An Explainable Multimodal Artificial Intelligence Model Integrating Histopathological Microenvironment and EHR Phenotypes for Germline Genetic Testing in Breast Cancer
Abstract Genetic testing for pathogenic germline variants is critical for the personalized management of high‐risk breast cancers, guiding targeted therapies and cascade testing for at‐risk families. In this study, MAIGGT (Multimodal Artificial Intelligence Germline Genetic Testing) is proposed, a d...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-08-01
|
| Series: | Advanced Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/advs.202502833 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849227321483984896 |
|---|---|
| author | Zijian Yang Changyuan Guo Jiayi Li Yalun Li Lei Zhong Pengming Pu Tongxuan Shang Lin Cong Yongxin Zhou Guangdong Qiao Ziqi Jia Hengyi Xu Heng Cao Yansong Huang Tianyi Liu Jian Liang Jiang Wu Dongxu Ma Yuchen Liu Ruijie Zhou Xiang Wang Jianming Ying Meng Zhou Jiaqi Liu |
| author_facet | Zijian Yang Changyuan Guo Jiayi Li Yalun Li Lei Zhong Pengming Pu Tongxuan Shang Lin Cong Yongxin Zhou Guangdong Qiao Ziqi Jia Hengyi Xu Heng Cao Yansong Huang Tianyi Liu Jian Liang Jiang Wu Dongxu Ma Yuchen Liu Ruijie Zhou Xiang Wang Jianming Ying Meng Zhou Jiaqi Liu |
| author_sort | Zijian Yang |
| collection | DOAJ |
| description | Abstract Genetic testing for pathogenic germline variants is critical for the personalized management of high‐risk breast cancers, guiding targeted therapies and cascade testing for at‐risk families. In this study, MAIGGT (Multimodal Artificial Intelligence Germline Genetic Testing) is proposed, a deep learning framework that integrates histopathological microenvironment features from whole‐slide images with clinical phenotypes from electronic health records for precise prescreening of germline BRCA1/2 mutations. Leveraging a multi‐scale Transformer‐based deep generative architecture, MAIGGT employs a cross‐modal latent representation unification mechanism to capture complementary biological insights from multimodal data. MAIGGT is rigorously validated across three independent cohorts and demonstrated robust performance with areas under receiver operating characteristic curves of 0.925 (95% CI 0.868 – 0.982), 0.845 (95% CI 0.779 – 0.911), and 0.833 (0.788 – 0.878), outperforming single‐modality models. Mechanistic interpretability analyses revealed that BRCA1/2‐mutated associated tumors may exhibit distinct microenvironment patterns, including increased inflammatory cell infiltration, stromal proliferation and necrosis, and nuclear heterogeneity. By bridging digital pathology with clinical phenotypes, MAIGGT establishes a new paradigm for cost‐effective, scalable, and biologically interpretable prescreening of hereditary breast cancer, with the potential to significantly improve the accessibility of genetic testing in routine clinical practice. |
| format | Article |
| id | doaj-art-d2b66dc7b9e049dcabea1245982ffd69 |
| institution | Kabale University |
| issn | 2198-3844 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Science |
| spelling | doaj-art-d2b66dc7b9e049dcabea1245982ffd692025-08-23T14:00:56ZengWileyAdvanced Science2198-38442025-08-011231n/an/a10.1002/advs.202502833An Explainable Multimodal Artificial Intelligence Model Integrating Histopathological Microenvironment and EHR Phenotypes for Germline Genetic Testing in Breast CancerZijian Yang0Changyuan Guo1Jiayi Li2Yalun Li3Lei Zhong4Pengming Pu5Tongxuan Shang6Lin Cong7Yongxin Zhou8Guangdong Qiao9Ziqi Jia10Hengyi Xu11Heng Cao12Yansong Huang13Tianyi Liu14Jian Liang15Jiang Wu16Dongxu Ma17Yuchen Liu18Ruijie Zhou19Xiang Wang20Jianming Ying21Meng Zhou22Jiaqi Liu23Institute of Genomic Medicine School of Biomedical Engineering Wenzhou Medical University Wenzhou 325027 ChinaDepartment of Pathology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgery Chinese Academy of Medical Science and Peking Union Medical College Hospital Beijing 100730 ChinaDepartment of Breast Surgery the Affiliated Yantai Yuhuangding Hospital of Qingdao University Yantai 264000 ChinaDepartment of Breast Surgery Sixth Affiliated Hospital of Harbin Medical University Harbin 150023 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgery the Affiliated Yantai Yuhuangding Hospital of Qingdao University Yantai 264000 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaState Key Laboratory of Molecular Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Pathology Second Affiliated Hospital of Harbin Medical University Harbin 150086 ChinaDepartment of Breast Surgery Second Affiliated Hospital of Harbin Medical University Harbin 150086 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaDepartment of Pathology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaInstitute of Genomic Medicine School of Biomedical Engineering Wenzhou Medical University Wenzhou 325027 ChinaDepartment of Breast Surgical Oncology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing 100021 ChinaAbstract Genetic testing for pathogenic germline variants is critical for the personalized management of high‐risk breast cancers, guiding targeted therapies and cascade testing for at‐risk families. In this study, MAIGGT (Multimodal Artificial Intelligence Germline Genetic Testing) is proposed, a deep learning framework that integrates histopathological microenvironment features from whole‐slide images with clinical phenotypes from electronic health records for precise prescreening of germline BRCA1/2 mutations. Leveraging a multi‐scale Transformer‐based deep generative architecture, MAIGGT employs a cross‐modal latent representation unification mechanism to capture complementary biological insights from multimodal data. MAIGGT is rigorously validated across three independent cohorts and demonstrated robust performance with areas under receiver operating characteristic curves of 0.925 (95% CI 0.868 – 0.982), 0.845 (95% CI 0.779 – 0.911), and 0.833 (0.788 – 0.878), outperforming single‐modality models. Mechanistic interpretability analyses revealed that BRCA1/2‐mutated associated tumors may exhibit distinct microenvironment patterns, including increased inflammatory cell infiltration, stromal proliferation and necrosis, and nuclear heterogeneity. By bridging digital pathology with clinical phenotypes, MAIGGT establishes a new paradigm for cost‐effective, scalable, and biologically interpretable prescreening of hereditary breast cancer, with the potential to significantly improve the accessibility of genetic testing in routine clinical practice.https://doi.org/10.1002/advs.202502833BRCA1/2breast cancerdeep learningelectronic health recordstumor microenvironmentwhole‐slide image |
