Identification of predictive subphenotypes for clinical outcomes using real world data and machine learning
Weishen Pan1, Deep Hathi2, Zhenxing Xu1
1Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, USA.
Nature Communications
|May 12, 2025
Summary
This study introduces Graph-Encoded Mixture Survival (GEMS) to identify patient subphenotypes for predicting treatment response in advanced non-small cell lung cancer (aNSCLC). GEMS improves overall survival (OS) prediction and reveals distinct patient groups for personalized therapy.
Area of Science:
- Oncology
- Bioinformatics
- Machine Learning
Background:
- Predicting treatment response is crucial but challenging due to patient heterogeneity.
- Existing unsupervised machine learning methods for electronic health record (EHR) data lack guaranteed outcome coherence within patient clusters.
- Identifying distinct patient subphenotypes is key to understanding and managing treatment variability.
Purpose of the Study:
- To develop a machine learning framework, Graph-Encoded Mixture Survival (GEMS), for identifying predictive subphenotypes with coherent survival outcomes.
- To apply GEMS to advanced non-small cell lung cancer (aNSCLC) patients receiving first-line immune checkpoint inhibitor (ICI) therapy.
- To improve the prediction of overall survival (OS) and understand treatment response heterogeneity.
Main Methods:
- Proposed Graph-Encoded Mixture Survival (GEMS), a novel machine learning framework.
- Utilized a real-world dataset of advanced non-small cell lung cancer (aNSCLC) patients undergoing first-line immune checkpoint inhibitor (ICI) therapy.
- Employed GEMS to identify distinct patient subphenotypes based on EHR data and predict overall survival (OS).
Main Results:
- GEMS outperformed baseline methods in predicting overall survival (OS).
- Identified three reproducible subphenotypes within the aNSCLC patient cohort.
- These subphenotypes exhibited distinct baseline clinical characteristics and differential OS outcomes.
Conclusions:
- GEMS effectively identifies predictive subphenotypes, addressing heterogeneity in treatment response.
- The identified subphenotypes offer insights into treatment variability for advanced non-small cell lung cancer (aNSCLC) patients.
- This approach has the potential to inform and personalize immune checkpoint inhibitor (ICI) therapy selection.
More Related Videos
Related Concept Videos
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
106
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
106
01:21Cancer Survival Analysis
311
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...
311
01:24Kaplan-Meier Approach
62
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,...
62
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
19
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
19