Related Experiment Video
Updated: Aug 20, 2025
Predictive Immune Modeling of Solid Tumors
Published on: February 25, 2020
Artificial intelligence-based immunoprofiling serves as a potentially predictive biomarker of nivolumab treatment for
Jan-Mou Lee1, Yi-Ping Hung2,3, Kai-Yuan Chou3
1FullHope Biomedical Co., Ltd., New Taipei City, Taiwan.
Abstract:
Immune checkpoint inhibitors (ICI) have been applied in treating advanced hepatocellular carcinoma (aHCC) patients, but few patients exhibit stable and lasting responses. Moreover, identifying aHCC patients suitable for ICI treatment is still challenged. This study aimed to evaluate whether dissecting peripheral immune cell subsets by Mann-Whitney U test and artificial intelligence (AI) algorithms could serve as predictive biomarkers of nivolumab treatment for aHCC. Disease control group carried significantly increased percentages of PD-L1+ monocytes, PD-L1+ CD8 T cells, PD-L1+ CD8 NKT cells, and decreased percentages of PD-L1+ CD8 NKT cells via Mann-Whitney U test. By recursive feature elimination method, five featured subsets (CD4 NKTreg, PD-1+ CD8 T cells, PD-1+ CD8 NKT cells, PD-L1+ CD8 T cells and PD-L1+ monocytes) were selected for AI training. The featured subsets were highly overlapping with ones identified via Mann-Whitney U test. Trained AI algorithms committed valuable AUC from 0.8417 to 0.875 to significantly separate disease control group from disease progression group, and SHAP value ranking also revealed PD-L1+ monocytes and PD-L1+ CD8 T cells exclusively and significantly contributed to this discrimination. In summary, the current study demonstrated that integrally analyzing immune cell profiling with AI algorithms could serve as predictive biomarkers of ICI treatment.
Insights
Predicting response to immune checkpoint inhibitors (ICI) in advanced hepatocellular carcinoma (aHCC) is challenging. This study shows that analyzing immune cell subsets using artificial intelligence (AI) can identify patients likely to benefit from ICI treatment.
Area of Science:
- Immunology
- Oncology
- Artificial Intelligence
Background:
- Immune checkpoint inhibitors (ICI) show limited efficacy in advanced hepatocellular carcinoma (aHCC).
- Predicting patient response to ICI therapy remains a significant clinical challenge.
- Novel biomarkers are needed to identify aHCC patients suitable for ICI treatment.
Purpose of the Study:
- To evaluate peripheral immune cell subsets as predictive biomarkers for nivolumab treatment in aHCC.
- To utilize Mann-Whitney U test and artificial intelligence (AI) algorithms for identifying predictive immune cell signatures.
Main Methods:
- Peripheral immune cell subsets were analyzed using Mann-Whitney U test.
- Recursive feature elimination and AI algorithms were employed for feature selection and model training.
- Area Under the Curve (AUC) and SHAP value analysis were used to assess predictive performance.
Main Results:
- Significant differences in PD-L1+ monocyte and PD-L1+ CD8 T cell percentages were observed between disease control and progression groups.
- AI algorithms achieved high AUC values (0.8417-0.875) in distinguishing treatment responders from non-responders.
- PD-L1+ monocytes and PD-L1+ CD8 T cells were identified as key predictive features by SHAP value analysis.
Conclusions:
- Integrally analyzing immune cell profiling with AI algorithms can serve as predictive biomarkers for ICI treatment in aHCC.
- This approach enhances the ability to identify aHCC patients who may benefit from nivolumab therapy.
- AI-driven immune cell profiling offers a promising strategy for personalized medicine in aHCC treatment.
More Related Videos
07:32Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
Published on: April 12, 2024
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
