JMIR Publications

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.