Meeting Banner
Abstract #3392

Mathematical Modelling of Malignant Transformation in Low Grade Gliomas and survival prediction with XGBoost.

Tan Lily1, James Ruffle1, Sebastian Brandner1, Parashkev Nachev1, and Harpreet Hyare1
1UCL, London, United Kingdom

Synopsis

Keywords: Diagnosis/Prediction, Machine Learning/Artificial Intelligence

Motivation: MRI features associated with malignant transformation (MT) have low specificity and circumscribed by diagnostic errors.

Goal(s): The objective of this study was to develop a non-linear machine learning model to predict overall survival (OS) quantified by known time-to-death data.

Approach: We aimed to assess the prognostic significance of the model inputs and identify the most critical determinants of survival through the model training loop.

Results: The RMSE and MAE values in the testing set indicate that the model predicts time to death with an average deviation of ~2.27 years.

Impact: Prediction of malignant transformation of low grade gliomas will allow precision treatment decisions and personalized medicine.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords