Prediction of post-nephroureterectomy renal function in non-dialysis upper tract urothelial carcinoma using machine learning with PyCaret and SHAP explanations

被引:0
|
作者
Lee, Hsiang Ying [1 ,2 ,3 ]
Li, Wei-Ming [1 ,2 ,3 ,4 ]
Yeh, Hsin-Chih [1 ,2 ,3 ,5 ]
Wu, Wen-Jeng [1 ,2 ,3 ]
Li, Ching-Chia [1 ,2 ,3 ,4 ]
Ke, Hung-Lung [1 ,2 ,3 ,5 ]
Wang, Yen-Chun [1 ,6 ]
机构
[1] Kaohsiung Med Univ Hosp, Dept Urol, 100 Shih Chuan 1st Rd, Kaohsiung 807, Taiwan
[2] Kaohsiung Med Univ, Coll Med, Sch Med, Dept Urol, Kaohsiung 807, Taiwan
[3] Kaohsiung Med Univ, Grad Inst Clin Med, Coll Med, Kaohsiung 807, Taiwan
[4] Kaohsiung Med Univ, Dept Urol, Gangshan Hosp, Kaohsiung 820, Taiwan
[5] Ta Tung Hosp, Dept Urol, Kaohsiung Municipal, Kaohsiung, Taiwan
[6] Natl Cheng Kung Univ, Coll Med, Dept Publ Hlth, Tainan 701, Taiwan
关键词
prediction of renal function; upper tract urothelial carcinoma; machine learning; RADICAL NEPHROURETERECTOMY; FUNCTION DECLINE; OUTCOMES;
D O I
10.3892/ol.2025.14946
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Renal function after radical nephroureterectomy (RNU) in patients with advanced upper tract urothelial carcinoma (UTUC) is an indicator of eligibility for postoperative chemotherapy. The present study aimed to utilize machine learning for predicting renal function status after RNU and to investigate the contribution of several features to this prediction. The present retrospective study included 764 medical records of patients with non-metastatic UTUC who received RNU from 2008 to 2022. The records were divided into training (n=534) and testing (n=230) datasets. Several demographic and clinicopathological parameters were collected for analysis. PyCaret was utilized for data processing, model establishment and comparison, while SHapley Additive exPlanations values were adopted to assess the contribution of each variable to the predictive performance of the model. The results demonstrated that the Random Forest Regressor model had improved accuracy in predicting postoperative renal function compared with other algorithms. In both the estimated glomerular filtration rate (eGFR) and chronic kidney disease outcome, preoperative renal function had the most marked contribution to postoperative renal function. Additionally, the Charlson Comorbidity Index (CCI), body mass index (BMI) and tumor size were highly associated with renal function after RNU, and hydronephrosis was another main factor for predicting postoperative eGFR. The retrospective design was a limitation of the present study. The results demonstrated that important predictors, including preoperative eGFR, tumor size, BMI, CCI and hydronephrosis, were associated with postoperative renal function. To conclude, using a machine learning prediction model may be used in the future to determine appropriate therapeutic strategies and inform the timing of perioperative systemic chemotherapy, in particular perioperative systemic chemotherapy, for advanced UTUC.
引用
收藏
页数:10
相关论文
共 45 条
  • [41] Radiomics-based machine learning approach for the prediction of grade and stage in upper urinary tract urothelial carcinoma: a step towards virtual biopsy
    Alqahtani, Abdulsalam
    Bhattacharjee, Sourav
    Almopti, Abdulrahman
    Li, Chunhui
    Nabi, Ghulam
    INTERNATIONAL JOURNAL OF SURGERY, 2024, 110 (06) : 3258 - 3268
  • [42] Post-operative urothelial recurrence in patients with upper urinary tract urothelial carcinoma managed by radical nephroureterectomy with an ipsilateral bladder cuff: Minimal prognostic impact in comparison with non-urothelial recurrence and other clinical indicators
    Takahara, Kiyoshi
    Inamoto, Teruo
    Komura, Kazumasa
    Watsuji, Toshikazu
    Azuma, Haruhito
    ONCOLOGY LETTERS, 2013, 6 (04) : 1015 - 1020
  • [43] Prediction of post-donation renal function using machine learning techniques and conventional regression models in living kidney donors
    Jeon, Junseok
    Song, Yeejun
    Yu, Jae Yong
    Jung, Weon
    Lee, Kyungho
    Lee, Jung Eun
    Huh, Wooseong
    Cha, Won Chul
    Jang, Hye Ryoun
    JOURNAL OF NEPHROLOGY, 2024, 37 (06) : 1679 - 1687
  • [44] New classification of hydronephrosis on 18F-FDG-PET/CT predicts post-operative renal function and muscle-invasive disease in patients with upper urinary tract urothelial carcinoma
    Asai, Seiji
    Fukumoto, Tetsuya
    Watanabe, Ryuta
    Koyama, Kanae
    Sawada, Yuichiro
    Noda, Terutaka
    Miura, Noriyoshi
    Yanagihara, Yutaka
    Miyauchi, Yuki
    Miyagawa, Masao
    Kikugawa, Tadahiko
    Saika, Takashi
    JAPANESE JOURNAL OF CLINICAL ONCOLOGY, 2018, 48 (11) : 1022 - 1027
  • [45] Re: Thomas Seisen, Benoit Peyronnet, Jose Luis Dominguez-Escrig, et al. Oncologic Outcomes of Kidney-sparing Surgery Versus Radical Nephroureterectomy for Upper Tract Urothelial Carcinoma: A Systematic Review by the EAU Non-muscle Invasive Bladder Cancer Guidelines Panel. Eur Urol 2016; 70: 1052-68 Preoperative Bladder Cancer History and Chronic Kidney Disease Are Associated with Occult Renal Pelvis Cancer in Preoperative Solitary Ureteral Cancer
    Luo, Hao Lun
    Chen, Yen Ta
    Cheng, Yuan Tso
    Chiang, Po Hui
    EUROPEAN UROLOGY, 2017, 71 (04) : E109 - E110