Research Paper Volume 13, Issue 5 pp 7361—7381

Artificial intelligence prediction model for overall survival of clear cell renal cell carcinoma based on a 21-gene molecular prognostic score system

Qiliang Peng1,2, *, , Yi Shen3, *, , Kai Fu4, *, , Zheng Dai4, , Lu Jin4, , Dongrong Yang4, , Jin Zhu4, ,

  • 1 Department of Radiotherapy and Oncology, The Second Affiliated Hospital of Soochow University, Suzhou, China
  • 2 Institute of Radiotherapy and Oncology, Soochow University, Suzhou, China
  • 3 Department of Radiation Oncology, The Affiliated Suzhou Science and Technology Town Hospital of Nanjing Medical University, Suzhou, China
  • 4 Department of Urology, The Second Affiliated Hospital of Soochow University, Suzhou, China
* Equal contribution

Received: November 2, 2020       Accepted: January 14, 2021       Published: March 3, 2021
How to Cite

Copyright: © 2021 Peng et al. This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.


We developed and validated a new prognostic model for predicting the overall survival in clear cell renal cell carcinoma (ccRCC) patients. In this study, artificial intelligence (AI) algorithms including random forest and neural network were trained to build a molecular prognostic score (mPS) system. Afterwards, we investigated the potential mechanisms underlying mPS by assessing gene set enrichment analysis, mutations, copy number variations (CNVs) and immune cell infiltration. A total of 275 prognosis-related genes were identified, which were also differentially expressed between ccRCC patients and healthy controls. We then constructed a universal mPS system that depends on the expression status of only 21 of these genes by applying AI-based algorithms. Then, the mPS were validated by another independent cohort and demonstrated to be applicable to ccRCC subsets. Furthermore, a nomogram comprising the mPS score and several independent variables was established and proved to effectively predict ccRCC patient prognosis. Finally, significant differences were identified regarding the pathways, mutated genes, CNVs and tumor-infiltrating immune cells among the subgroups of ccRCC stratified by the mPS system. The AI-based mPS system can provide critical prognostic prediction for ccRCC patients and may be useful to inform treatment and surveillance decisions before initial intervention.


AI: artificial intelligence; mPS: molecular prognostic score; ccRCC: clear cell renal cell carcinoma; AJCC: American Joint Committee on Cancer; TNM: tumor node metastasis; TCGA: The Cancer Genome Atlas; ICGC: International Cancer Genome Consortium; CNVs: copy number variations; UCISS: University of California Integrated Staging System; HR: hazard ratio; CI: confidence interval; GSEA: gene set enrichment analysis; TMB: tumor mutation burden; MCRs: minimal common regions; GISTIC: Genomic Identification of Significant Targets in Cancer.