A comparison between centralized and asynchronous federated learning approaches for survival outcome prediction using clinical and PET data from non-small cell lung cancer patients
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Federated learning (FL) effectively predicts survival time in non-small cell lung cancer (NSCLC) patients using clinical and PET data. This privacy-preserving approach matches centralized model performance, outperforming single-client methods.
Area Of Science
- Medical Informatics
- Machine Learning in Oncology
- Radiomics
Background
- Survival analysis is crucial for cancer treatment decisions.
- Deep learning (DL) shows promise for survival prediction.
- Integrating multi-institutional data for DL is hindered by privacy concerns.
Purpose Of The Study
- To propose FedSurv, an asynchronous federated learning (FL) framework for survival time prediction.
- To integrate clinical information and positron emission tomography (PET)-based features for improved prediction.
- To address medical data privacy challenges in developing ideal prediction models.
Main Methods
- Developed FedSurv, an asynchronous FL framework utilizing DL for survival prediction.
- Employed two datasets: RNSCLC (public) and CNUHH (in-house) for non-small cell lung cancer (NSCLC) patients.
- Trained DL models on distributed clients, aggregating weights into a global model for enhanced privacy and performance.
Main Results
- FedSurv achieved comparable performance to centralized methods on both RNSCLC and CNUHH datasets.
- The FL approach demonstrated superior survival time prediction accuracy compared to single-client models.
- Evaluated performance using Mean Absolute Error (MAE) and C-Index on independent datasets.
Conclusions
- Federated learning (FL) is feasible and effective for individual survival prediction in NSCLC patients.
- The integration of clinical and PET-based features within an FL framework enhances prediction accuracy.
- This privacy-preserving method facilitates collaborative model development across institutions.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
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...
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...
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,...
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...