Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2021 Nov 2;9(11):e32726. doi: 10.2196/32726

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

©Jeongmin Kim, Hakyung Lim, Jae-Hyeon Ahn, Kyoung Hwa Lee, Kwang Suk Lee, Kyo Chul Koo. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 02.11.2021.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on https://medinform.jmir.org/, as well as this copyright and license information must be included.

PMC Copyright notice

Relationships between each feature and Shapley additive explanations (SHAP) values. Dependence plots for each of the top 9 important features, including patient age, lymphocyte proportion, platelet count, BMI, hematocrit, shortness of breath, sex, body temperature, and heart rate. Each scatter plot shows the impact of each feature on the predictions made by the study model. The x-axis represents the variables’ values, and the y-axis represents their SHAP values. The inflection points indicate the nonlinear impact of a feature on the model’s prediction.