Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants

Xiangjun Qi; Shujing Wang; Caishan Fang; Jie Jia; Lizhu Lin; Tianhui Yuan

doi:10.1016/j.redox.2024.103470

Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants

Redox Biol. 2024 Dec 16:79:103470. doi: 10.1016/j.redox.2024.103470. Online ahead of print.

Authors

Xiangjun Qi¹, Shujing Wang¹, Caishan Fang², Jie Jia³, Lizhu Lin⁴, Tianhui Yuan⁵

Affiliations

¹ The First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, 510000, China.
² Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu, 610031, China; Yong Loo Lin School of Medicine, National University of Singapore, 117597, Singapore.
³ The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, 510405, China; Guangdong Clinical Research Academy of Chinese Medicine, Guangzhou, 510405, China; Kolling Institute of Medical Research, University of Sydney, Sydney, NSW, 2065, Australia.
⁴ The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, 510405, China; Guangdong Clinical Research Academy of Chinese Medicine, Guangzhou, 510405, China. Electronic address: gzucmlinlz@163.com.
⁵ The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, 510405, China; Guangdong Clinical Research Academy of Chinese Medicine, Guangzhou, 510405, China. Electronic address: laura.yth@hotmail.com.

PMID: 39700695
DOI: 10.1016/j.redox.2024.103470

Abstract

Objective: To develop and validate a machine learning model incorporating dietary antioxidants to predict cardiovascular disease (CVD)-cancer comorbidity and to elucidate the role of antioxidants in disease prediction.

Methods: Data were sourced from the National Health and Nutrition Examination Survey. Antioxidants, including vitamins, minerals, and polyphenols, were selected as key features. Additionally, demographic, lifestyle, and health condition features were incorporated to improve model accuracy. Feature preprocessing included removing collinear features, addressing class imbalance, and normalizing data. Models constructed within the mlr3 framework included recursive partitioning and regression trees, random forest, kernel k-nearest neighbors, naïve bayes, and light gradient boosting machine (LightGBM). Benchmarking provided a systematic approach to evaluating and comparing model performance. SHapley Additive exPlanation (SHAP) values were calculated to determine the prediction role of each feature in the model with the highest predictive performance.

Results: This analysis included 10,064 participants, with 353 identified as having comorbid CVD and cancer. After excluding collinear features, the machine learning model retained 29 dietary antioxidant features and 9 baseline features. LightGBM achieved the highest predictive accuracy at 87.9 %, a classification error rate of 12.1 %, and the top area under the receiver operating characteristic curve (0.951) and the precision-recall curve (0.930). LightGBM also demonstrated balanced sensitivity and specificity, both close to 88 %. SHAP analysis indicated that naringenin, magnesium, theaflavin, kaempferol, hesperetin, selenium, malvidin, and vitamin C were the most influential contributors.

Conclusion: LightGBM exhibited the best performance for predicting CVD-cancer comorbidity. SHAP values highlighted the importance of antioxidants, with naringenin and magnesium emerging as primary factors in this model.

Keywords: Cancer; Cardiovascular disease; Dietary antioxidants; Machine learning; SHAP.