Machine learning-based survival prediction in colorectal cancer combining clinical and biological features (IMAGE)
Caption
Figure 1: LASSO feature ranking and SHAP explanatory for Cases 1, 2, and 3 feature selection models.
A positive SHAP value indicates a positive impact on prediction, leading the model to predict 1 (Patient survival). A negative value indicates an adverse effect, leading the model to predict 0 (Patient non-survival). The color of the SHAP data points shows the values as a heatmap where blue is the lowest value (e.g., 0) and red is the highest value (e.g., 1). For Cases 1 and 2, pathological stage and E2F8 expression are the most relevant clinical and biological features respectively. On the other hand, for group 3, pathological stage and hsa-miR-495-3p expression are the most relevant features.
Credit
Copyright: © 2025 Vieira et al. This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Usage Restrictions
With credit to the original source.
License
Original content