Survival Analysis (Time to Event)
Survival analysis predicts the time it will take for an event to occur based on the occurrence of past events. Survival analysis is challenged by the presence of censored data, events that have not occurred yet, but might in the future. In the case study we provide here, we are predicting the survival of Low Grade Glioma (LGG) patients based on a variety of clinical data and the expression of microRNA.
Reading the Molecular Labels in Cancer
Predicting survival time in Low-grade glioma (LGG) patients is difficult. Current prognostic indicators, such as patient age, tumor size and location, do not explain the survival differences seen in LGG patients.
One of the unique capabilities of JADBio is to predict Survival, even when samples are few, features are many, and the data is highly censored. All of these challenges are present in this study, which identifies miRNA expression levels that predict survival in LGG patients.
Read more: Low-grade Gliomas
Applying just the basic Preliminary analysis, JADBio analyzed the expression data from 621 miRNAs and 501 tumor profiles. The analysis involved the testing and optimizing of hyperparameters in 30 models in just 14 seconds. The resulting Best Performing model has a concordance Index of 0.768 with confidence intervals between [ 0.690, 0.842 ]. Kaplan-Meir visualizations split the patients into two, three, or more risk groups based on the 14 selected most predictive features. This automated analysis corroborates the findings of Forst’s publication, cited above.
OTHER
Do you have questions?
JADBio can meet your needs. Ask one of our experts for an interactive demo.
Stay connected to get our news first!
Do you have questions?
JADBio can meet your needs. Ask one of our experts for an interactive demo.
Join the JADai Community!
Sign up with a FREE Basic plan! Be part of a growing community of AutoML enthusiasts
GET STARTED
