Development and validation of a prediction model for ED using machine learning: according to NHANES 2001-2004

被引:1
作者
Chen, Xing-Yu [1 ,2 ]
Lu, Wen-Ting [3 ]
Zhang, Di [4 ]
Tan, Mo-Yao [5 ]
Qin, Xin [1 ,2 ]
机构
[1] Chengdu Integrated TCM, Chengdu, Sichuan, Peoples R China
[2] Western Med Hosp, Chengdu, Sichuan, Peoples R China
[3] XinDu Hosp Tradit Chinese Med, Chengdu, Sichuan, Peoples R China
[4] Sichuan Univ, West China Sch Pharm, Chengdu, Sichuan, Peoples R China
[5] Chengdu Univ Tradit Chinese Med, Chengdu, Sichuan, Peoples R China
来源
SCIENTIFIC REPORTS | 2024年 / 14卷 / 01期
关键词
Erectile Dysfunction; Machine learning; XGBoost; National Health and Nutrition Examination Survey; Prediction model; URINARY-TRACT SYMPTOMS; ERECTILE DYSFUNCTION; CARDIOVASCULAR-DISEASE; OXIDATIVE STRESS; NEURAL-NETWORKS; MEN; PREVALENCE; DIAGNOSIS; TESTOSTERONE; CLASSIFICATION;
D O I
10.1038/s41598-024-78797-2
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Erectile Dysfunction (ED) is a form of sexual dysfunction in males that imposes significant health and financial burdens globally. Despite its high prevalence, diagnosing ED remains challenging due to the limitations of current diagnostic methods and patients' reluctance to seek medical help. Currently, some studies have used machine learning techniques for developing ED prediction models, but the performance and interpretability of existing models need to be further improved. This study utilized data from the National Health and Nutrition Examination Survey (NHANES) for the years 2001 to 2004, adhering to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement. After excluding male respondents who did not meet the study criteria, a total of 3,869 participants were included. Gradient boosting decision tree (GBDT) algorithms (XGBoost, CatBoost, LightGBM) were used to develop the ED prediction model. Data preprocessing, feature selection, model evaluation, and interpretability analysis were performed to ensure the reliability and effectiveness of the model. The model evaluation results revealed that the AUC values are XGBoost: 0.887 +/- 0.016; LightGBM: 0.879 +/- 0.016; CatBoost: 0.871 +/- 0.019. The F1-Scores are XGBoost: 0.695 +/- 0.023; LightGBM: 0.681 +/- 0.025; CatBoost: 0.681 +/- 0.025. The Recall values are XGBoost: 0.789 +/- 0.026; LightGBM: 0.739 +/- 0.030; CatBoost: 0.711 +/- 0.030. These results confirmed that the XGBoost model is the best-performing ED prediction model in this study. Interpretability analysis results of the XGBoost model showed that age, obesity, cardiovascular risk factors, prostate-related diseases, and socioeconomic status are key features for predicting ED, playing a significant role in the ED mechanism. Therefore, we believe the ED prediction model trained in this study has strong predictive performance and high interpretability. This model can help to expand the diagnostic options for ED, improve the diagnosis rate of ED, and assist doctors in early intervention for patients with ED, ultimately improving patient prognosis.
引用
收藏
页数:18
相关论文
共 50 条
  • [41] A Prediction Model for Osteoporosis Risk Using a Machine-Learning Approach and Its Validation in a Large Cohort
    Wu, Xuangao
    Park, Sunmin
    [J]. JOURNAL OF KOREAN MEDICAL SCIENCE, 2023, 38 (21)
  • [42] Development and external validation of a machine learning model to predict bronchopulmonary dysplasia using dynamic factors
    Ho Jung Choi
    Garam Lee
    Seung Han Shin
    Seung Mi Lee
    Hyung-Chul Lee
    Jin A. Sohn
    Jin A. Lee
    Han-suk Kim
    [J]. Scientific Reports, 15 (1)
  • [43] Development and validation of a multivariate predictive model for rheumatoid arthritis mortality using a machine learning approach
    Lezcano-Valverde, Jose M.
