Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Mar 30, 2025
Date Accepted: Jul 31, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Deep Learning for Predicting Colorectal Cancer Patients’ Overall Survival: An IGHT (Image Generator for Health Tabular Data) Approach
ABSTRACT
Background:
Artificial Intelligence (AI) has shown great potential in aiding clinicians with medical decision-making by leveraging patient data.
Objective:
In this study, we aimed to develop and evaluate deep learning-based models for predicting survival using data from colorectal cancer patients.
Methods:
In this study, we present a novel approach for predicting patient survival in colorectal cancer using the Image Generator Health Tabular (IGHT) data. By transforming tabular data into image data using IGHT, we employ deep learning models to enhance performance. Colorectal cancer patients were categorized into colon cancer and rectal cancer groups based on tumor site, and three state-of-the-art models—Artificial Neural Network (ANN), Convolutional Neural Network (CNN), and VGG16 (a transfer learning model based on CNN)—were utilized for analysis.
Results:
Our results demonstrate that the VGG16 model outperforms other models, achieving a survival prediction rate of 78.44% for colon cancer and 74.83% for rectal cancer. Additionally, we employ Grad-CAM to calculate and visualize individual patient risk factors as images.
Conclusions:
It is worth noting that future studies incorporating standardized multicenter Electronic Medical Record (EMR) datasets can potentially yield more generalizable research outcomes. Our findings represent a significant step towards the implementation of personalized medicine, leveraging the power of AI and machine learning techniques.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.