Related Experiment Video

Updated: Jun 10, 2026

Testing Targeted Therapies in Cancer using Structural DNA Alteration Analysis and Patient-Derived Xenografts
10:27

Testing Targeted Therapies in Cancer using Structural DNA Alteration Analysis and Patient-Derived Xenografts

Published on: July 25, 2020

7.8K

Artificial Intelligence-Powered Human Epidermal Growth Factor Receptor 2 Quantification and Clinical Outcomes in

Hongsik Kim1, Chiyoon Oum2, Soo Ick Cho2

  • 1Division of Hematology-Oncology, Department of Internal Medicine, Chungbuk National University Hospital, Chungbuk National University College of Medicine, Cheongju, South Korea.

JCO Precision Oncology
|October 2, 2025
PubMed
Abstract

Insights

Artificial intelligence (AI) can precisely define human epidermal growth factor receptor 2 (HER2) positivity in biliary tract cancer (BTC), improving treatment outcomes. This AI approach offers a better biomarker than traditional methods for predicting response to HER2-targeted therapies.

Area of Science:

  • Oncology
  • Biomarker Discovery
  • Artificial Intelligence in Medicine

Background:

  • Current guidelines lack clear thresholds for human epidermal growth factor receptor 2 (HER2) positivity in biliary tract cancer (BTC).
  • Anti-HER2 therapies have advanced treatment for HER2-positive BTC, but precise patient selection remains a challenge.

Purpose of the Study:

  • To investigate the utility of artificial intelligence (AI) in analyzing HER2 expression and immune phenotypes (IP) for HER2-positive BTC patients receiving anti-HER2 therapy.
  • To establish AI-driven thresholds for HER2 positivity to predict treatment response.

Main Methods:

  • Post hoc analysis of a phase II trial (KCSG HB19-14) involving trastuzumab plus FOLFOX for HER2-positive BTC.
  • AI-powered quantification of HER2 expression and immune profiling on whole-slide images of pretreatment tumor samples.
  • Evaluation of clinical outcomes based on AI-defined HER2 positivity and spatial distribution of tumor-infiltrating lymphocytes.

Main Results:

  • AI-defined HER2 positivity (≥30% tumor cell proportion) significantly predicted improved progression-free survival (6.7 vs 4.9 months) and overall survival (not reached vs 8.4 months) with trastuzumab plus FOLFOX.
  • Traditional pathologist-based scoring did not stratify outcomes, unlike the AI-based continuous scoring system.
  • AI immune profiling indicated distinct immune phenotypes between HER2 3+ (immune-desert) and HER2 2+ (inflamed) tumors, suggesting implications for immunotherapy efficacy.

Conclusions:

  • AI-powered HER2 quantification offers a refined biomarker for predicting response to HER2-targeted therapies in BTC, proposing a ≥30% HER2 3+ tumor cell proportion threshold.
  • Findings suggest potential for combining anti-HER2 therapy with immune checkpoint inhibitors, guided by AI-derived immune profiling.

More Related Videos

Quantifying Antibody-Dependent Cellular Cytotoxicity in a Tumor Spheroid Model: Application for Drug Discovery13:19

Quantifying Antibody-Dependent Cellular Cytotoxicity in a Tumor Spheroid Model: Application for Drug Discovery

Published on: April 26, 2024

3.8K
Validated Immunochemical Assay for Comprehensive Determination of the Human Epidermal Growth Factor Receptor 2 Released from and Bound to Cells08:28

Validated Immunochemical Assay for Comprehensive Determination of the Human Epidermal Growth Factor Receptor 2 Released from and Bound to Cells

Published on: May 9, 2025

687

Related Concept Videos

Pharmacogenetics of Drug Targets: β₂-Adrenergic Receptors, Apo E, Thymidylate Synthase01:11

Pharmacogenetics of Drug Targets: β₂-Adrenergic Receptors, Apo E, Thymidylate Synthase

Genetic polymorphisms in drug targets have emerged as critical determinants of interindividual variability in drug response and toxicity. Pharmacogenomic investigations increasingly focus on identifying these variations to personalize and optimize therapeutic interventions. A drug target may be a receptor, enzyme, or signaling protein involved in pharmacologic responses or disease-related pathways. While early pharmacogenetic studies focused primarily on drug metabolism, current research...