain Metastasis Population - PDF(Abstract)

Back to course

Pdf Summary

A study conducted at Miami Cancer Institute aimed to develop a machine-learning algorithm to predict the risk of distant intracranial failure (DIF) in patients with non-small cell lung cancer (NSCLC) brain metastasis. The study included patients treated with stereotactic radiosurgery (SRS) between 2017 and 2021. Data on patient characteristics, treatment details, and outcomes were collected from electronic medical records. Machine-learning analysis was performed to identify factors affecting the risk of DIF, including time to DIF, age, gender, performance score, number of lesions, tumor size, extracranial disease, molecular status, and type of systemic therapy. The data was divided into training and test sets for model development and evaluation. The study included 844 brain metastases in 226 patients, with a median age of 64 and 55% female. Molecular profiling revealed various mutations, and after SRS, 45% of patients received immunotherapy, 34% had targeted therapy, and 40% had chemotherapy. After a median follow-up of 14.5 months, the actuarial 1-year cumulative incidence of DIF was 52.1%. The machine-learning model generated 100 trees and showed an accuracy of 76% in predicting DIF. Factors such as performance score, age, use of immunotherapy, male gender, and use of chemotherapy were found to impact the risk of DIF. The study concluded that the machine-learning model could be useful in predicting intra-cranial tumor control and guiding treatment decisions in NSCLC brain metastasis patients, including considering alternative systemic therapy or whole-brain radiotherapy for high-risk patients.

Asset Subtitle

Rupesh Kotecha

Meta Tag

Speaker Rupesh Kotecha

Topic Metastatic NSCLC: Local Therapies

Keywords

Miami Cancer Institute

machine-learning algorithm

distant intracranial failure

non-small cell lung cancer

NSCLC brain metastasis

stereotactic radiosurgery

patient characteristics

treatment details

electronic medical records

factors affecting risk