Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content
Fig. 4 | BMC Medical Informatics and Decision Making

Fig. 4

From: Death risk prediction model for patients with non-traumatic intracerebral hemorrhage

Fig. 4

A. SHAP variable importance chart, displaying the included features arranged in descending order based on their average absolute SHAP values. B and C. SHAP force plots for two cases: Each feature’s contribution is denoted by color, with purple signifying a negative impact on the prediction (indicated by an arrow pointing left, resulting in a decrease in SHAP value), and yellow signifying a positive impact (indicated by an arrow pointing right, increasing in SHAP value). The length of the color bar represents the magnitude of the contribution, while E[f(x)] corresponds to the SHAP reference value, which is the model’s mean prediction. f(x) denotes the individual SHAP value

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us