Cancer Metastasis Prediction and Genomic Biomarker Identification through Machine Learning and eXplainable Artificial Intelligence in Breast Cancer Research

被引:5
|
作者
Yagin, Burak [1 ]
Yagin, Fatma Hilal [1 ]
Colak, Cemil [1 ]
Inceoglu, Feyza [2 ]
Kadry, Seifedine [3 ,4 ,5 ]
Kim, Jungeun [6 ]
机构
[1] Inonu Univ, Fac Med, Dept Biostat & Med Informat, TR-44280 Malatya, Turkiye
[2] Malatya Turgut Ozal Univ, Fac Med, Dept Biostat, TR-44090 Malatya, Turkiye
[3] Noroff Univ Coll, Dept Appl Data Sci, N-4612 Kristiansand, Norway
[4] Ajman Univ, Artificial Intelligence Res Ctr AIRC, Ajman 346, U Arab Emirates
[5] Lebanese Amer Univ, Dept Elect & Comp Engn, Byblos 36, Lebanon
[6] Kongju Natl Univ, Dept Software, Cheonan 31080, South Korea
关键词
breast cancer metastasis; machine learning algorithms; genomic biomarkers; eXplainable artificial intelligence; SHAP; EXPRESSION; ASSOCIATION; PROGNOSIS;
D O I
10.3390/diagnostics13213314
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Aim: Method: This research presents a model combining machine learning (ML) techniques and eXplainable artificial intelligence (XAI) to predict breast cancer (BC) metastasis and reveal important genomic biomarkers in metastasis patients. Method: A total of 98 primary BC samples was analyzed, comprising 34 samples from patients who developed distant metastases within a 5-year follow-up period and 44 samples from patients who remained disease-free for at least 5 years after diagnosis. Genomic data were then subjected to biostatistical analysis, followed by the application of the elastic net feature selection method. This technique identified a restricted number of genomic biomarkers associated with BC metastasis. A light gradient boosting machine (LightGBM), categorical boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Gradient Boosting Trees (GBT), and Ada boosting (AdaBoost) algorithms were utilized for prediction. To assess the models' predictive abilities, the accuracy, F1 score, precision, recall, area under the ROC curve (AUC), and Brier score were calculated as performance evaluation metrics. To promote interpretability and overcome the "black box" problem of ML models, a SHapley Additive exPlanations (SHAP) method was employed. Results: The LightGBM model outperformed other models, yielding remarkable accuracy of 96% and an AUC of 99.3%. In addition to biostatistical evaluation, in XAI-based SHAP results, increased expression levels of TSPYL5, ATP5E, CA9, NUP210, SLC37A1, ARIH1, PSMD7, UBQLN1, PRAME, and UBE2T (p <= 0.05) were found to be associated with an increased incidence of BC metastasis. Finally, decreased levels of expression of CACTIN, TGFB3, SCUBE2, ARL4D, OR1F1, ALDH4A1, PHF1, and CROCC (p <= 0.05) genes were also determined to increase the risk of metastasis in BC. Conclusion: The findings of this study may prevent disease progression and metastases and potentially improve clinical outcomes by recommending customized treatment approaches for BC patients.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Explainable artificial intelligence for microbiome data analysis in colorectal cancer biomarker identification
    Novielli, Pierfrancesco
    Romano, Donato
    Magarelli, Michele
    Di Bitonto, Pierpaolo
    Diacono, Domenico
    Chiatante, Annalisa
    Lopalco, Giuseppe
    Sabella, Daniele
    Venerito, Vincenzo
    Filannino, Pasquale
    Bellotti, Roberto
    De Angelis, Maria
    Iannone, Florenzo
    Tangaro, Sabina
    [J]. FRONTIERS IN MICROBIOLOGY, 2024, 15
  • [2] Explainable artificial intelligence for machine learning prediction of bandgap energies
    Masuda, Taichi
    Tanabe, Katsuaki
    [J]. Journal of Applied Physics, 2024, 136 (17)
  • [3] Advances in Machine Learning and Explainable Artificial Intelligence for Depression Prediction
    Byeon, Haewon
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2023, 14 (06) : 520 - 526
  • [4] Explainable machine learning of the breast cancer staging for designing smart biomarker sensors
    Idrees, Muhammad
    Sohail, Ayesha
    [J]. Sensors International, 2022, 3
  • [5] Morphological and molecular breast cancer profiling through explainable machine learning
    Alexander Binder
    Michael Bockmayr
    Miriam Hägele
    Stephan Wienert
    Daniel Heim
    Katharina Hellweg
    Masaru Ishii
    Albrecht Stenzinger
    Andreas Hocke
    Carsten Denkert
    Klaus-Robert Müller
    Frederick Klauschen
    [J]. Nature Machine Intelligence, 2021, 3 : 355 - 366
  • [6] Morphological and molecular breast cancer profiling through explainable machine learning
    Binder, Alexander
    Bockmayr, Michael
    Hagele, Miriam
    Wienert, Stephan
    Heim, Daniel
    Hellweg, Katharina
    Ishii, Masaru
    Stenzinger, Albrecht
    Hocke, Andreas
    Denkert, Carsten
    Mueller, Klaus-Robert
    Klauschen, Frederick
    [J]. NATURE MACHINE INTELLIGENCE, 2021, 3 (04) : 355 - 366
  • [7] A novel machine learning prediction model for metastasis in breast cancer
    Li, Huan
    Liu, Ren-Bin
    Long, Chen-meng
    Teng, Yuan
    Liu, Yu
    [J]. CANCER REPORTS, 2024, 7 (03)
  • [8] Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review
    Ghasemi, Amirehsan
    Hashtarkhani, Soheil
    Schwartz, David L.
    Shaban-Nejad, Arash
    [J]. CANCER INNOVATION, 2024, 3 (05):
  • [9] Analyzing breast cancer invasive disease event classification through explainable artificial intelligence
    Massafra, Raffaella
    Fanizzi, Annarita
    Amoroso, Nicola
    Bove, Samantha
    Comes, Maria Colomba
    Pomarico, Domenico
    Didonna, Vittorio
    Diotaiuti, Sergio
    Galati, Luisa
    Giotta, Francesco
    La Forgia, Daniele
    Latorre, Agnese
    Lombardi, Angela
    Nardone, Annalisa
    Pastena, Maria Irene
    Ressa, Cosmo Maurizio
    Rinaldi, Lucia
    Tamborra, Pasquale
    Zito, Alfredo
    Paradiso, Angelo Virgilio
    Bellotti, Roberto
    Lorusso, Vito
    [J]. FRONTIERS IN MEDICINE, 2023, 10
  • [10] Explainable Machine Learning Explores Association Between Sarcopenia and Breast Cancer Distant Metastasis
    Qi, Hongzhuo
    An, Yunfei
    Hu, Xiaohui
    Miao, Shidi
    Li, Jing
    [J]. IEEE ACCESS, 2023, 11 : 65725 - 65738