| spellingShingle | Zijian Yang Changyuan Guo Jiayi Li Yalun Li Lei Zhong Pengming Pu Tongxuan Shang Lin Cong Yongxin Zhou Guangdong Qiao Ziqi Jia Hengyi Xu Heng Cao Yansong Huang Tianyi Liu Jian Liang Jiang Wu Dongxu Ma Yuchen Liu Ruijie Zhou Xiang Wang Jianming Ying Meng Zhou Jiaqi Liu An Explainable Multimodal Artificial Intelligence Model Integrating Histopathological Microenvironment and EHR Phenotypes for Germline Genetic Testing in Breast Cancer Advanced Science BRCA1/2 breast cancer deep learning electronic health records tumor microenvironment whole‐slide image |
| title | An Explainable Multimodal Artificial Intelligence Model Integrating Histopathological Microenvironment and EHR Phenotypes for Germline Genetic Testing in Breast Cancer |
| title_full | An Explainable Multimodal Artificial Intelligence Model Integrating Histopathological Microenvironment and EHR Phenotypes for Germline Genetic Testing in Breast Cancer |
| title_fullStr | An Explainable Multimodal Artificial Intelligence Model Integrating Histopathological Microenvironment and EHR Phenotypes for Germline Genetic Testing in Breast Cancer |
| title_full_unstemmed | An Explainable Multimodal Artificial Intelligence Model Integrating Histopathological Microenvironment and EHR Phenotypes for Germline Genetic Testing in Breast Cancer |
| title_short | An Explainable Multimodal Artificial Intelligence Model Integrating Histopathological Microenvironment and EHR Phenotypes for Germline Genetic Testing in Breast Cancer |
| title_sort | explainable multimodal artificial intelligence model integrating histopathological microenvironment and ehr phenotypes for germline genetic testing in breast cancer |
| topic | BRCA1/2 breast cancer deep learning electronic health records tumor microenvironment whole‐slide image |
| url | https://doi.org/10.1002/advs.202502833 |
| work_keys_str_mv | AT zijianyang anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT changyuanguo anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jiayili anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT yalunli anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT leizhong anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT pengmingpu anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT tongxuanshang anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT lincong anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT yongxinzhou anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT guangdongqiao anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT ziqijia anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT hengyixu anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT hengcao anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT yansonghuang anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT tianyiliu anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jianliang anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jiangwu anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT dongxuma anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT yuchenliu anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT ruijiezhou anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT xiangwang anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jianmingying anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT mengzhou anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jiaqiliu anexplainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT zijianyang explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT changyuanguo explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jiayili explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT yalunli explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT leizhong explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT pengmingpu explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT tongxuanshang explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT lincong explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT yongxinzhou explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT guangdongqiao explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT ziqijia explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT hengyixu explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT hengcao explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT yansonghuang explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT tianyiliu explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jianliang explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jiangwu explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT dongxuma explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT yuchenliu explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT ruijiezhou explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT xiangwang explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jianmingying explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT mengzhou explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer AT jiaqiliu explainablemultimodalartificialintelligencemodelintegratinghistopathologicalmicroenvironmentandehrphenotypesforgermlinegenetictestinginbreastcancer |