Machine learning analysis for detecting late recurrence and loss to follow‐up after renal cell carcinoma surgery

Abstract Objectives Renal cell carcinoma (RCC) is shown to have a tendency for late recurrence, occurring 5 or more years after curative surgery. Imaging diagnosis is required for follow‐up, and there is no definitive answer as to how long this should continue. Some patients discontinue follow‐up vi...

Full description

Saved in:
Bibliographic Details
Main Authors: Kodai Sato, Tomokazu Sazuka, Takayuki Arai, Hiroaki Sato, Manato Kanesaka, Keisuke Ando, Shinpei Saito, Sangjon Pae, Yasutaka Yamada, Yusuke Imamura, Shinichi Sakamoto, Tomohiko Ichikawa
Format: Article
Language:English
Published: Wiley 2024-10-01
Series:BJUI Compass
Subjects:
Online Access:https://doi.org/10.1002/bco2.425
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846110560338313216
author Kodai Sato
Tomokazu Sazuka
Takayuki Arai
Hiroaki Sato
Manato Kanesaka
Keisuke Ando
Shinpei Saito
Sangjon Pae
Yasutaka Yamada
Yusuke Imamura
Shinichi Sakamoto
Tomohiko Ichikawa
author_facet Kodai Sato
Tomokazu Sazuka
Takayuki Arai
Hiroaki Sato
Manato Kanesaka
Keisuke Ando
Shinpei Saito
Sangjon Pae
Yasutaka Yamada
Yusuke Imamura
Shinichi Sakamoto
Tomohiko Ichikawa
author_sort Kodai Sato
collection DOAJ
description Abstract Objectives Renal cell carcinoma (RCC) is shown to have a tendency for late recurrence, occurring 5 or more years after curative surgery. Imaging diagnosis is required for follow‐up, and there is no definitive answer as to how long this should continue. Some patients discontinue follow‐up visits at their own discretion. How best to predict late recurrence and loss to follow‐up (LF) remains unclear. Patients and methods This study targeted patients diagnosed with non‐metastatic RCC who underwent either radical or partial nephrectomy at Chiba University Hospital between 1988 and 2021. Follow‐up for patients with RCC is typically lifelong. We used random survival forests (RSFs), a machine learning‐based survival analysis method, to predict late recurrence and LF. For verification of prediction accuracy, we applied the time‐dependent area under the receiver operating characteristic curve (t‐AUC). To analyse the risks of late recurrence and LF, SurvSHAP(t) and partial dependence plots were used. Results We analysed 1051 cases in this study. Median follow‐up was 58.5 (range: 0–376) months. The predictive accuracy of recurrence using RSF was t‐AUC 0.806, 0.761, 0.674 and 0.566 at 60, 120, 180 and 240 months postoperatively, respectively. The recurrence risk impact showed a time‐dependent increase up to approximately 50 months postoperatively. Beyond 50 months, there were no distinct risk factors characteristic of late recurrence. The predictive accuracy of LF using RSF was t‐AUC 0.542, 0.699, 0.685, 0.628 and 0.674 at 60, 120, 180, 240 and 300 months postoperatively, respectively. The risk of LF increased with advancing age beyond 70 years. Conclusion It is difficult to identify factors that predict late recurrence. For long‐term follow‐up observation, it is essential to pay particular attention to patients with RCC aged 70 years and above. Establishing frameworks to facilitate collaboration with local hospitals near patients' residences and providing care within the community is necessary.
format Article
id doaj-art-b275577542f14d42916a6fbdce0eb5a3
institution Kabale University
issn 2688-4526
language English
publishDate 2024-10-01
publisher Wiley
record_format Article
series BJUI Compass
spelling doaj-art-b275577542f14d42916a6fbdce0eb5a32024-12-24T02:30:44ZengWileyBJUI Compass2688-45262024-10-015101064107010.1002/bco2.425Machine learning analysis for detecting late recurrence and loss to follow‐up after renal cell carcinoma surgeryKodai Sato0Tomokazu Sazuka1Takayuki Arai2Hiroaki Sato3Manato Kanesaka4Keisuke Ando5Shinpei Saito6Sangjon Pae7Yasutaka Yamada8Yusuke Imamura9Shinichi Sakamoto10Tomohiko Ichikawa11Department of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanDepartment of Urology, Graduate School of Medicine Chiba University Chiba JapanAbstract Objectives Renal cell carcinoma (RCC) is shown to have a tendency for late recurrence, occurring 5 or more years after curative