OpenLB
Open Library of Bioscience
Advanced Search
Frontiers in public health
2022;10 1015952.

Bone metastasis risk and prognosis assessment models for kidney cancer based on machine learning.

Lichen Ji, Wei Zhang, Jiaqing Huang, Jinlong Tian, Xugang Zhong, Junchao Luo, Senbo Zhu, Zeju He, Yu Tong, Xiang Meng, Yao Kang, Qing Bi
Author Information
  1. Lichen Ji: Cancer Center, Department of Orthopedics, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  2. Wei Zhang: Department of Laboratory Medicine, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  3. Jiaqing Huang: Department of Laboratory Medicine, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  4. Jinlong Tian: Cancer Center, Department of Orthopedics, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  5. Xugang Zhong: Department of Laboratory Medicine, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  6. Junchao Luo: Cancer Center, Department of Orthopedics, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  7. Senbo Zhu: Cancer Center, Department of Orthopedics, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  8. Zeju He: Cancer Center, Department of Orthopedics, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  9. Yu Tong: Cancer Center, Department of Orthopedics, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  10. Xiang Meng: Cancer Center, Department of Orthopedics, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  11. Yao Kang: Cancer Center, Department of Orthopedics, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
  12. Qing Bi: Cancer Center, Department of Orthopedics, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
PMID: 36466509 DOI: 10.3389/fpubh.2022.1015952

Abstract

Background: Bone metastasis is a common adverse event in kidney cancer, often resulting in poor survival. However, tools for predicting KCBM and assessing survival after KCBM have not performed well.
Methods: The study uses machine learning to build models for assessing kidney cancer bone metastasis risk, prognosis, and performance evaluation. We selected 71,414 kidney cancer patients from SEER database between 2010 and 2016. Additionally, 963 patients with kidney cancer from an independent medical center were chosen to validate the performance. In the next step, eight different machine learning methods were applied to develop KCBM diagnosis and prognosis models while the risk factors were identified from univariate and multivariate logistic regression and the prognosis factors were analyzed through Kaplan-Meier survival curve and Cox proportional hazards regression. The performance of the models was compared with current models, including the logistic regression model and the AJCC TNM staging model, applying receiver operating characteristics, decision curve analysis, and the calculation of accuracy and sensitivity in both internal and independent external cohorts.
Results: Our prognosis model achieved an AUC of 0.8269 (95%CI: 0.8083-0.8425) in the internal validation cohort and 0.9123 (95%CI: 0.8979-0.9261) in the external validation cohort. In addition, we tested the performance of the extreme gradient boosting model through decision curve analysis curve, Precision-Recall curve, and Brier score and two models exhibited excellent performance.
Conclusion: Our developed models can accurately predict the risk and prognosis of KCBM and contribute to helping improve decision-making.

Keywords

bone metastasis diagnosis kidney cancer machine learning predicting model prognosis

References

Int J Mol Sci. 2016 Jun 22;17(6): [PMID: 27338367]
Ann Oncol. 2012 Apr;23(4):973-80 [PMID: 21890909]
Pain. 1997 Jan;69(1-2):1-18 [PMID: 9060007]
Front Oncol. 2021 Nov 25;11:731905 [PMID: 34900681]
CA Cancer J Clin. 2021 May;71(3):209-249 [PMID: 33538338]
Comput Struct Biotechnol J. 2014 Nov 15;13:8-17 [PMID: 25750696]
Nat Rev Urol. 2010 May;7(5):245-57 [PMID: 20448658]
Eur Urol. 2015 Jan;67(1):85-97 [PMID: 24857407]
Comput Math Methods Med. 2022 Oct 3;2022:5676570 [PMID: 36226243]
Am J Transl Res. 2021 Sep 15;13(9):10248-10261 [PMID: 34650694]
N Engl J Med. 2019 Apr 4;380(14):1347-1358 [PMID: 30943338]
Int J Med Inform. 2021 Jan;145:104326 [PMID: 33197878]
Eur J Surg Oncol. 2019 Jul;45(7):1246-1252 [PMID: 30760414]
Cancer Treat Rev. 2012 Jun;38(4):284-91 [PMID: 21802857]
Trends Cancer. 2015 Sep;1(1):76-91 [PMID: 28741564]
Cell Death Dis. 2018 Jan 5;9(1):3 [PMID: 29305594]
Entropy (Basel). 2019 Feb 28;21(3): [PMID: 33266949]
Int J Oncol. 2009 Apr;34(4):881-95 [PMID: 19287945]
Sci Transl Med. 2017 Jul 5;9(397): [PMID: 28679654]
Circulation. 2015 Nov 17;132(20):1920-30 [PMID: 26572668]
Int J Oncol. 2001 Aug;19(2):379-82 [PMID: 11445855]
Lancet Oncol. 2014 Apr;15(4):e170-7 [PMID: 24694640]
Ann N Y Acad Sci. 2010 Jun;1198:173-81 [PMID: 20536932]
Int Braz J Urol. 2021 Mar-Apr;47(2):333-349 [PMID: 33284535]
Eur Urol. 2018 Mar;73(3):311-315 [PMID: 29223605]
Eur Urol. 2022 Oct;82(4):399-410 [PMID: 35346519]
Nat Rev Urol. 2018 Aug;15(8):511-521 [PMID: 29904105]
Nat Rev Urol. 2020 Mar;17(3):137-150 [PMID: 32020040]
Asia Pac J Clin Oncol. 2010 Mar;6(1):5-18 [PMID: 20398033]
Int J Environ Res Public Health. 2021 Nov 30;18(23): [PMID: 34886378]
J Urol. 2011 May;185(5):1611-4 [PMID: 21419440]
Front Endocrinol (Lausanne). 2022 Mar 09;12:752176 [PMID: 35356148]
Cancers (Basel). 2021 Dec 01;13(23): [PMID: 34885164]
Comput Biol Med. 2021 Sep;136:104770 [PMID: 34426170]
Reg Anesth Pain Med. 2021 Sep;46(9):779-783 [PMID: 34266992]
Methods Mol Biol. 2007;404:273-301 [PMID: 18450055]
Nat Rev Cancer. 2009 Apr;9(4):274-84 [PMID: 19308067]
Nat Biotechnol. 2006 Dec;24(12):1565-7 [PMID: 17160063]
Clin Cancer Res. 2006 Oct 15;12(20 Pt 2):6243s-6249s [PMID: 17062708]
Front Oncol. 2020 Feb 07;10:71 [PMID: 32117728]
Annu Rev Physiol. 2013;75:685-705 [PMID: 23140366]
Ann Oncol. 2014 Sep;25 Suppl 3:iii124-37 [PMID: 24782453]
Pathol Oncol Res. 2010 Mar;16(1):29-38 [PMID: 19639393]
Cold Spring Harb Perspect Med. 2020 Sep 1;10(9): [PMID: 31615864]
Mult Scler. 2021 Jul;27(8):1240-1249 [PMID: 33263261]
J Urol. 2014 Jun;191(6):1678-84 [PMID: 24384157]
Cancer Manag Res. 2021 Nov 23;13:8723-8736 [PMID: 34849027]
Cancers (Basel). 2020 Mar 05;12(3): [PMID: 32150991]
J Natl Compr Canc Netw. 2020 Sep;18(9):1160-1170 [PMID: 32886895]

MeSH Term

Humans
Prognosis
Kidney Neoplasms
Machine Learning
Logistic Models
Kaplan-Meier Estimate
Journal Article Research Support, Non-U.S. Gov't

Word Cloud

Similar Articles

Cited By