An approach for cancer outcomes modelling using a comprehensive synthetic dataset

Limited patient data availability presents a challenge for efficient machine learning (ML) model development. Recent studies have proposed methods to generate synthetic medical images but lack the corresponding prognostic information required for predicting outcomes. We present a cancer outcomes mod...

Full description

Saved in:
Bibliographic Details
Published in:Physical and engineering sciences in medicine Vol. 48; no. 3; pp. 1473 - 1483
Main Authors: Tu, Lorna, Choi, Hervé H. F., Clark, Haley, Lloyd, Samantha A. M.
Format: Journal Article
Language:English
Published: Cham Springer International Publishing 01.09.2025
Subjects:
Aged
AI Notes
Algorithms
Biological and Medical Physics
Biomedical and Life Sciences
Biomedical Engineering and Bioengineering
Biomedicine
Biophysics
Carcinoma, Non-Small-Cell Lung - diagnostic imaging
Female
Humans
Lung Neoplasms - diagnostic imaging
Machine Learning
Male
Medical and Radiation Physics
Middle Aged
Prognosis
Support Vector Machine
Tomography, X-Ray Computed
Treatment Outcome
Data augmentation
Overall survival
Outcomes prediction
Non-small cell lung cancer
Synthetic data
Radiomics
ISSN:2662-4729, 2662-4737, 2662-4737
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Limited patient data availability presents a challenge for efficient machine learning (ML) model development. Recent studies have proposed methods to generate synthetic medical images but lack the corresponding prognostic information required for predicting outcomes. We present a cancer outcomes modelling approach that involves generating a comprehensive synthetic dataset which can accurately mimic a real dataset. A real public dataset containing computed tomography-based radiomic features and clinical information for 132 non-small cell lung cancer patients was used. A synthetic dataset of virtual patients was synthesized using a conditional tabular generative adversarial network. Models to predict two-year overall survival were trained on real or synthetic data using combinations of four feature selection methods (mutual information, ANOVA F-test, recursive feature elimination, random forest (RF) importance weights) and six ML algorithms (RF, k-nearest neighbours, logistic regression, support vector machine, XGBoost, Gaussian Naïve Bayes). Models were tested on withheld real data and externally validated. Real and synthetic datasets were similar, with an average one minus Kolmogorov–Smirnov test statistic of 0.871 for continuous features. Chi-square test confirmed agreement for discrete features ( p  < 0.001). XGBoost using RF importance-based features performed the most consistently for both datasets, with percent differences in balanced accuracy and area under the precision-recall curve of < 1.3%. Preliminary findings demonstrate the potential application of synthetic radiomic and clinical data augmentation for cancer outcomes modelling, although further validation with larger diverse datasets is crucial. While our approach was described in a lung context, it may be applied to other sites or endpoints.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2662-4729
2662-4737
2662-4737
DOI:10.1007/s13246-025-01594-2