surgery. Imaging diagnosis is required for follow‐up, and there is no definitive answer as to how long this should continue. Some patients discontinue follow‐up visits at their own discretion. How best to predict late recurrence and loss to follow‐up (LF) remains unclear. Patients and methods This study targeted patients diagnosed with non‐metastatic RCC who underwent either radical or partial nephrectomy at Chiba University Hospital between 1988 and 2021. Follow‐up for patients with RCC is typically lifelong. We used random survival forests (RSFs), a machine learning‐based survival analysis method, to predict late recurrence and LF. For verification of prediction accuracy, we applied the time‐dependent area under the receiver operating characteristic curve (t‐AUC). To analyse the risks of late recurrence and LF, SurvSHAP(t) and partial dependence plots were used. Results We analysed 1051 cases in this study. Median follow‐up was 58.5 (range: 0–376) months. The predictive accuracy of recurrence using RSF was t‐AUC 0.806, 0.761, 0.674 and 0.566 at 60, 120, 180 and 240 months postoperatively, respectively. The recurrence risk impact showed a time‐dependent increase up to approximately 50 months postoperatively. Beyond 50 months, there were no distinct risk factors characteristic of late recurrence. The predictive accuracy of LF using RSF was t‐AUC 0.542, 0.699, 0.685, 0.628 and 0.674 at 60, 120, 180, 240 and 300 months postoperatively, respectively. The risk of LF increased with advancing age beyond 70 years. Conclusion It is difficult to identify factors that predict late recurrence. For long‐term follow‐up observation, it is essential to pay particular attention to patients with RCC aged 70 years and above. Establishing frameworks to facilitate collaboration with local hospitals near patients' residences and providing care within the community is necessary.https://doi.org/10.1002/bco2.425late recurrenceloss to follow‐upmachine learningrandom survival forestsrenal cell carcinoma
spellingShingle Kodai Sato
Tomokazu Sazuka
Takayuki Arai
Hiroaki Sato
Manato Kanesaka
Keisuke Ando
Shinpei Saito
Sangjon Pae
Yasutaka Yamada
Yusuke Imamura
Shinichi Sakamoto
Tomohiko Ichikawa
Machine learning analysis for detecting late recurrence and loss to follow‐up after renal cell carcinoma surgery
BJUI Compass
late recurrence
loss to follow‐up
machine learning
random survival forests
renal cell carcinoma
title Machine learning analysis for detecting late recurrence and loss to follow‐up after renal cell carcinoma surgery
title_full Machine learning analysis for detecting late recurrence and loss to follow‐up after renal cell carcinoma surgery
title_fullStr Machine learning analysis for detecting late recurrence and loss to follow‐up after renal cell carcinoma surgery
title_full_unstemmed Machine learning analysis for detecting late recurrence and loss to follow‐up after renal cell carcinoma surgery
title_short Machine learning analysis for detecting late recurrence and loss to follow‐up after renal cell carcinoma surgery
title_sort machine learning analysis for detecting late recurrence and loss to follow up after renal cell carcinoma surgery
topic late recurrence
loss to follow‐up
machine learning
random survival forests
renal cell carcinoma
url https://doi.org/10.1002/bco2.425
work_keys_str_mv AT kodaisato machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT tomokazusazuka machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT takayukiarai machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT hiroakisato machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT manatokanesaka machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT keisukeando machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT shinpeisaito machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT sangjonpae machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT yasutakayamada machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT yusukeimamura machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT shinichisakamoto machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery
AT tomohikoichikawa machinelearninganalysisfordetectinglaterecurrenceandlosstofollowupafterrenalcellcarcinomasurgery