    Salazar, Fernando
    Leon, Leticia
    Toledano, Esther
    Jover, Juan A.
    Fernandez-Gutierrez, Benjamin
    Soudah, Eduardo
    Gonzalez-Alvaro, Isidoro
    Abasolo, Lydia
    Rodriguez-Rodriguez, Luis
    [J]. SCIENTIFIC REPORTS, 2017, 7
  • [44] Development of a Nurse Turnover Prediction Model in Korea Using Machine Learning
    Kim, Seong-Kwang
    Kim, Eun-Joo
    Kim, Hye-Kyeong
    Song, Sung-Sook
    Park, Bit-Na
    Jo, Kyoung-Won
    [J]. HEALTHCARE, 2023, 11 (11)
  • [45] Development and Validation of a Machine Learning-Based Nomogram for Prediction of Ankylosing Spondylitis
    Jichong Zhu
    Qing Lu
    Tuo Liang
    Hao JieJiang
    Chenxin Li
    Shaofeng Zhou
    Tianyou Wu
    Jiarui Chen
    Guobing Chen
    Yuanlin Deng
    Shian Yao
    Chaojie Liao
    Shengsheng Yu
    Xuhua Huang
    Liyi Sun
    Wenkang Chen
    Zhen Chen
    Hao Ye
    Wuhua Guo
    Wenyong Chen
    Binguang Jiang
    Xiang Fan
    Xinli Tao
    Chong Zhan
    [J]. Rheumatology and Therapy, 2022, 9 : 1377 - 1397
  • [46] Prediction of postpartum depression in women: development and validation of multiple machine learning models
    Qi, Weijing
    Wang, Yongjian
    Wang, Yipeng
    Huang, Sha
    Li, Cong
    Jin, Haoyu
    Zuo, Jinfan
    Cui, Xuefei
    Wei, Ziqi
    Guo, Qing
    Hu, Jie
    [J]. JOURNAL OF TRANSLATIONAL MEDICINE, 2025, 23 (01) : 291
  • [47] Development and validation of a machine learning model for prediction of comorbid major depression disorder among narcolepsy type 1
    Pan, Yuanhang
    Zhang, Xinbo
    Wen, Xinyu
    Yuan, Na
    Guo, Li
    Shi, Yifan
    Jia, Yuanyuan
    Guo, Yanzhao
    Hao, Fengli
    Qu, Shuyi
    Chen, Ze
    Yang, Lei
    Wang, Xiaoli
    Liu, Yonghong
    [J]. SLEEP MEDICINE, 2024, 119 : 556 - 564
  • [48] Cardiovascular complications in a diabetes prediction model using machine learning: a systematic review
    Kee, Ooi Ting
    Harun, Harmiza
    Mustafa, Norlaila
    Murad, Nor Azian Abdul
    Chin, Siok Fong
    Jaafar, Rosmina
    Abdullah, Noraidatulakma
    [J]. CARDIOVASCULAR DIABETOLOGY, 2023, 22 (01)
  • [49] A Machine Learning Approach for the Prediction of Testicular Sperm Extraction in Nonobstructive Azoospermia: Algorithm Development and Validation Study
    Bachelot, Guillaume
    Dhombres, Ferdinand
    Sermondade, Nathalie
    Hamid, Rahaf Haj
    Berthaut, Isabelle
    Frydman, Valentine
    Prades, Marie
    Kolanska, Kamila
    Selleret, Lise
    Mathieu-D'Argent, Emmanuelle
    Rivet-Danon, Diane
    Levy, Rachel
    Lamaziere, Antonin
    Dupont, Charlotte
    [J]. JOURNAL OF MEDICAL INTERNET RESEARCH, 2023, 25
  • [50] Cardiovascular complications in a diabetes prediction model using machine learning: a systematic review
    Ooi Ting Kee
    Harmiza Harun
    Norlaila Mustafa
    Nor Azian Abdul Murad
    Siok Fong Chin
    Rosmina Jaafar
    Noraidatulakma Abdullah
    [J]. Cardiovascular Diabetology, 22