JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Can we predict overall survival using machine learning algorithms at 3-months for brain metastases from non-small cell lung cancer after gamma knife radiosurgery?

  • 0Department of Neurosurgery, Gamma Knife Icon Center, Chungbuk National University Hospital, Cheongju, Republic of Korea.
Medicine +

|

February 2, 2024

|

February 2, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

Machine learning accurately predicts 3-month survival for non-small cell lung cancer patients after Gamma Knife radiosurgery (GRKS). Old age and large tumor volume indicate higher mortality risk, potentially avoiding overtreatment with GRKS.

Area Of Science

  • Oncology
  • Medical Physics
  • Artificial Intelligence

Background

  • Gamma Knife radiosurgery (GRKS) is a common treatment for brain metastases.
  • Predicting overall survival (OS) within 3 months post-GRKS for non-small cell lung cancer (NSCLC) patients remains challenging.
  • A significant percentage of NSCLC patients experience mortality within 8 weeks post-GRKS, suggesting potential overtreatment.

Purpose Of The Study

  • To develop machine learning (ML) models for predicting 3-month OS in NSCLC patients undergoing GRKS.
  • To identify key prognostic features influencing survival post-GRKS in NSCLC patients.

Main Methods

  • 120 NSCLC patients who underwent GRKS were analyzed.
  • Data was split into training (n=80) and testing (n=40) sets with 14 features.
  • Three ML algorithms (Decision Tree, Random Forest, Boosted Tree) were employed to predict 3-month OS.

Main Results

  • The Decision Tree algorithm achieved the highest prediction accuracy at 77.5%.
  • Key predictors identified included age, chemotherapy status, and pretreatment.
  • Tumor volume (>10 cc) and age (>71 years) were critical factors for 3-month mortality.

Conclusions

  • ML algorithms can effectively predict 3-month OS in NSCLC patients post-GRKS.
  • Identifying high-risk patients (older age, larger tumor volume) can help personalize treatment decisions.
  • GRKS may not be suitable for NSCLC patients with poor prognoses, advanced age, and large tumor volumes.

Related Concept Videos

Cancer Survival Analysis 01:21

348

Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...

Kaplan-Meier Approach 01:24

141

The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...

Comparing the Survival Analysis of Two or More Groups 01:20

188

Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...